{ "schemaVersion": "deck-intelligence.v1", "id": "019dd923-5e88-73ef-bd59-174b7f7da09c", "slug": "d9ee2fdc0bd7b0ec", "title": "enhaced data extraction using gen ai ey collaboration with wlastic", "subtitle": "EY", "author": "EY", "pageCount": 16, "kind": "consulting-deck", "orientation": "landscape", "aspectRatio": 1.778, "document": { "id": "019dd923-5e88-73ef-bd59-174b7f7da09c", "slug": "d9ee2fdc0bd7b0ec", "title": "enhaced data extraction using gen ai ey collaboration with wlastic", "rawTitle": "enhaced data extraction using gen ai ey collaboration with wlastic", "authorId": "MorganStanley", "authorName": "EY", "authorDisplay": "EY", "kind": { "slug": "consulting-deck", "label": "Consulting deck" }, "sourceType": { "slug": "equity_research", "label": "Equity research" }, "fileName": "enhaced-data-extraction-using-gen-ai-ey-collaboration-with-wlastic.pdf", "sourceUrl": null, "sourceDate": null, "presentationDate": null, "ingestedAt": "2026-04-24 14:50:27+00", "status": "ready", "pageCount": 16, "orientation": "landscape", "aspectRatio": 1.778, "targetCompany": null, "targetTicker": null, "metadata": { "local_root": "/tmp/legacy-images/d9ee2fdc0bd7b0ec", "origin_corpus": "consulting" } }, "coverage": { "pageCount": 16, "pagesIndexed": 16, "pagesWithImages": 16, "pagesWithMetadata": 16, "imageCoveragePct": 100, "metadataCoveragePct": 100, "componentCount": 114, "chartCount": 5, "metricSlides": 0, "toolMatches": 4, "documentToolMatches": 0, "frameworkMatches": 2, "arcMatches": 1, "beatMatches": 5, "loopMatches": 2, "patternMatches": 0, "storymakersMatch": false, "scoreAvailable": true, "reviewAvailable": true, "activistThesisAvailable": false, "pitchdeckMetadataAvailable": false, "pitchdeckProfileAvailable": false }, "blocks": [], "matches": { "arcs": [ { "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null, "categoryName": "Strategy & Business", "categorySlug": "strategy-business" }, "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "evidence": "The deck follows a logical structure, starting with a problem statement, then presenting a solution and evidence to support it", "isPrimary": true, "confidence": 0.8, "extraction": { "at": "2026-07-17 03:16:08.023881+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": "doc-narrative-v1" } } ], "beats": [ { "to": 4, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null, "categoryName": "Strategy & Business", "categorySlug": "strategy-business" }, "from": 3, "name": "Situation & Context", "beatId": "e3077b66-a96d-4be2-9521-145f02396c38", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Situation & Context", "slug": "consultants-gambit-situation-context", "status": "active", "canonId": "019dd9b8-05ae-741b-992d-65ee83c639b3", "version": 1, "description": null }, "evidence": "The deck provides an introduction to the current state and main challenges of data extraction", "position": 0, "isPrimaryArc": true, "parentBeatType": { "name": "Setup", "slug": "setup", "status": "active", "canonId": "019dd9b8-020e-7505-af9b-d9b9a4679bcc", "version": 1, "description": "Where the deck grounds the reader before doing anything else. Almost every arc opens here." }, "alignedBlockIds": null, "matchConfidence": 0.8 }, { "to": 5, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null, "categoryName": "Strategy & Business", "categorySlug": "strategy-business" }, "from": 4, "name": "Problem & Complication", "beatId": "f6422833-097c-4dae-acb2-e12ecb8dc8ea", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Problem & Complication", "slug": "consultants-gambit-problem-complication", "status": "active", "canonId": "019dd9b8-064a-777f-a374-e9a8c43dedd4", "version": 1, "description": null }, "evidence": "The deck highlights the inefficiencies of current data extraction methods", "position": 1, "isPrimaryArc": true, "parentBeatType": { "name": "Complication", "slug": "complication", "status": "active", "canonId": "019dd9b8-0275-7709-b2d6-4f77c3fc7579", "version": 1, "description": "The point in the narrative where the audience should feel discomfort. Required for argumentative arcs." }, "alignedBlockIds": null, "matchConfidence": 0.8 }, { "to": 6, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null, "categoryName": "Strategy & Business", "categorySlug": "strategy-business" }, "from": 5, "name": "Solution & Approach", "beatId": "1efec661-4651-4613-962f-1c8e8166349a", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Solution & Approach", "slug": "consultants-gambit-solution-approach", "status": "active", "canonId": "019dd9b8-071c-7161-9184-580fdac7a4f9", "version": 1, "description": null }, "evidence": "The deck presents Gen AI as a solution to improve data extraction efficiency", "position": 2, "isPrimaryArc": true, "parentBeatType": { "name": "Turn", "slug": "turn", "status": "active", "canonId": "019dd9b8-0396-702b-ac2f-9901f8dd8b54", "version": 1, "description": "The pivot — solution proposed, catalyst introduced, decision made. Common (15/20 arcs) but not universal: Triple-take, AIDA, PAS, Voyage-return and Pixar substitute it with a strong reflection or development beat." }, "alignedBlockIds": null, "matchConfidence": 0.8 }, { "to": 13, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null, "categoryName": "Strategy & Business", "categorySlug": "strategy-business" }, "from": 8, "name": "Evidence & Proof", "beatId": "8c4a78bd-1b53-456f-9179-be874097af96", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Evidence & Proof", "slug": "consultants-gambit-evidence-proof", "status": "active", "canonId": "019dd9b8-07b1-7688-8e1e-7637fec3802a", "version": 1, "description": null }, "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI in data extraction", "position": 3, "isPrimaryArc": true, "parentBeatType": { "name": "Evidence", "slug": "evidence", "status": "active", "canonId": "019dd9b8-03f9-772a-b84a-4f07b415b77a", "version": 1, "description": "A dedicated proof beat exists in only ~4 arcs (Gambit, Sequoia, AIDA, Monroes). Other arcs embed evidence inline within development." }, "alignedBlockIds": null, "matchConfidence": 0.8 }, { "to": 14, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null, "categoryName": "Strategy & Business", "categorySlug": "strategy-business" }, "from": 14, "name": "Impact & Next Steps", "beatId": "04e4435f-987f-49e9-bd77-b8061242e7cf", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Impact & Next Steps", "slug": "consultants-gambit-impact-next-steps", "status": "active", "canonId": "019dd9b8-0849-7728-9ee9-fd1609c4c655", "version": 1, "description": null }, "evidence": "The deck concludes with a call to action and a summary of the benefits of Gen AI in data extraction", "position": 4, "isPrimaryArc": true, "parentBeatType": { "name": "Resolution", "slug": "resolution", "status": "active", "canonId": "019dd9b8-045d-703b-8dd7-e92aba3ba91b", "version": 1, "description": "How the deck ends. Required in 19/20 arcs. The exception (Sparkline) ends with new bliss which is functionally a resolution." }, "alignedBlockIds": null, "matchConfidence": 0.8 } ], "loops": [ { "to": 6, "from": 3, "loop": { "name": "02_pattern_hunter", "slug": "02-pattern-hunter", "status": "active", "bestFor": "Time-pressed audiences, building consensus, when data is strong", "canonId": "019dd956-6695-771a-be2e-f1748ef041a4", "version": 1, "bodyDocId": "019df22a-2420-77be-bc41-ded96d08cb21", "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion", "description": "Group multiple pieces of evidence that together point to a pattern or conclusion", "familyLabel": null, "categoryName": "Logical Reasoning", "categorySlug": "logical-reasoning" }, "matchId": "565e85cb-f579-4e65-a33a-b008d293d5f2", "evidence": "The deck presents a problem statement and a proposed solution using Gen AI", "position": 0, "objective": "Identify patterns in current data extraction methods", "confidence": 0.6, "extraction": { "at": "2026-07-17 03:16:08.283215+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": "doc-narrative-v1" } }, { "to": 13, "from": 8, "loop": { "name": "05_the_reveal", "slug": "05-the-reveal", "status": "active", "bestFor": "Product launches, strategic pivots, unexpected findings", "canonId": "019dd956-67e8-77bc-a867-02c2b36370bd", "version": 1, "bodyDocId": "019df22a-2420-77be-bc41-ded96d08cb21", "structure": "Setup the Question -> Build Suspense -> The Big Reveal", "description": "Build mystery and anticipation, then deliver a surprising or powerful conclusion", "familyLabel": null, "categoryName": "Narrative", "categorySlug": "narrative" }, "matchId": "22c3ec8f-4e2e-4190-bd35-ca7dceee7d84", "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI", "position": 1, "objective": "Reveal the benefits of Gen AI in data extraction", "confidence": 0.7, "extraction": { "at": "2026-07-17 03:16:08.325926+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": "doc-narrative-v1" } } ], "tools": [ { "tool": { "name": "Executive summary", "slug": "executive-summary", "status": "active", "bestFor": null, "canonId": "019dd9e1-4b63-72d5-9734-da757d91ca61", "version": 1, "bodyDocId": null, "description": "A condensed view of the entire argument on a single slide / block.", "familyLabel": null, "categoryName": null, "categorySlug": null }, "agent": null, "layer": "slide", "agents": null, "matchId": "5a33e595-a791-4d39-86db-ad573b89d35f", "evidence": "This slide contains an executive summary.", "pageRefs": null, "priority": null, "whenToUse": null, "confidence": 0.9, "extraction": { "at": "2026-07-16 21:47:59.793221+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": null }, "pageNumber": 2, "whyItWorks": null, "antipattern": null, "cardinality": "common", "narrativePurpose": null }, { "tool": { "name": "Problem Statement Canvas", "slug": "problem-statement-canvas", "status": "active", "bestFor": null, "canonId": "019dd956-839d-744b-ad11-9bf3e3642a18", "version": 1, "bodyDocId": null, "description": "Structured definition of the problem: What? Who? Where? When? Scale?", "familyLabel": null, "categoryName": "Block", "categorySlug": "block" }, "agent": "Architect", "layer": "slide", "agents": [ "Architect" ], "matchId": "049de222-4f62-458a-a13c-46915fc6e68f", "evidence": "The slide describes a specific problem in financial analysis and a proposed solution.", "pageRefs": null, "priority": null, "whenToUse": null, "confidence": 0.5, "extraction": { "at": "2026-07-17 03:19:52.472887+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": null }, "pageNumber": 11, "whyItWorks": null, "antipattern": null, "cardinality": null, "narrativePurpose": null }, { "tool": { "name": "Chart Selection Guide", "slug": "chart-selection-guide", "status": "active", "bestFor": null, "canonId": "019dd956-b1a0-700b-ba17-0e16c4d5bcae", "version": 1, "bodyDocId": null, "description": "Choosing the right chart type for your data and message", "familyLabel": null, "categoryName": "Slide", "categorySlug": "slide" }, "agent": "Designer", "layer": "slide", "agents": [ "Designer" ], "matchId": "ecafc3b4-2d0d-4a8f-92e5-ad01cef7fc66", "evidence": "The slide presents a bar chart comparing the accuracy of EY's solution and a naive approach.", "pageRefs": null, "priority": null, "whenToUse": null, "confidence": 0.7, "extraction": { "at": "2026-07-17 03:19:52.588318+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": null }, "pageNumber": 13, "whyItWorks": null, "antipattern": null, "cardinality": null, "narrativePurpose": null }, { "tool": { "name": "Storytelling: the closing ask", "slug": "closing-ask", "status": "active", "bestFor": null, "canonId": "019df269-24e0-70ab-8dd9-983832c1c665", "version": 1, "bodyDocId": "019df269-24bc-7554-b88d-245127606b8d", "description": "The single most important slide in the deck — after the cover. The final", "familyLabel": "narrative-block", "categoryName": "Narrative & Transformation", "categorySlug": "narrative-transformation" }, "agent": "storyteller", "layer": "slide", "agents": [ "storyteller" ], "matchId": "f44f4c0d-3f02-4ad5-8fd5-f6e230ebc265", "evidence": "The slide is titled 'Conclusion' and presents a summary of the main points.", "pageRefs": null, "priority": null, "whenToUse": null, "confidence": 0.9, "extraction": { "at": "2026-07-17 03:19:52.672921+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": null }, "pageNumber": 14, "whyItWorks": null, "antipattern": null, "cardinality": null, "narrativePurpose": null } ], "frameworks": [ { "matchId": "a0c418cd-09e4-4790-9e56-31d8aad7dfc3", "evidence": "The diagram shows a flow from input reports to output dashboarding/reporting.", "framework": null, "confidence": 0.8, "extraction": { "at": "2026-05-02 18:05:57.403+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "pageNumber": 8, "frameworkName": "process" }, { "matchId": "7611814e-3600-437c-b695-ca00d94267c7", "evidence": "Text explicitly describes RAG process and architecture", "framework": null, "confidence": 1, "extraction": { "at": "2026-05-02 18:06:00.733+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "pageNumber": 9, "frameworkName": "Retrieval-Augmented Generation (RAG)" } ], "patterns": [] }, "storymakers": null, "score": { "backend": "codex", "scoredAt": "2026-05-02 15:01:08.817+00", "subScores": { "scqa_arc": 58, "action_titles": 18, "mece_structure": 60, "closing_strength": 52, "evidence_quality": 76, "clarity_of_thesis": 63, "production_quality": 55, "visual_storytelling": 72 }, "totalScore": 56.75, "coveragePct": 88, "explanations": { "scqa_arc": "Slides 2-4 establish the situation and complication, slides 5-7 move into the answer, and slides 8-13 evidence it, but the implied question is never framed explicitly and the flow reads partly as a technical walkthrough.", "action_titles": "Titles are mostly topic labels rather than insight sentences, for example slide 10 is titled \"Use case implementation evaluation (Cont'd)\" despite containing benchmark evidence of Elastic RAG outperforming Naive RAG.", "mece_structure": "The deck has a logical progression from challenge to retrieval approach to ESG and financial-report use cases, but repeated generic section titles blur boundaries and make the two use-case chapters feel partially overlapping.", "closing_strength": "Slide 14 provides a conclusion and synthesis, but it stops at a broad value statement rather than a specific recommendation, decision request, implementation roadmap, or next steps.", "evidence_quality": "The strongest claims are backed by comparative benchmark charts on slides 10 and 13, including accuracy, relevancy, processing time, and a stated 24% accuracy improvement, though earlier strategic claims rely more on assertion.", "clarity_of_thesis": "The thesis is inferable by slides 2-5 as Gen AI plus Elastic can improve complex financial-services data extraction, but it is not stated as a sharp declarative argument in the opening.", "production_quality": "Production quality appears polished with consistent brand imagery, diagrams, callouts, and footnotes on technical slides, but weak action-title discipline and repeated continuation titles reduce executive readability.", "visual_storytelling": "The deck generally matches tools to messages, using challenge diagrams on slide 4, architecture/process flows on slides 8-9 and 12, and benchmark charts on slides 10 and 13." }, "slidesAnalyzed": 14 }, "review": { "backend": null, "verdict": "A research-paper-styled EY/Elastic case study with a real quantitative payoff buried under topic-label titles and a vacuous conclusion — useful as a counter-example of what action titles and a closing 'R' should fix, not as a Storymakers exemplar.", "reviewedAt": "2026-04-25 04:45:16+00", "slidesSeen": 16, "suggestions": [ "Rewrite the title block: lead slide 1 or slide 2 with the headline answer, e.g. 'EY + Elastic RAG lifts financial-document extraction accuracy by ~24% vs. naive RAG'", "Convert every 'Use case implementation evaluation (Cont'd)' into a declarative action title that states the finding of that page (e.g., 'Elastic RAG beats Naive RAG on context relevancy' for p.10; 'Table summarization unlocks PDF financial reports' for p.11)", "Replace the one-slide 'Conclusion' with a 2–3 slide closing arc: (a) summary of the 24% result, (b) recommended next steps for FS clients, (c) explicit call to action / engagement model" ], "closingScore": 35, "openingScore": 45, "topStrengths": [ "Slide 4 'Current state and main challenges' with its callout ('these challenges highlight the need for a sophisticated solution') sets up a problem-solution tension early", "Slide 10 carries a genuinely insight-bearing callout quantifying that Elastic RAG outperforms Naive RAG on context relevancy — a strong analytical anchor", "Slide 13 surfaces a concrete, headline-worthy result (~24% accuracy improvement) that would make a powerful Storymakers payoff if elevated" ], "topWeaknesses": [ "Seven consecutive slides titled 'Use case implementation evaluation (Cont'd)' (p.8–13) — the canonical anti-pattern for action titles and section structure", "The conclusion (p.14) is a generic motherhood statement with no recommendation, ask, or next steps — Storymakers' R is missing", "Opening five slides defer the thesis; the 24% result and the EY+Elastic recommendation are buried two-thirds of the way through", "No MECE section dividers; the analytical block is a single undifferentiated chain rather than discrete pillars (e.g., Retrieval / Table extraction / Evaluation)" ], "narrativeScore": 55, "pillarCritique": "There are no true section dividers — the deck is a flat sequence where seven consecutive 'Use case implementation evaluation (Cont'd)' slides act as a single undifferentiated topic dump rather than MECE pillars.", "closingCritique": "Slide 14 'Conclusion' offers only a vague platitude ('Gen AI plays a pivotal role in revolutionizing data retrieval') with no recommendation, next steps, or call to action; slides 15-16 are bios and disclaimer, so the deck effectively trails off rather than landing.", "openingCritique": "The first five slides read like a research paper preamble (Cover → Abstract → Introduction → Challenges → 'Gen AI and retrieval strategies'), never leading with the answer or the 24% accuracy headline that ultimately defines the work. Stakes are implied but no thesis is asserted up front.", "extractionSeconds": 78.11755, "narrativeCritique": "The deck loosely follows S→C→A→R (Abstract/Intro → Challenges → Retrieval strategies & implementation → Conclusion), but the analysis act is bloated with seven near-identical 'Use case implementation evaluation (Cont'd)' slides while the resolution shrinks to a single generic 'Conclusion'. The arc is detectable but unbalanced and the tension/complication is weakly drawn.", "titleQualityScore": 20, "titleQualityCritique": "Titles are almost entirely topic labels, not action titles: 'Abstract', 'Introduction', 'Current state and main challenges', 'Conclusion', and the repeated 'Use case implementation evaluation (Cont'd)' tells the reader nothing. The 24% accuracy lift from slide 13 should have been the title." }, "activistThesis": null, "pitchdeck": { "metadata": null, "profile": null }, "slides": [ { "page": 1, "type": "setup", "title": "EY branding present; visual theme is futuristic/AI-focused.", "function": "front_matter", "imagePath": "https://imgproxy.kitesheet.com/9OtclLf_WfYv0o7iptG0Xrd6qCuCkian7XKNbisdL0k/rs:fit:1200:1200:0/q:82/f:webp/czM6Ly9raXRlc2hlZXQvY29ycHVzL3NsaWRlcy9kOWVlMmZkYzBiZDdiMGVjL3AwMDEuanBn", "rawType": "cover", "block": null, "metadata": { "slideType": "cover", "slideTypeCanon": { "name": "Cover", "slug": "cover", "status": "active", "canonId": "019de52d-05f2-729d-9f93-e0504f0a2410", "version": 1, "description": null }, "function": "front_matter", "functionCanon": { "name": "Front matter", "slug": "front_matter", "status": "active", "canonId": "019de52d-133d-73f0-9e26-201eda96b098", "version": 1, "description": null }, "density": "sparse", "densityScore": 20, "componentCount": 5, "textChars": 140, "nDataPoints": 0, "notes": "EY branding present; visual theme is futuristic/AI-focused.", "elementsJson": [ "photo", "logo_grid" ], "confidence": 1, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:56.906+00", "seconds": 2.813, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/1", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-1", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": { "h": 1, "w": 0.6, "x": 0.4, "y": 0 }, "kind": "image", "text": null, "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Illustration", "slug": "illustration", "status": "active", "canonId": "019de52c-fe76-7772-a5ac-c0b7294d7615", "version": 1, "description": null }, "framework": null }, "subkind": "illustration", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:56.906+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "3e1bc967-354e-48a6-8dd9-40fa90c16343", "parentComponentId": null }, { "bbox": { "h": 0.15, "w": 0.08, "x": 0.88, "y": 0.75 }, "kind": "image", "text": null, "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Logo", "slug": "logo", "status": "active", "canonId": "019de52c-fdaf-743d-94c4-d7c6a0e55302", "version": 1, "description": null }, "framework": null }, "subkind": "logo", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:56.906+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "b34e8da1-988c-4efe-9cd1-f52989ec74ce", "parentComponentId": null }, { "bbox": { "h": 0.03, "w": 0.45, "x": 0.04, "y": 0.92 }, "kind": "paragraph", "text": "The better the question. The better the answer. The better the world works.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:56.906+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "69fda262-cee1-483e-9b50-0f6c7b5e6a42", "parentComponentId": null }, { "bbox": { "h": 0.15, "w": 0.3, "x": 0.07, "y": 0.35 }, "kind": "title", "text": "Enhanced Data Extraction using Gen AI", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:56.906+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "a9bf112c-68bc-4b36-b077-86a1547eb74a", "parentComponentId": null }, { "bbox": { "h": 0.05, "w": 0.3, "x": 0.07, "y": 0.55 }, "kind": "title", "text": "EY and Elastic Collaboration", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Subtitle", "slug": "subtitle", "status": "active", "canonId": "019de52c-fb09-739d-900c-815b0d9ac526", "version": 1, "description": null }, "framework": null }, "subkind": "subtitle", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:56.906+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "e7cce2df-ab0a-4d07-b064-a73a3e229137", "parentComponentId": null } ], "metrics": [], "tools": [], "frameworks": [], "arcBeats": [], "loops": [], "thumbSrc": "https://imgproxy.kitesheet.com/PVQJdu166bvZvyb0-gRxcYgrbG03q1FvtTQ0qQh4ldo/rs:fit:480:480:0/q:78/f:webp/czM6Ly9raXRlc2hlZXQvY29ycHVzL3NsaWRlcy9kOWVlMmZkYzBiZDdiMGVjL3AwMDEuanBn", "imagePathAlt": "https://imgproxy.kitesheet.com/64OUcGTbXXg4r_AAOOSEicpotISEoU-fRZ7Qq7-pNPc/rs:fit:1200:1200:0/q:82/f:webp/czM6Ly9raXRlc2hlZXQvY29ycHVzL3NsaWRlcy9kOWVlMmZkYzBiZDdiMGVjL3AwMDEucG5n", "thumbSrcAlt": "https://imgproxy.kitesheet.com/DA3Ly1XsE1RutxY0Aj-BgQKxRWesRTXRbCwqmCEblJQ/rs:fit:480:480:0/q:78/f:webp/czM6Ly9raXRlc2hlZXQvY29ycHVzL3NsaWRlcy9kOWVlMmZkYzBiZDdiMGVjL3AwMDEucG5n" }, { "page": 2, "type": "setup", "function": "summarize", "rawType": "executive_summary", "block": null, "metadata": { "slideType": "executive_summary", "slideTypeCanon": { "name": "Executive summary", "slug": "executive_summary", "status": "active", "canonId": "019de52d-06be-73ff-81b3-f99fe7f0025e", "version": 1, "description": null }, "function": "summarize", "functionCanon": { "name": "Summarize", "slug": "summarize", "status": "active", "canonId": "019de52d-1541-704f-b86f-bf7b75056373", "version": 1, "description": null }, "density": "balanced", "densityScore": 44, "componentCount": 4, "textChars": 1135, "nDataPoints": 0, "notes": null, "elementsJson": [ "paragraph", "photo" ], "confidence": 1, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:56.566+00", "seconds": 2.452, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/2", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-2", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": { "h": 0.81, "w": 0.615, "x": 0.337, "y": 0.095 }, "kind": "image", "text": null, "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Photo", "slug": "photo", "status": "active", "canonId": "019de52c-fd37-757f-b4a8-ca26d4888875", "version": 1, "description": null }, "framework": null }, "subkind": "photo", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:56.566+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "2c5f05b4-4611-43cd-b4e2-2a7b1368e0d1", "parentComponentId": null }, { "bbox": { "h": 0.683, "w": 0.285, "x": 0.048, "y": 0.181 }, "kind": "paragraph", "text": "The growing accessibility of diverse types of data including structured databases, unstructured text, and multimedia, pose significant challenges for organizations that want to derive meaningful insights from complex data. Conventional search and retrieval methods are increasingly inadequate for managing the complexity and immense volume of data today. Let's take a look at how generative AI (gen AI) can enhance retrieval strategies through language embeddings and source grounding, focusing on optimizing performance, speed, and scalability to effectively address these challenges.\nTo assess the effectiveness of these gen AI-driven strategies, we'll explore a critical intersection between financial services and environmental, social, and governance (ESG).\nWe'll specifically focus on extracting data from unstructured documents, such as banks' emissions reports and quarterly reports, and constructing a database from these data points that were previously difficult to access, demonstrating the practical applications and benefits of advanced data retrieval in the financial services sector.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:56.566+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "f07cb8f2-53a3-498a-a8c2-4e69e272b08e", "parentComponentId": null }, { "bbox": { "h": 0.038, "w": 0.148, "x": 0.048, "y": 0.095 }, "kind": "title", "text": "Abstract", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:56.566+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "7d07b7ec-6b98-43fc-8720-177b2a78dccf", "parentComponentId": null }, { "bbox": { "h": 0.014, "w": 0.133, "x": 0.819, "y": 0.033 }, "kind": "title", "text": "EY and Elastic Collaboration", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Subtitle", "slug": "subtitle", "status": "active", "canonId": "019de52c-fb09-739d-900c-815b0d9ac526", "version": 1, "description": null }, "framework": null }, "subkind": "subtitle", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:56.566+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "43c32c1a-2d5f-4d4c-9220-cb0fcb9f15e6", "parentComponentId": null } ], "metrics": [], "tools": [ { "tool": { "name": "Executive summary", "slug": "executive-summary", "status": "active", "bestFor": null, "canonId": "019dd9e1-4b63-72d5-9734-da757d91ca61", "version": 1, "bodyDocId": null, "description": "A condensed view of the entire argument on a single slide / block.", "familyLabel": null, "categoryName": null, "categorySlug": null }, "agent": null, "layer": "slide", "agents": null, "matchId": "5a33e595-a791-4d39-86db-ad573b89d35f", "evidence": "This slide contains an executive summary.", "pageRefs": null, "priority": null, "whenToUse": null, "confidence": 0.9, "extraction": { "at": "2026-07-16 21:47:59.793221+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": null }, "pageNumber": 2, "whyItWorks": null, "antipattern": null, "cardinality": "common", "narrativePurpose": null } ], "frameworks": [], "arcBeats": [], "loops": [], "locked": true }, { "page": 3, "type": "tension", "function": "frame_problem", "rawType": "problem_statement", "block": null, "metadata": { "slideType": "problem_statement", "slideTypeCanon": { "name": "Problem statement", "slug": "problem_statement", "status": "active", "canonId": "019de52d-0879-768d-bba8-8da8a5a121d4", "version": 1, "description": null }, "function": "frame_problem", "functionCanon": { "name": "Frame problem", "slug": "frame_problem", "status": "active", "canonId": "019de52d-13db-753e-ad70-e9b2d0dab398", "version": 1, "description": null }, "density": "overcrowded", "densityScore": 86, "componentCount": 11, "textChars": 1695, "nDataPoints": 0, "notes": null, "elementsJson": [ "paragraph", "icon_grid", "photo" ], "confidence": 1, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:58.531+00", "seconds": 4.304, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/3", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-3", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": null, "kind": "callout", "text": "Let's take a look at varying retrieval and language model strategies that can offer innovative information retrieval methods for the financial services sector.", "attrs": null, "canon": { "kind": { "name": "Callout", "slug": "callout", "status": "active", "canonId": "019de52c-f8d3-761a-8953-7d37080de5e2", "version": 1, "description": "Highlighted callout box." }, "tool": { "name": "Visual emphasis", "slug": "visual-emphasis", "status": "active", "bestFor": null, "canonId": "019dd9e1-474b-736b-a8eb-a794dd88241c", "version": 1, "bodyDocId": null, "description": "Drawing the eye to one element above the rest of the slide.", "familyLabel": null }, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-04-24 16:25:31+00", "model": "or:google/gemini-3.1-flash-lite-preview", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "019dd952-340f-723f-8a12-acec86f426b7", "parentComponentId": null }, { "bbox": { "h": 1, "w": 0.3, "x": 0.33, "y": 0 }, "kind": "image", "text": null, "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Photo", "slug": "photo", "status": "active", "canonId": "019de52c-fd37-757f-b4a8-ca26d4888875", "version": 1, "description": null }, "framework": null }, "subkind": "photo", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.531+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "e01240c0-1775-44b2-a5a8-bc0c3da1cd39", "parentComponentId": null }, { "bbox": { "h": 0.08, "w": 0.23, "x": 0.715, "y": 0.28 }, "kind": "list", "text": "Large language models (LLMs) may generate hallucinations – responses that are out of context – that result in unreliable outcomes.", "attrs": null, "canon": { "kind": { "name": "List", "slug": "list", "status": "active", "canonId": "019de52c-f94b-779b-a53b-fd4904a5f4d2", "version": 1, "description": "Bullet or numbered list." }, "tool": null, "subkind": { "name": "Bullet list", "slug": "bullet", "status": "active", "canonId": "019de52c-fc98-7169-a083-5cab805076ca", "version": 1, "description": null }, "framework": null }, "subkind": "bullet", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.531+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "1051dcd9-e998-40c6-b081-df46434a3f5a", "parentComponentId": null }, { "bbox": { "h": 0.05, "w": 0.23, "x": 0.715, "y": 0.46 }, "kind": "list", "text": "Cost and speed constraints can result in limited scalability across extensive source databases.", "attrs": null, "canon": { "kind": { "name": "List", "slug": "list", "status": "active", "canonId": "019de52c-f94b-779b-a53b-fd4904a5f4d2", "version": 1, "description": "Bullet or numbered list." }, "tool": null, "subkind": { "name": "Bullet list", "slug": "bullet", "status": "active", "canonId": "019de52c-fc98-7169-a083-5cab805076ca", "version": 1, "description": null }, "framework": null }, "subkind": "bullet", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.531+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "17d15d7b-e89d-4ceb-b67a-3fd9f54d114f", "parentComponentId": null }, { "bbox": { "h": 0.05, "w": 0.23, "x": 0.715, "y": 0.63 }, "kind": "list", "text": "Out-of-the-box LLMs and search engines are difficult to set up for the most suitable parameters", "attrs": null, "canon": { "kind": { "name": "List", "slug": "list", "status": "active", "canonId": "019de52c-f94b-779b-a53b-fd4904a5f4d2", "version": 1, "description": "Bullet or numbered list." }, "tool": null, "subkind": { "name": "Bullet list", "slug": "bullet", "status": "active", "canonId": "019de52c-fc98-7169-a083-5cab805076ca", "version": 1, "description": null }, "framework": null }, "subkind": "bullet", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.531+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "77421fd7-adfb-4719-bdab-4fece332a088", "parentComponentId": null }, { "bbox": { "h": 0.05, "w": 0.3, "x": 0.648, "y": 0.77 }, "kind": "paragraph", "text": "Let's take a look at varying retrieval and language model strategies that can offer innovative information retrieval methods for the financial services sector.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.531+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "0570b29c-90f6-4063-8e28-8023a27062c8", "parentComponentId": null }, { "bbox": { "h": 0.05, "w": 0.3, "x": 0.648, "y": 0.18 }, "kind": "paragraph", "text": "Organizations that have attempted to implement gen AI solutions have quickly encountered new challenges, including:", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.531+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "05c733c8-269f-4834-8d19-7f7d2fda7c13", "parentComponentId": null }, { "bbox": { "h": 0.15, "w": 0.28, "x": 0.048, "y": 0.33 }, "kind": "paragraph", "text": "Alternatively, organizations had to build their own extraction pipelines, an endeavour that came with its own challenges. But with the advent of gen AI, the entire financial services industry has been disrupted, resulting in a lasting change in the field of data extraction.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.531+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "509e7518-9c91-4976-bb38-808c047aefb4", "parentComponentId": null }, { "bbox": { "h": 0.2, "w": 0.28, "x": 0.048, "y": 0.48 }, "kind": "paragraph", "text": "Gen AI can autonomously analyze and interpret vast amounts of unstructured data with unprecedented accuracy and speed, using natural language processing and machine learning algorithms. These innovative capabilities include contextual understanding, pattern recognition and the generation of coherent data summaries, which significantly reduce the time and resources required to extract data.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.531+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "7c0b9918-e7f4-4b5d-a1ba-bb6bd07ccb6b", "parentComponentId": null }, { "bbox": { "h": 0.15, "w": 0.28, "x": 0.048, "y": 0.18 }, "kind": "paragraph", "text": "Data extraction has always been challenging, particularly when dealing with unstructured, inconsistent, and notably large amounts of data. Organizations have often relied on external data providers, which was not only costly but also not always up-to-date or live.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.531+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "e6a9978a-646c-4b44-84a4-dce7c5f8044e", "parentComponentId": null }, { "bbox": { "h": 0.04, "w": 0.19, "x": 0.048, "y": 0.095 }, "kind": "title", "text": "Introduction", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.531+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "bea0df2d-f148-421f-8718-4ebfbad589e0", "parentComponentId": null } ], "metrics": [], "tools": [], "frameworks": [], "arcBeats": [ { "to": 4, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null }, "from": 3, "name": "Situation & Context", "beatId": "e3077b66-a96d-4be2-9521-145f02396c38", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Situation & Context", "slug": "consultants-gambit-situation-context", "status": "active", "canonId": "019dd9b8-05ae-741b-992d-65ee83c639b3", "version": 1, "description": null }, "evidence": "The deck provides an introduction to the current state and main challenges of data extraction", "position": 0, "isPrimaryArc": true, "parentBeatType": { "name": "Setup", "slug": "setup", "status": "active", "canonId": "019dd9b8-020e-7505-af9b-d9b9a4679bcc", "version": 1, "description": "Where the deck grounds the reader before doing anything else. Almost every arc opens here." }, "alignedBlockIds": null, "matchConfidence": 0.8 } ], "loops": [ { "to": 6, "from": 3, "loop": { "name": "02_pattern_hunter", "slug": "02-pattern-hunter", "status": "active", "bestFor": "Time-pressed audiences, building consensus, when data is strong", "canonId": "019dd956-6695-771a-be2e-f1748ef041a4", "version": 1, "bodyDocId": "019df22a-2420-77be-bc41-ded96d08cb21", "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion", "description": "Group multiple pieces of evidence that together point to a pattern or conclusion", "familyLabel": null }, "matchId": "565e85cb-f579-4e65-a33a-b008d293d5f2", "evidence": "The deck presents a problem statement and a proposed solution using Gen AI", "position": 0, "objective": "Identify patterns in current data extraction methods", "confidence": 0.6, "extraction": { "at": "2026-07-17 03:16:08.283215+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": "doc-narrative-v1" } } ], "locked": true }, { "page": 4, "type": "tension", "title": "The slide uses a circular diagram to represent the interconnected nature of the five challenges.", "function": "frame_problem", "rawType": "problem_statement", "block": null, "metadata": { "slideType": "problem_statement", "slideTypeCanon": { "name": "Problem statement", "slug": "problem_statement", "status": "active", "canonId": "019de52d-0879-768d-bba8-8da8a5a121d4", "version": 1, "description": null }, "function": "frame_problem", "functionCanon": { "name": "Frame problem", "slug": "frame_problem", "status": "active", "canonId": "019de52d-13db-753e-ad70-e9b2d0dab398", "version": 1, "description": null }, "density": "overcrowded", "densityScore": 86, "componentCount": 11, "textChars": 1708, "nDataPoints": 0, "notes": "The slide uses a circular diagram to represent the interconnected nature of the five challenges.", "elementsJson": [ "paragraph", "icon_grid" ], "confidence": 1, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:06:00.44+00", "seconds": 6.165, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/4", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-4", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": null, "kind": "callout", "text": "These challenges highlight the need for a sophisticated solution to data extraction and analysis.", "attrs": null, "canon": { "kind": { "name": "Callout", "slug": "callout", "status": "active", "canonId": "019de52c-f8d3-761a-8953-7d37080de5e2", "version": 1, "description": "Highlighted callout box." }, "tool": { "name": "Visual emphasis", "slug": "visual-emphasis", "status": "active", "bestFor": null, "canonId": "019dd9e1-474b-736b-a8eb-a794dd88241c", "version": 1, "bodyDocId": null, "description": "Drawing the eye to one element above the rest of the slide.", "familyLabel": null }, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-04-24 16:25:32+00", "model": "or:google/gemini-3.1-flash-lite-preview", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "019dd952-340f-723f-8a13-7895da3a2a1e", "parentComponentId": null }, { "bbox": { "h": 0.21, "w": 0.21, "x": 0.505, "y": 0.385 }, "kind": "diagram", "text": "Circular diagram showing 5 challenges: Keyword dependency, Static queries, Scalability challenges, Unstructured data complexity, Velocity and volume barriers.", "attrs": null, "canon": { "kind": { "name": "Diagram", "slug": "diagram", "status": "active", "canonId": "019de52c-f9f0-734a-81de-15382ff28c65", "version": 1, "description": "Schematic or relational diagram." }, "tool": null, "subkind": { "name": "Hub and spoke", "slug": "hub-spoke", "status": "active", "canonId": "019de52d-04db-73e6-81ca-a234f2f23fc1", "version": 1, "description": null }, "framework": null }, "subkind": "hub-spoke", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.44+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "75f760b7-cb54-4d1d-87ac-15f286f46aaa", "parentComponentId": null }, { "bbox": { "h": 0.08, "w": 0.2, "x": 0.755, "y": 0.455 }, "kind": "list", "text": "Static queries: Predefined queries lack the flexibility to adapt to new data types or unexpected querying requirements, hindering the discovery of insights in evolving datasets.", "attrs": null, "canon": { "kind": { "name": "List", "slug": "list", "status": "active", "canonId": "019de52c-f94b-779b-a53b-fd4904a5f4d2", "version": 1, "description": "Bullet or numbered list." }, "tool": null, "subkind": { "name": "Bullet list", "slug": "bullet", "status": "active", "canonId": "019de52c-fc98-7169-a083-5cab805076ca", "version": 1, "description": null }, "framework": null }, "subkind": "bullet", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.44+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "591111e6-b152-4099-a0ed-8680765e454c", "parentComponentId": null }, { "bbox": { "h": 0.08, "w": 0.2, "x": 0.72, "y": 0.655 }, "kind": "list", "text": "Scalability challenges: The increasing volume and complexity of data outpace the capabilities of conventional search tools, leading to slower search responses and a strain on resources.", "attrs": null, "canon": { "kind": { "name": "List", "slug": "list", "status": "active", "canonId": "019de52c-f94b-779b-a53b-fd4904a5f4d2", "version": 1, "description": "Bullet or numbered list." }, "tool": null, "subkind": { "name": "Bullet list", "slug": "bullet", "status": "active", "canonId": "019de52c-fc98-7169-a083-5cab805076ca", "version": 1, "description": null }, "framework": null }, "subkind": "bullet", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.44+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "84f9e00f-04da-4c13-bde2-70c9f4d000b0", "parentComponentId": null }, { "bbox": { "h": 0.08, "w": 0.2, "x": 0.545, "y": 0.255 }, "kind": "list", "text": "Keyword dependency: Limited to exact keyword matches, traditional systems suffer with the nuances of language, failing to capture context and semantic variations.", "attrs": null, "canon": { "kind": { "name": "List", "slug": "list", "status": "active", "canonId": "019de52c-f94b-779b-a53b-fd4904a5f4d2", "version": 1, "description": "Bullet or numbered list." }, "tool": null, "subkind": { "name": "Bullet list", "slug": "bullet", "status": "active", "canonId": "019de52c-fc98-7169-a083-5cab805076ca", "version": 1, "description": null }, "framework": null }, "subkind": "bullet", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.44+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "9de16fb3-532f-4aa8-91e1-ce1ab290cfd9", "parentComponentId": null }, { "bbox": { "h": 0.08, "w": 0.2, "x": 0.33, "y": 0.455 }, "kind": "list", "text": "Velocity and volume barriers: Traditional architectures struggle to maintain performance and scalability amid the rapid growth of data speed and volume.", "attrs": null, "canon": { "kind": { "name": "List", "slug": "list", "status": "active", "canonId": "019de52c-f94b-779b-a53b-fd4904a5f4d2", "version": 1, "description": "Bullet or numbered list." }, "tool": null, "subkind": { "name": "Bullet list", "slug": "bullet", "status": "active", "canonId": "019de52c-fc98-7169-a083-5cab805076ca", "version": 1, "description": null }, "framework": null }, "subkind": "bullet", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.44+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "a9c8c982-5743-42ef-bb73-0857bb8b7f84", "parentComponentId": null }, { "bbox": { "h": 0.08, "w": 0.2, "x": 0.345, "y": 0.655 }, "kind": "list", "text": "Unstructured data complexity: The predominance of unstructured data necessitates advanced analytical techniques beyond the scope of traditional methods.", "attrs": null, "canon": { "kind": { "name": "List", "slug": "list", "status": "active", "canonId": "019de52c-f94b-779b-a53b-fd4904a5f4d2", "version": 1, "description": "Bullet or numbered list." }, "tool": null, "subkind": { "name": "Bullet list", "slug": "bullet", "status": "active", "canonId": "019de52c-fc98-7169-a083-5cab805076ca", "version": 1, "description": null }, "framework": null }, "subkind": "bullet", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.44+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "e928b98d-d5a7-48da-945a-f57392194f59", "parentComponentId": null }, { "bbox": { "h": 0.135, "w": 0.256, "x": 0.048, "y": 0.182 }, "kind": "paragraph", "text": "The recent surge in data availability has rendered traditional methods of data extraction and analysis obsolete. These legacy systems, once reliant on manual keyword searches and static queries, struggle when confronted with today's vast, dynamic, and diverse data streams.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.44+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "cb873369-eb2d-4e69-9926-e308100d55fc", "parentComponentId": null }, { "bbox": { "h": 0.06, "w": 0.58, "x": 0.321, "y": 0.84 }, "kind": "paragraph", "text": "These challenges highlight the need for a sophisticated solution to data extraction and analysis. Such solutions should be designed to handle the intricacies of language, adapt to evolving data types, and scale in response to the increasing volume and complexity of data.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.44+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "dc8fc284-e1e1-429a-8efd-41320ccd9d55", "parentComponentId": null }, { "bbox": { "h": 0.02, "w": 0.256, "x": 0.321, "y": 0.182 }, "kind": "paragraph", "text": "Key challenges in information retrieval include:", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.44+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "e671141d-80b3-46a7-9019-dbad4fb8943b", "parentComponentId": null }, { "bbox": { "h": 0.038, "w": 0.445, "x": 0.048, "y": 0.095 }, "kind": "title", "text": "Current state and main challenges", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.44+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "b77a30cf-6ab2-4127-ab29-26169847b643", "parentComponentId": null } ], "metrics": [], "tools": [], "frameworks": [], "arcBeats": [ { "to": 4, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null }, "from": 3, "name": "Situation & Context", "beatId": "e3077b66-a96d-4be2-9521-145f02396c38", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Situation & Context", "slug": "consultants-gambit-situation-context", "status": "active", "canonId": "019dd9b8-05ae-741b-992d-65ee83c639b3", "version": 1, "description": null }, "evidence": "The deck provides an introduction to the current state and main challenges of data extraction", "position": 0, "isPrimaryArc": true, "parentBeatType": { "name": "Setup", "slug": "setup", "status": "active", "canonId": "019dd9b8-020e-7505-af9b-d9b9a4679bcc", "version": 1, "description": "Where the deck grounds the reader before doing anything else. Almost every arc opens here." }, "alignedBlockIds": null, "matchConfidence": 0.8 }, { "to": 5, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null }, "from": 4, "name": "Problem & Complication", "beatId": "f6422833-097c-4dae-acb2-e12ecb8dc8ea", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Problem & Complication", "slug": "consultants-gambit-problem-complication", "status": "active", "canonId": "019dd9b8-064a-777f-a374-e9a8c43dedd4", "version": 1, "description": null }, "evidence": "The deck highlights the inefficiencies of current data extraction methods", "position": 1, "isPrimaryArc": true, "parentBeatType": { "name": "Complication", "slug": "complication", "status": "active", "canonId": "019dd9b8-0275-7709-b2d6-4f77c3fc7579", "version": 1, "description": "The point in the narrative where the audience should feel discomfort. Required for argumentative arcs." }, "alignedBlockIds": null, "matchConfidence": 0.8 } ], "loops": [ { "to": 6, "from": 3, "loop": { "name": "02_pattern_hunter", "slug": "02-pattern-hunter", "status": "active", "bestFor": "Time-pressed audiences, building consensus, when data is strong", "canonId": "019dd956-6695-771a-be2e-f1748ef041a4", "version": 1, "bodyDocId": "019df22a-2420-77be-bc41-ded96d08cb21", "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion", "description": "Group multiple pieces of evidence that together point to a pattern or conclusion", "familyLabel": null }, "matchId": "565e85cb-f579-4e65-a33a-b008d293d5f2", "evidence": "The deck presents a problem statement and a proposed solution using Gen AI", "position": 0, "objective": "Identify patterns in current data extraction methods", "confidence": 0.6, "extraction": { "at": "2026-07-17 03:16:08.283215+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": "doc-narrative-v1" } } ], "locked": true }, { "page": 5, "type": "setup", "function": "establish_context", "rawType": "situation_overview", "block": null, "metadata": { "slideType": "situation_overview", "slideTypeCanon": { "name": "Situation overview", "slug": "situation_overview", "status": "active", "canonId": "019de52d-0cfe-7769-99aa-9a2fe82a4039", "version": 1, "description": null }, "function": "establish_context", "functionCanon": { "name": "Establish context", "slug": "establish_context", "status": "active", "canonId": "019de52d-1314-74e6-9074-d213dc0bdcdf", "version": 1, "description": null }, "density": "dense", "densityScore": 62, "componentCount": 6, "textChars": 2142, "nDataPoints": 0, "notes": null, "elementsJson": [ "headline_text", "paragraph", "footnote" ], "confidence": 1, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:57.188+00", "seconds": 2.784, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/5", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-5", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": null, "kind": "callout", "text": "Due to the distributed systems approach and overall design, EY's solution showed superior performance alongside Elastic's technology stack.", "attrs": null, "canon": { "kind": { "name": "Callout", "slug": "callout", "status": "active", "canonId": "019de52c-f8d3-761a-8953-7d37080de5e2", "version": 1, "description": "Highlighted callout box." }, "tool": { "name": "Visual emphasis", "slug": "visual-emphasis", "status": "active", "bestFor": null, "canonId": "019dd9e1-474b-736b-a8eb-a794dd88241c", "version": 1, "bodyDocId": null, "description": "Drawing the eye to one element above the rest of the slide.", "familyLabel": null }, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-04-24 16:25:31+00", "model": "or:google/gemini-3.1-flash-lite-preview", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "019dd952-340f-723f-8a12-c516148040d9", "parentComponentId": null }, { "bbox": { "h": 0.135, "w": 0.315, "x": 0.321, "y": 0.725 }, "kind": "paragraph", "text": "The pipeline of these retrieval systems is a comprehensive collection of tools that enhance the core functionalities. It combines language embedding models and source groundings, data transformation and storage (including vectors), and data search and retrieval, all within a single ecosystem. It also encompasses tools for data security and provides integration capabilities with other software, including various data sources and LLMs. This integration is particularly valuable in addressing the financial services industry's very nuanced challenges.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.188+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "1eef1891-dfc3-4be6-9e14-3914b43247bd", "parentComponentId": null }, { "bbox": { "h": 0.135, "w": 0.315, "x": 0.639, "y": 0.435 }, "kind": "paragraph", "text": "Throughout the pipeline, the technology was developed by EY's gen AI professionals and the technology was enabled by Elasticsearch¹. For comparison, we'll compare the efficiency, cost, and speed between EY's approach and a naïve retrieval pipeline. Due to the distributed systems approach and overall design, EY's solution showed superior performance alongside Elastic's technology stack.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.188+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "6e9471d0-1ca3-4d56-825b-dfcc0351371d", "parentComponentId": null }, { "bbox": { "h": 0.285, "w": 0.315, "x": 0.321, "y": 0.435 }, "kind": "paragraph", "text": "The process of data search, storage, and analysis is being revolutionized using advanced retrieval systems enabled by gen AI. These systems, characterized by their scalability and high- levels of performance, excel in real-time processing of various data types, including structured, unstructured text, numerical, and geospatial information. The use of sophisticated domain specific queries in these systems enable intricate and detailed searches, unlocking profound insights from extensive datasets. These strategies are integral for a wide array of applications including log and event data analysis, full-text searches, security intelligence, business analytics, and operational intelligence.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.188+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "f7098205-ab3f-4715-a2c0-e88afd87c786", "parentComponentId": null }, { "bbox": { "h": 0.095, "w": 0.315, "x": 0.639, "y": 0.808 }, "kind": "source-note", "text": "¹ Elasticsearch is an open- source distributed, RESTful search and analytics engine, scalable data store, and vector database capable of addressing a growing number of use cases. As the heart of the Elastic Stack, it centrally stores your data for lightning-fast search, fine-tuned relevancy, and powerful analytics that scale with ease.", "attrs": { "numbered": true }, "canon": { "kind": { "name": "Source note", "slug": "source-note", "status": "active", "canonId": "23484952-494b-4a5e-b1ad-550d0d70e948", "version": 1, "description": "Attribution / source / caveat placed at the slide footer. Numbered footnotes use attrs.numbered." }, "tool": null, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.188+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "52a5e69d-3cd2-40b1-abaa-5f4e3774e2fd", "parentComponentId": null }, { "bbox": { "h": 0.052, "w": 0.268, "x": 0.048, "y": 0.435 }, "kind": "title", "text": "Gen AI and retrieval strategies", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.188+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "bcbf65d5-b2a3-4486-b337-4b41f5fe4be3", "parentComponentId": null } ], "metrics": [], "tools": [], "frameworks": [], "arcBeats": [ { "to": 5, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null }, "from": 4, "name": "Problem & Complication", "beatId": "f6422833-097c-4dae-acb2-e12ecb8dc8ea", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Problem & Complication", "slug": "consultants-gambit-problem-complication", "status": "active", "canonId": "019dd9b8-064a-777f-a374-e9a8c43dedd4", "version": 1, "description": null }, "evidence": "The deck highlights the inefficiencies of current data extraction methods", "position": 1, "isPrimaryArc": true, "parentBeatType": { "name": "Complication", "slug": "complication", "status": "active", "canonId": "019dd9b8-0275-7709-b2d6-4f77c3fc7579", "version": 1, "description": "The point in the narrative where the audience should feel discomfort. Required for argumentative arcs." }, "alignedBlockIds": null, "matchConfidence": 0.8 }, { "to": 6, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null }, "from": 5, "name": "Solution & Approach", "beatId": "1efec661-4651-4613-962f-1c8e8166349a", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Solution & Approach", "slug": "consultants-gambit-solution-approach", "status": "active", "canonId": "019dd9b8-071c-7161-9184-580fdac7a4f9", "version": 1, "description": null }, "evidence": "The deck presents Gen AI as a solution to improve data extraction efficiency", "position": 2, "isPrimaryArc": true, "parentBeatType": { "name": "Turn", "slug": "turn", "status": "active", "canonId": "019dd9b8-0396-702b-ac2f-9901f8dd8b54", "version": 1, "description": "The pivot — solution proposed, catalyst introduced, decision made. Common (15/20 arcs) but not universal: Triple-take, AIDA, PAS, Voyage-return and Pixar substitute it with a strong reflection or development beat." }, "alignedBlockIds": null, "matchConfidence": 0.8 } ], "loops": [ { "to": 6, "from": 3, "loop": { "name": "02_pattern_hunter", "slug": "02-pattern-hunter", "status": "active", "bestFor": "Time-pressed audiences, building consensus, when data is strong", "canonId": "019dd956-6695-771a-be2e-f1748ef041a4", "version": 1, "bodyDocId": "019df22a-2420-77be-bc41-ded96d08cb21", "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion", "description": "Group multiple pieces of evidence that together point to a pattern or conclusion", "familyLabel": null }, "matchId": "565e85cb-f579-4e65-a33a-b008d293d5f2", "evidence": "The deck presents a problem statement and a proposed solution using Gen AI", "position": 0, "objective": "Identify patterns in current data extraction methods", "confidence": 0.6, "extraction": { "at": "2026-07-17 03:16:08.283215+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": "doc-narrative-v1" } } ], "locked": true }, { "page": 6, "type": "appendix", "title": "The slide explains the technical components of a RAG (Retrieval-Augmented Generation) pipeline.", "function": "present_framework", "rawType": "other", "block": null, "metadata": { "slideType": "other", "slideTypeCanon": { "name": "Other (fallback)", "slug": "other", "status": "active", "canonId": "019de52d-0af5-71ed-83de-d51ae245fc43", "version": 1, "description": null }, "function": "present_framework", "functionCanon": { "name": "Present framework", "slug": "present_framework", "status": "active", "canonId": "019de52d-1403-7667-9100-d2ac6709f750", "version": 1, "description": null }, "density": "overcrowded", "densityScore": 82, "componentCount": 9, "textChars": 2067, "nDataPoints": 0, "notes": "The slide explains the technical components of a RAG (Retrieval-Augmented Generation) pipeline.", "elementsJson": [ "headline_text", "paragraph", "footnote", "photo" ], "confidence": 0.9, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:58.417+00", "seconds": 3.94, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/6", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-6", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": null, "kind": "callout", "text": "These models help convert normal language into a space of vectors that are understood by retriever systems, emphasizing the understanding of context and the user's intent, and transcending the limitations of traditional keyword matching.", "attrs": null, "canon": { "kind": { "name": "Callout", "slug": "callout", "status": "active", "canonId": "019de52c-f8d3-761a-8953-7d37080de5e2", "version": 1, "description": "Highlighted callout box." }, "tool": { "name": "Visual emphasis", "slug": "visual-emphasis", "status": "active", "bestFor": null, "canonId": "019dd9e1-474b-736b-a8eb-a794dd88241c", "version": 1, "bodyDocId": null, "description": "Drawing the eye to one element above the rest of the slide.", "familyLabel": null }, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-04-24 16:25:32+00", "model": "or:google/gemini-3.1-flash-lite-preview", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "019dd952-340f-723f-8a13-296177de2de9", "parentComponentId": null }, { "bbox": { "h": 1, "w": 0.32, "x": 0.68, "y": 0 }, "kind": "image", "text": null, "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Photo", "slug": "photo", "status": "active", "canonId": "019de52c-fd37-757f-b4a8-ca26d4888875", "version": 1, "description": null }, "framework": null }, "subkind": "photo", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.417+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "89ab55de-7648-4071-b22f-bc0796b73ef7", "parentComponentId": null }, { "bbox": { "h": 0.2, "w": 0.3, "x": 0.05, "y": 0.32 }, "kind": "paragraph", "text": "A crucial component of the retrieval pipeline is the vector store, which is essentially a robust data storage system that can handle a diverse array of data types. This includes unstructured text, structured data, and dense vectors (embeddings). The vector store is designed to accommodate data both before and after it has been transformed by embedding models, making it a versatile tool in the pipeline.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.417+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "1c759217-74a1-4eb1-9051-268abcef4734", "parentComponentId": null }, { "bbox": { "h": 0.03, "w": 0.35, "x": 0.05, "y": 0.16 }, "kind": "paragraph", "text": "The end-to-end pipeline of the retrieval system is outlined below:", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.417+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "560f79fd-082d-4ec7-aa2d-e290d24c66f8", "parentComponentId": null }, { "bbox": { "h": 0.35, "w": 0.3, "x": 0.37, "y": 0.32 }, "kind": "paragraph", "text": "These retrieval systems often employ embedding models, such as the Elastic Learned Sparse EncodeR (ELSER)², to facilitate a retrieval model that offers enterprises the capability to execute precise semantic searches. These models help convert normal language into a space of vectors that are understood by retriever systems, emphasizing the understanding of context and the user's intent, and transcending the limitations of traditional keyword matching. Harnessing a rich training dataset composed of high-quality question-answer pairs, these models enhance the efficiency of calculating similarity between queries and documents. This not only refines the accuracy of information retrieval, but also expedites the indexing process, improving the search experience for users", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.417+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "e46a6d2e-5f19-471b-86d2-3e19dc03de0e", "parentComponentId": null }, { "bbox": { "h": 0.2, "w": 0.3, "x": 0.68, "y": 0.72 }, "kind": "source-note", "text": "2 ELSER is a retrieval model trained by Elastic that enables semantic search, which allows the solution to retrieve more relevant search results. This search type provides search results based on contextual meaning and user intent, rather than exact keyword matches. 3 RRF is a method for combining multiple result sets with different relevance indicators into a single result set. RRF requires no tuning, and the different relevance indicators do not have to be related to each other to achieve high-quality results.", "attrs": null, "canon": { "kind": { "name": "Source note", "slug": "source-note", "status": "active", "canonId": "23484952-494b-4a5e-b1ad-550d0d70e948", "version": 1, "description": "Attribution / source / caveat placed at the slide footer. Numbered footnotes use attrs.numbered." }, "tool": null, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.417+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "96b938f4-f4f7-4ac7-8563-fdb5323e494c", "parentComponentId": null }, { "bbox": { "h": 0.03, "w": 0.15, "x": 0.05, "y": 0.24 }, "kind": "title", "text": "Vector store", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.417+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "0a03f1da-505c-4daa-9b19-e24f3275f9f0", "parentComponentId": null }, { "bbox": { "h": 0.03, "w": 0.2, "x": 0.37, "y": 0.24 }, "kind": "title", "text": "Embedding models", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.417+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "b0dc2987-60b8-4bd0-9217-6d337d9f29eb", "parentComponentId": null }, { "bbox": { "h": 0.05, "w": 0.4, "x": 0.05, "y": 0.08 }, "kind": "title", "text": "Gen AI and retrieval strategies (Cont'd)", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.417+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "f05cfadb-1176-4782-b31f-c731fe43faa4", "parentComponentId": null } ], "metrics": [], "tools": [], "frameworks": [], "arcBeats": [ { "to": 6, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null }, "from": 5, "name": "Solution & Approach", "beatId": "1efec661-4651-4613-962f-1c8e8166349a", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Solution & Approach", "slug": "consultants-gambit-solution-approach", "status": "active", "canonId": "019dd9b8-071c-7161-9184-580fdac7a4f9", "version": 1, "description": null }, "evidence": "The deck presents Gen AI as a solution to improve data extraction efficiency", "position": 2, "isPrimaryArc": true, "parentBeatType": { "name": "Turn", "slug": "turn", "status": "active", "canonId": "019dd9b8-0396-702b-ac2f-9901f8dd8b54", "version": 1, "description": "The pivot — solution proposed, catalyst introduced, decision made. Common (15/20 arcs) but not universal: Triple-take, AIDA, PAS, Voyage-return and Pixar substitute it with a strong reflection or development beat." }, "alignedBlockIds": null, "matchConfidence": 0.8 } ], "loops": [ { "to": 6, "from": 3, "loop": { "name": "02_pattern_hunter", "slug": "02-pattern-hunter", "status": "active", "bestFor": "Time-pressed audiences, building consensus, when data is strong", "canonId": "019dd956-6695-771a-be2e-f1748ef041a4", "version": 1, "bodyDocId": "019df22a-2420-77be-bc41-ded96d08cb21", "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion", "description": "Group multiple pieces of evidence that together point to a pattern or conclusion", "familyLabel": null }, "matchId": "565e85cb-f579-4e65-a33a-b008d293d5f2", "evidence": "The deck presents a problem statement and a proposed solution using Gen AI", "position": 0, "objective": "Identify patterns in current data extraction methods", "confidence": 0.6, "extraction": { "at": "2026-07-17 03:16:08.283215+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": "doc-narrative-v1" } } ], "locked": true }, { "page": 7, "type": "appendix", "title": "The slide uses a two-column layout to define technical concepts (RRF and kNN) relevant to AI search architectures.", "function": "present_framework", "rawType": "other", "block": null, "metadata": { "slideType": "other", "slideTypeCanon": { "name": "Other (fallback)", "slug": "other", "status": "active", "canonId": "019de52d-0af5-71ed-83de-d51ae245fc43", "version": 1, "description": null }, "function": "present_framework", "functionCanon": { "name": "Present framework", "slug": "present_framework", "status": "active", "canonId": "019de52d-1403-7667-9100-d2ac6709f750", "version": 1, "description": null }, "density": "overcrowded", "densityScore": 76, "componentCount": 8, "textChars": 1675, "nDataPoints": 0, "notes": "The slide uses a two-column layout to define technical concepts (RRF and kNN) relevant to AI search architectures.", "elementsJson": [ "headline_text", "paragraph", "photo" ], "confidence": 0.9, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:58.652+00", "seconds": 4.127, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/7", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-7", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": { "h": 1, "w": 0.265, "x": 0.735, "y": 0 }, "kind": "image", "text": null, "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Photo", "slug": "photo", "status": "active", "canonId": "019de52c-fd37-757f-b4a8-ca26d4888875", "version": 1, "description": null }, "framework": null }, "subkind": "photo", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.652+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "a3226e84-3418-4e32-ac9b-69532c9a7e1c", "parentComponentId": null }, { "bbox": { "h": 0.15, "w": 0.335, "x": 0.371, "y": 0.275 }, "kind": "paragraph", "text": "The use of methods like k-Nearest Neighbors (kNN) in the retrieval pipeline, allows for fast and efficient similarity searches. These methods find the \"nearest\" documents to a given query in the embedding space. This is especially useful for identifying documents with similar patterns or themes, even if the exact keywords are not matched, enabling a more intuitive search experience.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.652+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "c78091cb-630a-4a20-b410-68a842d3b69d", "parentComponentId": null }, { "bbox": { "h": 0.18, "w": 0.335, "x": 0.371, "y": 0.415 }, "kind": "paragraph", "text": "The components within the retrieval system pipeline allow for enhanced search capability that grasps user intent, stores and retrieves the most relevant data for complex similarity searches, and the enables the fusion of multiple search strategies to further refine the search relevance. The search engine's ability to effectively handle metadata and employ different retrieval methods for intuitive similarity searches further underscores its capacity to efficiently navigate and interpret complex data structures.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.652+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "ef5cd546-31c1-42fe-a4bf-77a80da3944b", "parentComponentId": null }, { "bbox": { "h": 0.1, "w": 0.335, "x": 0.371, "y": 0.605 }, "kind": "paragraph", "text": "This process provides a powerful foundation for handling complex data, enabling businesses to more fully capitalize on their data's potential. Combined with solution engineering and industry expertise, it represents a transformative approach to overcoming the multifaceted challenges of data analysis in the digital age.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.652+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "f5bf91ff-0a8c-4dc9-ae8f-84e00e6f788b", "parentComponentId": null }, { "bbox": { "h": 0.15, "w": 0.315, "x": 0.048, "y": 0.275 }, "kind": "paragraph", "text": "Ranking models, such as Reciprocal Rank Fusion (RRF)3, are a key part of the retrieval pipeline. These models combine the strengths of multiple search strategies to improve result relevance. By merging outcomes from various queries and algorithms, ranking models improve the retrieval process for complex documents, making it easier to find pertinent information amid vast datasets.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.652+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "fc2cb223-d906-4e6f-807f-37c27ef92231", "parentComponentId": null }, { "bbox": { "h": 0.025, "w": 0.185, "x": 0.048, "y": 0.185 }, "kind": "title", "text": "Ranking models", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.652+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "8f5c8fb2-b1bf-402b-823f-f5eff3c34ea2", "parentComponentId": null }, { "bbox": { "h": 0.025, "w": 0.235, "x": 0.371, "y": 0.185 }, "kind": "title", "text": "Similarity searches", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.652+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "9179eaa1-389c-423d-bb24-1cd6576e50a5", "parentComponentId": null }, { "bbox": { "h": 0.035, "w": 0.498, "x": 0.048, "y": 0.095 }, "kind": "title", "text": "Gen AI and retrieval strategies (Cont'd)", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.652+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "dc194206-f07b-4653-9de5-9212afe97466", "parentComponentId": null } ], "metrics": [], "tools": [], "frameworks": [], "arcBeats": [], "loops": [], "locked": true }, { "page": 8, "type": "evidence", "title": "The diagram illustrates a process flow from various ESG reports through an expert review to final dashboarding and reporting.", "function": "illustrate_case", "rawType": "case_study", "block": null, "metadata": { "slideType": "case_study", "slideTypeCanon": { "name": "Case study", "slug": "case_study", "status": "active", "canonId": "019de52d-0b95-7344-8090-926f3b8e92c8", "version": 1, "description": null }, "function": "illustrate_case", "functionCanon": { "name": "Illustrate case", "slug": "illustrate_case", "status": "active", "canonId": "019de52d-13b4-772c-bb73-1873612a7463", "version": 1, "description": null }, "density": "balanced", "densityScore": 44, "componentCount": 6, "textChars": 490, "nDataPoints": 0, "notes": "The diagram illustrates a process flow from various ESG reports through an expert review to final dashboarding and reporting.", "elementsJson": [ "headline_text", "paragraph", "process_diagram", "photo" ], "confidence": 1, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:57.403+00", "seconds": 2.856, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/8", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-8", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": { "h": 0.775, "w": 0.454, "x": 0.518, "y": 0.2 }, "kind": "diagram", "text": null, "attrs": null, "canon": { "kind": { "name": "Diagram", "slug": "diagram", "status": "active", "canonId": "019de52c-f9f0-734a-81de-15382ff28c65", "version": 1, "description": "Schematic or relational diagram." }, "tool": null, "subkind": { "name": "Process flow", "slug": "process", "status": "active", "canonId": "019de52d-039c-718f-ad3a-efe9c4b3c838", "version": 1, "description": null }, "framework": null }, "subkind": "process", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.403+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "ff0d29c3-6d1f-4a18-a0df-04f921375a82", "parentComponentId": null }, { "bbox": { "h": 0.265, "w": 0.454, "x": 0.048, "y": 0.2 }, "kind": "image", "text": null, "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Illustration", "slug": "illustration", "status": "active", "canonId": "019de52c-fe76-7772-a5ac-c0b7294d7615", "version": 1, "description": null }, "framework": null }, "subkind": "illustration", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.403+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "a8e73332-136b-42a6-abbb-055922bd1b55", "parentComponentId": null }, { "bbox": { "h": 0.385, "w": 0.454, "x": 0.048, "y": 0.498 }, "kind": "paragraph", "text": "ESG reporting in the financial services industry is becoming an essential component of corporate transparency and accountability... In this use case study, we aim to extract ESG variables from publicly available annual ESG reports from the top Canadian banks.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.403+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "5b3fb29b-30a1-4264-9e4a-17bd8a0e52d2", "parentComponentId": null }, { "bbox": { "h": 0.035, "w": 0.454, "x": 0.518, "y": 0.78 }, "kind": "source-note", "text": "*TCFD: Task Force on Climate-related Financial Disclosures, GRI: Global Reporting Initiative, BIPOC: Black, Indigenous, and other People Of Colour", "attrs": null, "canon": { "kind": { "name": "Source note", "slug": "source-note", "status": "active", "canonId": "23484952-494b-4a5e-b1ad-550d0d70e948", "version": 1, "description": "Attribution / source / caveat placed at the slide footer. Numbered footnotes use attrs.numbered." }, "tool": null, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.403+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "dde6cd04-6330-4bed-8893-1a08638d92ec", "parentComponentId": null }, { "bbox": { "h": 0.022, "w": 0.415, "x": 0.048, "y": 0.138 }, "kind": "title", "text": "1. Extracting ESG variables from annual ESG reports", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Action title", "slug": "action-title", "status": "active", "canonId": "019de52c-fb31-734c-a0f5-a3935b73135d", "version": 1, "description": null }, "framework": null }, "subkind": "action-title", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.403+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "efe26e42-020f-47e1-8af2-2ffcde0534d3", "parentComponentId": null }, { "bbox": { "h": 0.038, "w": 0.466, "x": 0.048, "y": 0.088 }, "kind": "title", "text": "Use case implementation evaluation", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.403+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "2b77282d-ce6e-43b3-810c-442634418083", "parentComponentId": null } ], "metrics": [], "tools": [], "frameworks": [ { "matchId": "a0c418cd-09e4-4790-9e56-31d8aad7dfc3", "evidence": "The diagram shows a flow from input reports to output dashboarding/reporting.", "framework": null, "confidence": 0.8, "extraction": { "at": "2026-05-02 18:05:57.403+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "pageNumber": 8, "frameworkName": "process" } ], "arcBeats": [ { "to": 13, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null }, "from": 8, "name": "Evidence & Proof", "beatId": "8c4a78bd-1b53-456f-9179-be874097af96", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Evidence & Proof", "slug": "consultants-gambit-evidence-proof", "status": "active", "canonId": "019dd9b8-07b1-7688-8e1e-7637fec3802a", "version": 1, "description": null }, "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI in data extraction", "position": 3, "isPrimaryArc": true, "parentBeatType": { "name": "Evidence", "slug": "evidence", "status": "active", "canonId": "019dd9b8-03f9-772a-b84a-4f07b415b77a", "version": 1, "description": "A dedicated proof beat exists in only ~4 arcs (Gambit, Sequoia, AIDA, Monroes). Other arcs embed evidence inline within development." }, "alignedBlockIds": null, "matchConfidence": 0.8 } ], "loops": [ { "to": 13, "from": 8, "loop": { "name": "05_the_reveal", "slug": "05-the-reveal", "status": "active", "bestFor": "Product launches, strategic pivots, unexpected findings", "canonId": "019dd956-67e8-77bc-a867-02c2b36370bd", "version": 1, "bodyDocId": "019df22a-2420-77be-bc41-ded96d08cb21", "structure": "Setup the Question -> Build Suspense -> The Big Reveal", "description": "Build mystery and anticipation, then deliver a surprising or powerful conclusion", "familyLabel": null }, "matchId": "22c3ec8f-4e2e-4190-bd35-ca7dceee7d84", "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI", "position": 1, "objective": "Reveal the benefits of Gen AI in data extraction", "confidence": 0.7, "extraction": { "at": "2026-07-17 03:16:08.325926+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": "doc-narrative-v1" } } ], "locked": true }, { "page": 9, "type": "evidence", "title": "The slide details a technical architecture for RAG (Retrieval-Augmented Generation) applied to ESG reporting.", "function": "illustrate_case", "rawType": "case_study", "block": null, "metadata": { "slideType": "case_study", "slideTypeCanon": { "name": "Case study", "slug": "case_study", "status": "active", "canonId": "019de52d-0b95-7344-8090-926f3b8e92c8", "version": 1, "description": null }, "function": "illustrate_case", "functionCanon": { "name": "Illustrate case", "slug": "illustrate_case", "status": "active", "canonId": "019de52d-13b4-772c-bb73-1873612a7463", "version": 1, "description": null }, "density": "balanced", "densityScore": 47, "componentCount": 6, "textChars": 589, "nDataPoints": 0, "notes": "The slide details a technical architecture for RAG (Retrieval-Augmented Generation) applied to ESG reporting.", "elementsJson": [ "headline_text", "process_diagram", "paragraph" ], "confidence": 1, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:06:00.733+00", "seconds": 6.087, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/9", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-9", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": null, "kind": "callout", "text": "Retrieval-augmented generation (RAG) is an innovative AI technology that boosts the precision of information retrieval for complex documents like ESG reports using language embeddings and grounded sources.", "attrs": null, "canon": { "kind": { "name": "Callout", "slug": "callout", "status": "active", "canonId": "019de52c-f8d3-761a-8953-7d37080de5e2", "version": 1, "description": "Highlighted callout box." }, "tool": { "name": "Visual emphasis", "slug": "visual-emphasis", "status": "active", "bestFor": null, "canonId": "019dd9e1-474b-736b-a8eb-a794dd88241c", "version": 1, "bodyDocId": null, "description": "Drawing the eye to one element above the rest of the slide.", "familyLabel": null }, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-04-24 16:25:32+00", "model": "or:google/gemini-3.1-flash-lite-preview", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "019dd952-340f-723f-8a13-0489a6ab4d68", "parentComponentId": null }, { "bbox": { "h": 0.485, "w": 0.415, "x": 0.048, "y": 0.285 }, "kind": "diagram", "text": "Workflow of EY's solution", "attrs": null, "canon": { "kind": { "name": "Diagram", "slug": "diagram", "status": "active", "canonId": "019de52c-f9f0-734a-81de-15382ff28c65", "version": 1, "description": "Schematic or relational diagram." }, "tool": null, "subkind": { "name": "Process flow", "slug": "process", "status": "active", "canonId": "019de52d-039c-718f-ad3a-efe9c4b3c838", "version": 1, "description": null }, "framework": null }, "subkind": "process", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.733+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "32237d8d-0e12-49c1-ad0d-08495fc02002", "parentComponentId": null }, { "bbox": { "h": 0.685, "w": 0.427, "x": 0.525, "y": 0.218 }, "kind": "paragraph", "text": "EY's solution, enhanced by Elastic's advanced technology, offers a sophisticated solution to these challenges. Retrieval-augmented generation (RAG) is an innovative AI technology that boosts the precision of information retrieval.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.733+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "52fa1820-7d5c-4d82-b823-976a8819a8ab", "parentComponentId": null }, { "bbox": { "h": 0.015, "w": 0.135, "x": 0.188, "y": 0.762 }, "kind": "source-note", "text": "Figure 1: Workflow of EY's solution", "attrs": null, "canon": { "kind": { "name": "Source note", "slug": "source-note", "status": "active", "canonId": "23484952-494b-4a5e-b1ad-550d0d70e948", "version": 1, "description": "Attribution / source / caveat placed at the slide footer. Numbered footnotes use attrs.numbered." }, "tool": null, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.733+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "f90532f5-d684-44c1-bb86-9ffce773fcea", "parentComponentId": null }, { "bbox": { "h": 0.031, "w": 0.415, "x": 0.048, "y": 0.095 }, "kind": "title", "text": "Use case implementation evaluation (Cont'd)", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.733+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "0214f8dc-2f33-4b1c-a5e1-f5c6e9aa0def", "parentComponentId": null }, { "bbox": { "h": 0.022, "w": 0.391, "x": 0.048, "y": 0.138 }, "kind": "title", "text": "1. Extracting ESG variables from annual ESG reports", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Subtitle", "slug": "subtitle", "status": "active", "canonId": "019de52c-fb09-739d-900c-815b0d9ac526", "version": 1, "description": null }, "framework": null }, "subkind": "subtitle", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:06:00.733+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "bcdbdbd7-6504-439c-9571-7392b3b2b74b", "parentComponentId": null } ], "metrics": [], "tools": [], "frameworks": [ { "matchId": "7611814e-3600-437c-b695-ca00d94267c7", "evidence": "Text explicitly describes RAG process and architecture", "framework": null, "confidence": 1, "extraction": { "at": "2026-05-02 18:06:00.733+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "pageNumber": 9, "frameworkName": "Retrieval-Augmented Generation (RAG)" } ], "arcBeats": [ { "to": 13, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null }, "from": 8, "name": "Evidence & Proof", "beatId": "8c4a78bd-1b53-456f-9179-be874097af96", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Evidence & Proof", "slug": "consultants-gambit-evidence-proof", "status": "active", "canonId": "019dd9b8-07b1-7688-8e1e-7637fec3802a", "version": 1, "description": null }, "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI in data extraction", "position": 3, "isPrimaryArc": true, "parentBeatType": { "name": "Evidence", "slug": "evidence", "status": "active", "canonId": "019dd9b8-03f9-772a-b84a-4f07b415b77a", "version": 1, "description": "A dedicated proof beat exists in only ~4 arcs (Gambit, Sequoia, AIDA, Monroes). Other arcs embed evidence inline within development." }, "alignedBlockIds": null, "matchConfidence": 0.8 } ], "loops": [ { "to": 13, "from": 8, "loop": { "name": "05_the_reveal", "slug": "05-the-reveal", "status": "active", "bestFor": "Product launches, strategic pivots, unexpected findings", "canonId": "019dd956-67e8-77bc-a867-02c2b36370bd", "version": 1, "bodyDocId": "019df22a-2420-77be-bc41-ded96d08cb21", "structure": "Setup the Question -> Build Suspense -> The Big Reveal", "description": "Build mystery and anticipation, then deliver a surprising or powerful conclusion", "familyLabel": null }, "matchId": "22c3ec8f-4e2e-4190-bd35-ca7dceee7d84", "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI", "position": 1, "objective": "Reveal the benefits of Gen AI in data extraction", "confidence": 0.7, "extraction": { "at": "2026-07-17 03:16:08.325926+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": "doc-narrative-v1" } } ], "locked": true }, { "page": 10, "type": "analysis", "title": "The slide contains four distinct bar charts comparing different performance metrics for RAG implementations.", "function": "analyze_data", "rawType": "data_table", "block": null, "metadata": { "slideType": "data_table", "slideTypeCanon": { "name": "Data table", "slug": "data_table", "status": "active", "canonId": "019de52d-0bbd-71b9-9918-417f904abbf8", "version": 1, "description": null }, "function": "analyze_data", "functionCanon": { "name": "Analyze data", "slug": "analyze_data", "status": "active", "canonId": "019de52d-1590-7413-8c82-cc218cff40b4", "version": 1, "description": null }, "density": "overcrowded", "densityScore": 90, "componentCount": 10, "textChars": 1133, "nDataPoints": 40, "notes": "The slide contains four distinct bar charts comparing different performance metrics for RAG implementations.", "elementsJson": [ "headline_text", "bar_chart_grouped", "paragraph" ], "confidence": 1, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:58.374+00", "seconds": 3.589, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/10", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-10", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": null, "kind": "callout", "text": "In both metrics, Elastic RAG consistently outperforms Naive RAG. The context relevancy score, which assesses how well the retrieved information matches the query's context, is notably higher with Elastic RAG for all banks.", "attrs": null, "canon": { "kind": { "name": "Callout", "slug": "callout", "status": "active", "canonId": "019de52c-f8d3-761a-8953-7d37080de5e2", "version": 1, "description": "Highlighted callout box." }, "tool": { "name": "Visual emphasis", "slug": "visual-emphasis", "status": "active", "bestFor": null, "canonId": "019dd9e1-474b-736b-a8eb-a794dd88241c", "version": 1, "bodyDocId": null, "description": "Drawing the eye to one element above the rest of the slide.", "familyLabel": null }, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-04-24 16:25:32+00", "model": "or:google/gemini-3.1-flash-lite-preview", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "019dd952-340f-723f-8a13-421f9b786ca2", "parentComponentId": null }, { "bbox": { "h": 0.25, "w": 0.34, "x": 0.05, "y": 0.18 }, "kind": "chart", "text": "Figure 2: Processing time comparison: Elastic RAG vs Naive RAG", "attrs": null, "canon": { "kind": { "name": "Chart", "slug": "chart", "status": "active", "canonId": "019de52c-f9a0-76ef-adc6-0b859109d1f8", "version": 1, "description": "Quantitative chart." }, "tool": null, "subkind": { "name": "Grouped bar chart", "slug": "bar-grouped", "status": "active", "canonId": "019de52c-ff3b-751e-a8ff-f21ff11097b1", "version": 1, "description": null }, "framework": null }, "subkind": "bar-grouped", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.374+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "1ea0c973-bc0c-4fca-86ad-9dca765997d1", "parentComponentId": null }, { "bbox": { "h": 0.25, "w": 0.34, "x": 0.36, "y": 0.57 }, "kind": "chart", "text": "Figure 5: Scalability of Elastic solution", "attrs": null, "canon": { "kind": { "name": "Chart", "slug": "chart", "status": "active", "canonId": "019de52c-f9a0-76ef-adc6-0b859109d1f8", "version": 1, "description": "Quantitative chart." }, "tool": null, "subkind": { "name": "Grouped bar chart", "slug": "bar-grouped", "status": "active", "canonId": "019de52c-ff3b-751e-a8ff-f21ff11097b1", "version": 1, "description": null }, "framework": null }, "subkind": "bar-grouped", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.374+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "2404ce64-f26c-429b-b8e7-67d1a05341cc", "parentComponentId": null }, { "bbox": { "h": 0.25, "w": 0.34, "x": 0.05, "y": 0.57 }, "kind": "chart", "text": "Figure 4: Context relevancy score comparison: Elastic RAG vs Naive RAG", "attrs": null, "canon": { "kind": { "name": "Chart", "slug": "chart", "status": "active", "canonId": "019de52c-f9a0-76ef-adc6-0b859109d1f8", "version": 1, "description": "Quantitative chart." }, "tool": null, "subkind": { "name": "Grouped bar chart", "slug": "bar-grouped", "status": "active", "canonId": "019de52c-ff3b-751e-a8ff-f21ff11097b1", "version": 1, "description": null }, "framework": null }, "subkind": "bar-grouped", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.374+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "4d220694-fac6-452f-8d73-a5cc558cf3a3", "parentComponentId": null }, { "bbox": { "h": 0.25, "w": 0.34, "x": 0.36, "y": 0.18 }, "kind": "chart", "text": "Figure 3: Accuracy Test comparison: Elastic RAG vs Naive RAG", "attrs": null, "canon": { "kind": { "name": "Chart", "slug": "chart", "status": "active", "canonId": "019de52c-f9a0-76ef-adc6-0b859109d1f8", "version": 1, "description": "Quantitative chart." }, "tool": null, "subkind": { "name": "Grouped bar chart", "slug": "bar-grouped", "status": "active", "canonId": "019de52c-ff3b-751e-a8ff-f21ff11097b1", "version": 1, "description": null }, "framework": null }, "subkind": "bar-grouped", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.374+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "d45513f8-0cec-4fa7-926c-cba6b114ff6e", "parentComponentId": null }, { "bbox": null, "kind": "metric", "text": "Accuracy", "attrs": null, "canon": { "kind": { "name": "Metric", "slug": "metric", "status": "active", "canonId": "019de52c-f923-73bf-8081-d0b1a8c5264d", "version": 1, "description": "Big-number or KPI value." }, "tool": { "name": "Quantification", "slug": "quantification", "status": "active", "bestFor": null, "canonId": "019dd9e1-47ab-72ce-a079-aab1f5299e88", "version": 1, "bodyDocId": null, "description": "Translating a claim into numbers, charts, or tables.", "familyLabel": null }, "subkind": null, "framework": null }, "subkind": "primary", "groupRole": null, "confidence": null, "extraction": { "at": "2026-04-24 16:25:32+00", "model": "or:google/gemini-3.1-flash-lite-preview", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "019dd952-340f-723f-8a13-45ad4ec4aa54", "parentComponentId": null }, { "bbox": { "h": 0.2, "w": 0.28, "x": 0.69, "y": 0.44 }, "kind": "paragraph", "text": "Figure 5 displays that various data retrieval methods, such as Elastic RAG with keywords filter (KF) and Hybrid Retrieval (vector search and BM25) with keyword filter, consistently maintain high accuracy levels.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.374+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "1df37448-c6e8-48b0-b399-1fef0a987053", "parentComponentId": null }, { "bbox": { "h": 0.15, "w": 0.28, "x": 0.69, "y": 0.7 }, "kind": "paragraph", "text": "The fusion of search technologies with generative AI, represents a significant advancement in the field, providing a scalable and precise method for data extraction from these reports.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.374+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "5b695f37-4661-47bf-840b-b25ef35acae4", "parentComponentId": null }, { "bbox": { "h": 0.2, "w": 0.28, "x": 0.69, "y": 0.18 }, "kind": "paragraph", "text": "RAGFigures 3 and 4 illustrate a comparative analysis of Elastic RAG against a baseline Naive RAG across five Canadian banks in terms of context relevancy and accuracy. In both metrics, Elastic RAG consistently outperforms Naive RAG.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.374+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "6fe0fe6b-ec8b-4ddb-becf-4a264f46c233", "parentComponentId": null }, { "bbox": { "h": 0.04, "w": 0.5, "x": 0.04, "y": 0.08 }, "kind": "title", "text": "Use case implementation evaluation (Cont'd)", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.374+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "eb3d110b-38aa-4f8c-a530-fedf4bc2d91c", "parentComponentId": null } ], "metrics": [], "tools": [], "frameworks": [], "arcBeats": [ { "to": 13, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null }, "from": 8, "name": "Evidence & Proof", "beatId": "8c4a78bd-1b53-456f-9179-be874097af96", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Evidence & Proof", "slug": "consultants-gambit-evidence-proof", "status": "active", "canonId": "019dd9b8-07b1-7688-8e1e-7637fec3802a", "version": 1, "description": null }, "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI in data extraction", "position": 3, "isPrimaryArc": true, "parentBeatType": { "name": "Evidence", "slug": "evidence", "status": "active", "canonId": "019dd9b8-03f9-772a-b84a-4f07b415b77a", "version": 1, "description": "A dedicated proof beat exists in only ~4 arcs (Gambit, Sequoia, AIDA, Monroes). Other arcs embed evidence inline within development." }, "alignedBlockIds": null, "matchConfidence": 0.8 } ], "loops": [ { "to": 13, "from": 8, "loop": { "name": "05_the_reveal", "slug": "05-the-reveal", "status": "active", "bestFor": "Product launches, strategic pivots, unexpected findings", "canonId": "019dd956-67e8-77bc-a867-02c2b36370bd", "version": 1, "bodyDocId": "019df22a-2420-77be-bc41-ded96d08cb21", "structure": "Setup the Question -> Build Suspense -> The Big Reveal", "description": "Build mystery and anticipation, then deliver a surprising or powerful conclusion", "familyLabel": null }, "matchId": "22c3ec8f-4e2e-4190-bd35-ca7dceee7d84", "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI", "position": 1, "objective": "Reveal the benefits of Gen AI in data extraction", "confidence": 0.7, "extraction": { "at": "2026-07-17 03:16:08.325926+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": "doc-narrative-v1" } } ], "locked": true }, { "page": 11, "type": "evidence", "title": "The slide discusses the technical challenge of extracting structured financial data from unstructured documents using LLMs.", "function": "illustrate_case", "rawType": "case_study", "block": null, "metadata": { "slideType": "case_study", "slideTypeCanon": { "name": "Case study", "slug": "case_study", "status": "active", "canonId": "019de52d-0b95-7344-8090-926f3b8e92c8", "version": 1, "description": null }, "function": "illustrate_case", "functionCanon": { "name": "Illustrate case", "slug": "illustrate_case", "status": "active", "canonId": "019de52d-13b4-772c-bb73-1873612a7463", "version": 1, "description": null }, "density": "dense", "densityScore": 57, "componentCount": 5, "textChars": 1612, "nDataPoints": 1, "notes": "The slide discusses the technical challenge of extracting structured financial data from unstructured documents using LLMs.", "elementsJson": [ "headline_text", "paragraph", "photo" ], "confidence": 0.9, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:57.915+00", "seconds": 3.081, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/11", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-11", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": null, "kind": "callout", "text": "The EY approach to these challenges employs powerful search capabilities along with advanced table summarization techniques.", "attrs": null, "canon": { "kind": { "name": "Callout", "slug": "callout", "status": "active", "canonId": "019de52c-f8d3-761a-8953-7d37080de5e2", "version": 1, "description": "Highlighted callout box." }, "tool": { "name": "Visual emphasis", "slug": "visual-emphasis", "status": "active", "bestFor": null, "canonId": "019dd9e1-474b-736b-a8eb-a794dd88241c", "version": 1, "bodyDocId": null, "description": "Drawing the eye to one element above the rest of the slide.", "familyLabel": null }, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-04-24 16:25:35+00", "model": "or:google/gemini-3.1-flash-lite-preview", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "019dd952-340f-723f-8a14-fc38a52f9972", "parentComponentId": null }, { "bbox": { "h": 0.75, "w": 0.48, "x": 0.048, "y": 0.18 }, "kind": "image", "text": null, "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Photo", "slug": "photo", "status": "active", "canonId": "019de52c-fd37-757f-b4a8-ca26d4888875", "version": 1, "description": null }, "framework": null }, "subkind": "photo", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.915+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "e74c015b-e5dd-42e5-9f0c-e5c8e9695c7f", "parentComponentId": null }, { "bbox": { "h": 0.68, "w": 0.39, "x": 0.56, "y": 0.18 }, "kind": "paragraph", "text": "In the realm of financial analysis, extracting more than 40 financial variables from quarterly reports is an intricate endeavour, which is further magnified when deploying LLMs- which are typically attuned to unstructured text-to analyze structured table data found in financial documents. These reports feature tables filled with data organized in rows and columns, representing a unique challenge for LLMs that are adept at navigating textual data but less so with the intricate relationships and numerical nuances of tables. The extraction of financial variables from these reports is a more intricate task than that of ESG reporting, as it typically involves a greater number of variables. This represents a significant increase in data complexity when compared to ESG data extraction, making it a particularly challenging endeavor due to the sheer volume and intricacy of the financial information presented.\n\nThe EY approach to these challenges employs powerful search capabilities along with advanced table summarization techniques. This includes employing chain-of-thought and chain-of-verification processes to enhance the accuracy of the extracted data. Drawing on the experiences from ESG reporting, we developed a hybrid retrieval system that combines vector search with the BM25 algorithm, significantly increasing the reliability and precision of the data extraction process.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.915+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "78fdeed1-edfd-4bd5-b35e-eceeea488521", "parentComponentId": null }, { "bbox": { "h": 0.035, "w": 0.45, "x": 0.048, "y": 0.095 }, "kind": "title", "text": "Use case implementation evaluation (Cont'd)", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.915+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "8e4dee14-2fd4-4693-b54d-06327395521f", "parentComponentId": null }, { "bbox": { "h": 0.025, "w": 0.4, "x": 0.048, "y": 0.135 }, "kind": "title", "text": "2. Extracting financial variables from financial reports", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Subtitle", "slug": "subtitle", "status": "active", "canonId": "019de52c-fb09-739d-900c-815b0d9ac526", "version": 1, "description": null }, "framework": null }, "subkind": "subtitle", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.915+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "3469ca6b-c5c5-4a2f-a8e7-bac38a0fcd1b", "parentComponentId": null } ], "metrics": [], "tools": [ { "tool": { "name": "Problem Statement Canvas", "slug": "problem-statement-canvas", "status": "active", "bestFor": null, "canonId": "019dd956-839d-744b-ad11-9bf3e3642a18", "version": 1, "bodyDocId": null, "description": "Structured definition of the problem: What? Who? Where? When? Scale?", "familyLabel": null, "categoryName": "Block", "categorySlug": "block" }, "agent": "Architect", "layer": "slide", "agents": [ "Architect" ], "matchId": "049de222-4f62-458a-a13c-46915fc6e68f", "evidence": "The slide describes a specific problem in financial analysis and a proposed solution.", "pageRefs": null, "priority": null, "whenToUse": null, "confidence": 0.5, "extraction": { "at": "2026-07-17 03:19:52.472887+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": null }, "pageNumber": 11, "whyItWorks": null, "antipattern": null, "cardinality": null, "narrativePurpose": null } ], "frameworks": [], "arcBeats": [ { "to": 13, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null }, "from": 8, "name": "Evidence & Proof", "beatId": "8c4a78bd-1b53-456f-9179-be874097af96", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Evidence & Proof", "slug": "consultants-gambit-evidence-proof", "status": "active", "canonId": "019dd9b8-07b1-7688-8e1e-7637fec3802a", "version": 1, "description": null }, "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI in data extraction", "position": 3, "isPrimaryArc": true, "parentBeatType": { "name": "Evidence", "slug": "evidence", "status": "active", "canonId": "019dd9b8-03f9-772a-b84a-4f07b415b77a", "version": 1, "description": "A dedicated proof beat exists in only ~4 arcs (Gambit, Sequoia, AIDA, Monroes). Other arcs embed evidence inline within development." }, "alignedBlockIds": null, "matchConfidence": 0.8 } ], "loops": [ { "to": 13, "from": 8, "loop": { "name": "05_the_reveal", "slug": "05-the-reveal", "status": "active", "bestFor": "Product launches, strategic pivots, unexpected findings", "canonId": "019dd956-67e8-77bc-a867-02c2b36370bd", "version": 1, "bodyDocId": "019df22a-2420-77be-bc41-ded96d08cb21", "structure": "Setup the Question -> Build Suspense -> The Big Reveal", "description": "Build mystery and anticipation, then deliver a surprising or powerful conclusion", "familyLabel": null }, "matchId": "22c3ec8f-4e2e-4190-bd35-ca7dceee7d84", "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI", "position": 1, "objective": "Reveal the benefits of Gen AI in data extraction", "confidence": 0.7, "extraction": { "at": "2026-07-17 03:16:08.325926+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": "doc-narrative-v1" } } ], "locked": true }, { "page": 12, "type": "setup", "title": "The slide details a two-tiered retrieval mechanism for financial data extraction.", "function": "present_solution", "rawType": "implementation_plan", "block": null, "metadata": { "slideType": "implementation_plan", "slideTypeCanon": { "name": "Implementation plan", "slug": "implementation_plan", "status": "active", "canonId": "019de52d-0d75-700b-ae9f-f6069ba6e37a", "version": 1, "description": null }, "function": "present_solution", "functionCanon": { "name": "Present solution", "slug": "present_solution", "status": "active", "canonId": "019de52d-15b8-71da-bd23-2b767850cbce", "version": 1, "description": null }, "density": "dense", "densityScore": 58, "componentCount": 7, "textChars": 666, "nDataPoints": 0, "notes": "The slide details a two-tiered retrieval mechanism for financial data extraction.", "elementsJson": [ "headline_text", "process_diagram", "paragraph", "photo" ], "confidence": 1, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:57.916+00", "seconds": 2.791, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/12", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-12", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": null, "kind": "callout", "text": "The process begins with the analysis of PDF Financial reports to accurately capture table-based data. It then transforms that data into a structure that is more suitable to LLM processing.", "attrs": null, "canon": { "kind": { "name": "Callout", "slug": "callout", "status": "active", "canonId": "019de52c-f8d3-761a-8953-7d37080de5e2", "version": 1, "description": "Highlighted callout box." }, "tool": { "name": "Visual emphasis", "slug": "visual-emphasis", "status": "active", "bestFor": null, "canonId": "019dd9e1-474b-736b-a8eb-a794dd88241c", "version": 1, "bodyDocId": null, "description": "Drawing the eye to one element above the rest of the slide.", "familyLabel": null }, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-04-24 16:25:33+00", "model": "or:google/gemini-3.1-flash-lite-preview", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "019dd952-340f-723f-8a13-ee6462a88592", "parentComponentId": null }, { "bbox": { "h": 0.52, "w": 0.55, "x": 0.04, "y": 0.18 }, "kind": "diagram", "text": "Workflow diagram showing PDF parsing, tabular data extraction, Elastic Stack processing, and two-layer retrieval.", "attrs": null, "canon": { "kind": { "name": "Diagram", "slug": "diagram", "status": "active", "canonId": "019de52c-f9f0-734a-81de-15382ff28c65", "version": 1, "description": "Schematic or relational diagram." }, "tool": null, "subkind": { "name": "Process flow", "slug": "process", "status": "active", "canonId": "019de52d-039c-718f-ad3a-efe9c4b3c838", "version": 1, "description": null }, "framework": null }, "subkind": "process", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.916+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "f28aae83-caf1-44d1-a845-38f286d95c6f", "parentComponentId": null }, { "bbox": { "h": 1, "w": 0.38, "x": 0.62, "y": 0 }, "kind": "image", "text": "Person working in a server room", "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Photo", "slug": "photo", "status": "active", "canonId": "019de52c-fd37-757f-b4a8-ca26d4888875", "version": 1, "description": null }, "framework": null }, "subkind": "photo", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.916+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "bae427fd-9afa-415b-b62d-33c1ee0f7c2d", "parentComponentId": null }, { "bbox": { "h": 0.15, "w": 0.58, "x": 0.04, "y": 0.78 }, "kind": "paragraph", "text": "Figure 6 illustrates the workflow of the financial data extraction solution. The process begins with the analysis of PDF Financial reports to accurately capture table-based data.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.916+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "f21ed07c-f85e-4953-b314-8629914a36fe", "parentComponentId": null }, { "bbox": { "h": 0.03, "w": 0.28, "x": 0.18, "y": 0.69 }, "kind": "source-note", "text": "Figure 6: EY's solution of financial Variables extraction", "attrs": null, "canon": { "kind": { "name": "Source note", "slug": "source-note", "status": "active", "canonId": "23484952-494b-4a5e-b1ad-550d0d70e948", "version": 1, "description": "Attribution / source / caveat placed at the slide footer. Numbered footnotes use attrs.numbered." }, "tool": null, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.916+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "6872e171-9017-4edd-b096-5f40f7614761", "parentComponentId": null }, { "bbox": { "h": 0.04, "w": 0.45, "x": 0.04, "y": 0.08 }, "kind": "title", "text": "Use case implementation evaluation (Cont'd)", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.916+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "b7668e52-5cdc-488c-954a-eb9989bf410c", "parentComponentId": null }, { "bbox": { "h": 0.03, "w": 0.45, "x": 0.04, "y": 0.13 }, "kind": "title", "text": "2. Extracting financial variables from financial reports", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Subtitle", "slug": "subtitle", "status": "active", "canonId": "019de52c-fb09-739d-900c-815b0d9ac526", "version": 1, "description": null }, "framework": null }, "subkind": "subtitle", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:57.916+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "21eb2930-c8a9-4fda-9420-6c8f6482431f", "parentComponentId": null } ], "metrics": [], "tools": [], "frameworks": [], "arcBeats": [ { "to": 13, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null }, "from": 8, "name": "Evidence & Proof", "beatId": "8c4a78bd-1b53-456f-9179-be874097af96", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Evidence & Proof", "slug": "consultants-gambit-evidence-proof", "status": "active", "canonId": "019dd9b8-07b1-7688-8e1e-7637fec3802a", "version": 1, "description": null }, "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI in data extraction", "position": 3, "isPrimaryArc": true, "parentBeatType": { "name": "Evidence", "slug": "evidence", "status": "active", "canonId": "019dd9b8-03f9-772a-b84a-4f07b415b77a", "version": 1, "description": "A dedicated proof beat exists in only ~4 arcs (Gambit, Sequoia, AIDA, Monroes). Other arcs embed evidence inline within development." }, "alignedBlockIds": null, "matchConfidence": 0.8 } ], "loops": [ { "to": 13, "from": 8, "loop": { "name": "05_the_reveal", "slug": "05-the-reveal", "status": "active", "bestFor": "Product launches, strategic pivots, unexpected findings", "canonId": "019dd956-67e8-77bc-a867-02c2b36370bd", "version": 1, "bodyDocId": "019df22a-2420-77be-bc41-ded96d08cb21", "structure": "Setup the Question -> Build Suspense -> The Big Reveal", "description": "Build mystery and anticipation, then deliver a surprising or powerful conclusion", "familyLabel": null }, "matchId": "22c3ec8f-4e2e-4190-bd35-ca7dceee7d84", "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI", "position": 1, "objective": "Reveal the benefits of Gen AI in data extraction", "confidence": 0.7, "extraction": { "at": "2026-07-17 03:16:08.325926+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": "doc-narrative-v1" } } ], "locked": true }, { "page": 13, "type": "evidence", "title": "The slide highlights a 24% accuracy improvement using the EY solution.", "function": "quantify_impact", "rawType": "case_study", "block": null, "metadata": { "slideType": "case_study", "slideTypeCanon": { "name": "Case study", "slug": "case_study", "status": "active", "canonId": "019de52d-0b95-7344-8090-926f3b8e92c8", "version": 1, "description": null }, "function": "quantify_impact", "functionCanon": { "name": "Quantify impact", "slug": "quantify_impact", "status": "active", "canonId": "019de52d-1630-720d-b57d-fa7f76bebd8d", "version": 1, "description": null }, "density": "dense", "densityScore": 72, "componentCount": 7, "textChars": 1052, "nDataPoints": 10, "notes": "The slide highlights a 24% accuracy improvement using the EY solution.", "elementsJson": [ "headline_text", "bar_chart_grouped", "paragraph" ], "confidence": 1, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:58.642+00", "seconds": 2.962, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/13", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-13", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": null, "kind": "callout", "text": "In summary, the EY solution has made remarkable strides in accuracy enhancement, illustrating significant performance boosts where some instances reveal accuracy enhancements of nearly 24% compared to traditional RAG methods.", "attrs": null, "canon": { "kind": { "name": "Callout", "slug": "callout", "status": "active", "canonId": "019de52c-f8d3-761a-8953-7d37080de5e2", "version": 1, "description": "Highlighted callout box." }, "tool": { "name": "Visual emphasis", "slug": "visual-emphasis", "status": "active", "bestFor": null, "canonId": "019dd9e1-474b-736b-a8eb-a794dd88241c", "version": 1, "bodyDocId": null, "description": "Drawing the eye to one element above the rest of the slide.", "familyLabel": null }, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-04-24 16:25:33+00", "model": "or:google/gemini-3.1-flash-lite-preview", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "019dd952-340f-723f-8a13-9d88ca0b0b76", "parentComponentId": null }, { "bbox": { "h": 0.35, "w": 0.38, "x": 0.07, "y": 0.185 }, "kind": "chart", "text": "Accuracy comparison between EY Solution and Naive RAG across 5 banks", "attrs": null, "canon": { "kind": { "name": "Chart", "slug": "chart", "status": "active", "canonId": "019de52c-f9a0-76ef-adc6-0b859109d1f8", "version": 1, "description": "Quantitative chart." }, "tool": null, "subkind": { "name": "Grouped bar chart", "slug": "bar-grouped", "status": "active", "canonId": "019de52c-ff3b-751e-a8ff-f21ff11097b1", "version": 1, "description": null }, "framework": null }, "subkind": "bar-grouped", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.642+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "7692e2b7-47d8-480f-81e0-7e66990027b4", "parentComponentId": null }, { "bbox": { "h": 0.04, "w": 0.42, "x": 0.068, "y": 0.568 }, "kind": "legend", "text": "Figure 7: The performance of the EY solution in 2023 Q1 Supplementary Financial Reports", "attrs": null, "canon": { "kind": { "name": "Legend", "slug": "legend", "status": "active", "canonId": "31361933-3d22-4c70-bbad-0801e9fffc0c", "version": 1, "description": "Color/symbol decoder placed adjacent to a chart or diagram." }, "tool": null, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.642+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "800d27d9-c63f-485b-9d5e-611573ffb50d", "parentComponentId": null }, { "bbox": null, "kind": "metric", "text": "Accuracy: 24%", "attrs": null, "canon": { "kind": { "name": "Metric", "slug": "metric", "status": "active", "canonId": "019de52c-f923-73bf-8081-d0b1a8c5264d", "version": 1, "description": "Big-number or KPI value." }, "tool": { "name": "Quantification", "slug": "quantification", "status": "active", "bestFor": null, "canonId": "019dd9e1-47ab-72ce-a079-aab1f5299e88", "version": 1, "bodyDocId": null, "description": "Translating a claim into numbers, charts, or tables.", "familyLabel": null }, "subkind": null, "framework": null }, "subkind": "primary", "groupRole": null, "confidence": null, "extraction": { "at": "2026-04-24 16:25:33+00", "model": "or:google/gemini-3.1-flash-lite-preview", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "019dd952-340f-723f-8a13-a0bf388c2157", "parentComponentId": null }, { "bbox": { "h": 0.25, "w": 0.48, "x": 0.468, "y": 0.185 }, "kind": "paragraph", "text": "Figure 7 showcases the performance of the EY solution in 2023 Q1 Supplementary Financial Reports. In summary, the EY solution has made remarkable strides in accuracy enhancement, illustrating significant performance boosts where some instances reveal accuracy enhancements of nearly 24% compared to traditional RAG methods. This advancement not only refines the data extraction process but also elevates the quality of insights extracted from financial reports, setting a new standard for both efficiency and robustness in the realm of financial data analytics", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.642+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "c8ba3547-78ab-45e5-bb60-519ca9a0239c", "parentComponentId": null }, { "bbox": { "h": 0.02, "w": 0.35, "x": 0.048, "y": 0.138 }, "kind": "paragraph", "text": "2. Extracting financial variables from financial reports", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.642+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "da59d211-9bb3-4e3f-9ad1-d679a969adb7", "parentComponentId": null }, { "bbox": { "h": 0.035, "w": 0.415, "x": 0.048, "y": 0.095 }, "kind": "title", "text": "Use case implementation evaluation (Cont'd)", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.642+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "49d51683-46e3-4002-b10a-5dff318d3fe5", "parentComponentId": null } ], "metrics": [], "tools": [ { "tool": { "name": "Chart Selection Guide", "slug": "chart-selection-guide", "status": "active", "bestFor": null, "canonId": "019dd956-b1a0-700b-ba17-0e16c4d5bcae", "version": 1, "bodyDocId": null, "description": "Choosing the right chart type for your data and message", "familyLabel": null, "categoryName": "Slide", "categorySlug": "slide" }, "agent": "Designer", "layer": "slide", "agents": [ "Designer" ], "matchId": "ecafc3b4-2d0d-4a8f-92e5-ad01cef7fc66", "evidence": "The slide presents a bar chart comparing the accuracy of EY's solution and a naive approach.", "pageRefs": null, "priority": null, "whenToUse": null, "confidence": 0.7, "extraction": { "at": "2026-07-17 03:19:52.588318+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": null }, "pageNumber": 13, "whyItWorks": null, "antipattern": null, "cardinality": null, "narrativePurpose": null } ], "frameworks": [], "arcBeats": [ { "to": 13, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null }, "from": 8, "name": "Evidence & Proof", "beatId": "8c4a78bd-1b53-456f-9179-be874097af96", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Evidence & Proof", "slug": "consultants-gambit-evidence-proof", "status": "active", "canonId": "019dd9b8-07b1-7688-8e1e-7637fec3802a", "version": 1, "description": null }, "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI in data extraction", "position": 3, "isPrimaryArc": true, "parentBeatType": { "name": "Evidence", "slug": "evidence", "status": "active", "canonId": "019dd9b8-03f9-772a-b84a-4f07b415b77a", "version": 1, "description": "A dedicated proof beat exists in only ~4 arcs (Gambit, Sequoia, AIDA, Monroes). Other arcs embed evidence inline within development." }, "alignedBlockIds": null, "matchConfidence": 0.8 } ], "loops": [ { "to": 13, "from": 8, "loop": { "name": "05_the_reveal", "slug": "05-the-reveal", "status": "active", "bestFor": "Product launches, strategic pivots, unexpected findings", "canonId": "019dd956-67e8-77bc-a867-02c2b36370bd", "version": 1, "bodyDocId": "019df22a-2420-77be-bc41-ded96d08cb21", "structure": "Setup the Question -> Build Suspense -> The Big Reveal", "description": "Build mystery and anticipation, then deliver a surprising or powerful conclusion", "familyLabel": null }, "matchId": "22c3ec8f-4e2e-4190-bd35-ca7dceee7d84", "evidence": "The deck provides a case study to demonstrate the effectiveness of Gen AI", "position": 1, "objective": "Reveal the benefits of Gen AI in data extraction", "confidence": 0.7, "extraction": { "at": "2026-07-17 03:16:08.325926+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": "doc-narrative-v1" } } ], "locked": true }, { "page": 14, "type": "setup", "function": "summarize", "rawType": "closing_ask", "block": null, "metadata": { "slideType": "closing_ask", "slideTypeCanon": { "name": "Closing ask", "slug": "closing_ask", "status": "active", "canonId": "019de52d-0aa4-750f-8aa1-8d622dd99f5c", "version": 1, "description": null }, "function": "summarize", "functionCanon": { "name": "Summarize", "slug": "summarize", "status": "active", "canonId": "019de52d-1541-704f-b86f-bf7b75056373", "version": 1, "description": null }, "density": "balanced", "densityScore": 36, "componentCount": 4, "textChars": 686, "nDataPoints": 0, "notes": null, "elementsJson": [ "paragraph", "photo" ], "confidence": 1, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:58.663+00", "seconds": 2.839, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/14", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-14", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": null, "kind": "callout", "text": "Generative AI plays a pivotal role in revolutionizing data retrieval in the financial services sector.", "attrs": null, "canon": { "kind": { "name": "Callout", "slug": "callout", "status": "active", "canonId": "019de52c-f8d3-761a-8953-7d37080de5e2", "version": 1, "description": "Highlighted callout box." }, "tool": { "name": "Visual emphasis", "slug": "visual-emphasis", "status": "active", "bestFor": null, "canonId": "019dd9e1-474b-736b-a8eb-a794dd88241c", "version": 1, "bodyDocId": null, "description": "Drawing the eye to one element above the rest of the slide.", "familyLabel": null }, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-04-24 16:25:33+00", "model": "or:google/gemini-3.1-flash-lite-preview", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "019dd952-340f-723f-8a13-b5637e1b6bc5", "parentComponentId": null }, { "bbox": { "h": 0.73, "w": 0.5, "x": 0.452, "y": 0.183 }, "kind": "image", "text": null, "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Photo", "slug": "photo", "status": "active", "canonId": "019de52c-fd37-757f-b4a8-ca26d4888875", "version": 1, "description": null }, "framework": null }, "subkind": "photo", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.663+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "caed7792-0d9b-4a72-9818-383d64289da0", "parentComponentId": null }, { "bbox": { "h": 0.26, "w": 0.365, "x": 0.048, "y": 0.183 }, "kind": "paragraph", "text": "Generative AI plays a pivotal role in revolutionizing data retrieval in the financial services sector. It showcases how integrating advanced search technologies with AI can greatly improve the extraction of complex data from diverse documents, setting new standards for accuracy, speed and scalability. The demonstrated solutions not only address current data analysis challenges but also pave the way for future innovation, emphasizing the importance of adopting AI-driven strategies to fully capitalize on the growing volumes of data in informed decision-making processes.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.663+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "530233c8-e780-49d1-9af1-0caf355bc046", "parentComponentId": null }, { "bbox": { "h": 0.035, "w": 0.175, "x": 0.048, "y": 0.095 }, "kind": "title", "text": "Conclusion", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.663+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "30c18353-9278-4ee2-9937-2a80b7945252", "parentComponentId": null } ], "metrics": [], "tools": [ { "tool": { "name": "Storytelling: the closing ask", "slug": "closing-ask", "status": "active", "bestFor": null, "canonId": "019df269-24e0-70ab-8dd9-983832c1c665", "version": 1, "bodyDocId": "019df269-24bc-7554-b88d-245127606b8d", "description": "The single most important slide in the deck — after the cover. The final", "familyLabel": "narrative-block", "categoryName": "Narrative & Transformation", "categorySlug": "narrative-transformation" }, "agent": "storyteller", "layer": "slide", "agents": [ "storyteller" ], "matchId": "f44f4c0d-3f02-4ad5-8fd5-f6e230ebc265", "evidence": "The slide is titled 'Conclusion' and presents a summary of the main points.", "pageRefs": null, "priority": null, "whenToUse": null, "confidence": 0.9, "extraction": { "at": "2026-07-17 03:19:52.672921+00", "model": "or:meta-llama/llama-4-scout", "runId": null, "seconds": null, "promptVersion": null }, "pageNumber": 14, "whyItWorks": null, "antipattern": null, "cardinality": null, "narrativePurpose": null } ], "frameworks": [], "arcBeats": [ { "to": 14, "arc": { "name": "The Consultant's Gambit", "slug": "consultants-gambit", "status": "active", "bestFor": "Business cases, project proposals, strategic recommendations", "canonId": "019dd956-5e0a-73c8-b305-81c38c959e9c", "version": 1, "bodyDocId": "019df22a-2356-73eb-8061-d8c81dc0aa49", "structure": "Situation & Context -> Problem & Complication -> Solution & Approach -> Evidence & Proof -> Impact & Next Steps", "description": null, "familyLabel": null }, "from": 14, "name": "Impact & Next Steps", "beatId": "04e4435f-987f-49e9-bd77-b8061242e7cf", "matchId": "3e91d6c5-1638-4e7b-9dd8-c848749767eb", "beatType": { "name": "Impact & Next Steps", "slug": "consultants-gambit-impact-next-steps", "status": "active", "canonId": "019dd9b8-0849-7728-9ee9-fd1609c4c655", "version": 1, "description": null }, "evidence": "The deck concludes with a call to action and a summary of the benefits of Gen AI in data extraction", "position": 4, "isPrimaryArc": true, "parentBeatType": { "name": "Resolution", "slug": "resolution", "status": "active", "canonId": "019dd9b8-045d-703b-8dd7-e92aba3ba91b", "version": 1, "description": "How the deck ends. Required in 19/20 arcs. The exception (Sparkline) ends with new bliss which is functionally a resolution." }, "alignedBlockIds": null, "matchConfidence": 0.8 } ], "loops": [], "locked": true }, { "page": 15, "type": "setup", "function": "other", "rawType": "team_bio", "block": null, "metadata": { "slideType": "team_bio", "slideTypeCanon": { "name": "Team bio", "slug": "team_bio", "status": "active", "canonId": "019de52d-0a7d-7394-ae5b-037478e71f1e", "version": 1, "description": null }, "function": "other", "functionCanon": { "name": "Other (fallback)", "slug": "other", "status": "active", "canonId": "019de52d-15e1-75bc-99dc-07732380e2ce", "version": 1, "description": null }, "density": "dense", "densityScore": 50, "componentCount": 10, "textChars": 109, "nDataPoints": 0, "notes": null, "elementsJson": [ "headshot", "other" ], "confidence": 1, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:58.838+00", "seconds": 2.893, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/15", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-15", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": { "h": 0.1, "w": 0.25, "x": 0.365, "y": 0.22 }, "kind": "image", "text": "Ian Santee", "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Headshot", "slug": "headshot", "status": "active", "canonId": "019de52c-fd5f-765c-9282-38b54f61bbbf", "version": 1, "description": null }, "framework": null }, "subkind": "headshot", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.838+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "1b8a1ff4-0f1a-421d-abaf-222ff9058422", "parentComponentId": null }, { "bbox": { "h": 0.1, "w": 0.25, "x": 0.048, "y": 0.58 }, "kind": "image", "text": "Morgan Wang", "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Headshot", "slug": "headshot", "status": "active", "canonId": "019de52c-fd5f-765c-9282-38b54f61bbbf", "version": 1, "description": null }, "framework": null }, "subkind": "headshot", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.838+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "3c323001-75d8-437d-a086-839dff597213", "parentComponentId": null }, { "bbox": { "h": 0.1, "w": 0.25, "x": 0.048, "y": 0.7 }, "kind": "image", "text": "Ahmad Ghawanmeh", "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Headshot", "slug": "headshot", "status": "active", "canonId": "019de52c-fd5f-765c-9282-38b54f61bbbf", "version": 1, "description": null }, "framework": null }, "subkind": "headshot", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.838+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "4092ca4f-9b5a-4629-ac76-56174736bc7e", "parentComponentId": null }, { "bbox": { "h": 0.1, "w": 0.25, "x": 0.048, "y": 0.46 }, "kind": "image", "text": "Vishaal Venkatesh", "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Headshot", "slug": "headshot", "status": "active", "canonId": "019de52c-fd5f-765c-9282-38b54f61bbbf", "version": 1, "description": null }, "framework": null }, "subkind": "headshot", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.838+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "7748a0c7-4c4a-404c-9817-00114777a796", "parentComponentId": null }, { "bbox": { "h": 0.1, "w": 0.25, "x": 0.048, "y": 0.34 }, "kind": "image", "text": "Kiranjot Dhillon", "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Headshot", "slug": "headshot", "status": "active", "canonId": "019de52c-fd5f-765c-9282-38b54f61bbbf", "version": 1, "description": null }, "framework": null }, "subkind": "headshot", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.838+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "b3fcc1cd-8dc1-4c85-8f4f-77e696bbd1a9", "parentComponentId": null }, { "bbox": { "h": 0.1, "w": 0.25, "x": 0.365, "y": 0.34 }, "kind": "image", "text": "Thaddeus Walsh", "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Headshot", "slug": "headshot", "status": "active", "canonId": "019de52c-fd5f-765c-9282-38b54f61bbbf", "version": 1, "description": null }, "framework": null }, "subkind": "headshot", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.838+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "cde724bd-ef6b-4908-bb9d-274bedf3efae", "parentComponentId": null }, { "bbox": { "h": 0.1, "w": 0.25, "x": 0.048, "y": 0.22 }, "kind": "image", "text": "Yara Elias", "attrs": null, "canon": { "kind": { "name": "Image", "slug": "image", "status": "active", "canonId": "019de52c-f978-701f-a720-51d029d769e7", "version": 1, "description": "Photo, illustration, screenshot or icon." }, "tool": null, "subkind": { "name": "Headshot", "slug": "headshot", "status": "active", "canonId": "019de52c-fd5f-765c-9282-38b54f61bbbf", "version": 1, "description": null }, "framework": null }, "subkind": "headshot", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.838+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "d50898f7-b9af-48a0-a40b-ba9c59286e86", "parentComponentId": null }, { "bbox": { "h": 0.04, "w": 0.14, "x": 0.048, "y": 0.095 }, "kind": "title", "text": "Authors", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.838+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "a7550e1c-c837-45be-8451-41b072a2a18b", "parentComponentId": null }, { "bbox": { "h": 0.03, "w": 0.03, "x": 0.048, "y": 0.165 }, "kind": "title", "text": "EY", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Subtitle", "slug": "subtitle", "status": "active", "canonId": "019de52c-fb09-739d-900c-815b0d9ac526", "version": 1, "description": null }, "framework": null }, "subkind": "subtitle", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.838+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "5873baa8-a7f4-40bd-983b-750f1ae2e59f", "parentComponentId": null }, { "bbox": { "h": 0.03, "w": 0.06, "x": 0.365, "y": 0.165 }, "kind": "title", "text": "Elastic", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Subtitle", "slug": "subtitle", "status": "active", "canonId": "019de52c-fb09-739d-900c-815b0d9ac526", "version": 1, "description": null }, "framework": null }, "subkind": "subtitle", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:58.838+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "824d8f58-19f5-460d-a767-af2d54eb932f", "parentComponentId": null } ], "metrics": [], "tools": [], "frameworks": [], "arcBeats": [], "loops": [], "locked": true }, { "page": 16, "type": "setup", "function": "other", "rawType": "appendix_disclosure", "block": null, "metadata": { "slideType": "appendix_disclosure", "slideTypeCanon": { "name": "Appendix disclosure", "slug": "appendix_disclosure", "status": "active", "canonId": "019de52d-07b2-7549-8e8b-932a19f6e616", "version": 1, "description": null }, "function": "other", "functionCanon": { "name": "Other (fallback)", "slug": "other", "status": "active", "canonId": "019de52d-15e1-75bc-99dc-07732380e2ce", "version": 1, "description": null }, "density": "dense", "densityScore": 54, "componentCount": 5, "textChars": 1888, "nDataPoints": 0, "notes": null, "elementsJson": [ "paragraph" ], "confidence": 1, "extraction": { "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "at": "2026-05-02 18:05:59.73+00", "seconds": 3.524, "promptVersion": "v2-canon-conditioned" } }, "links": { "slide": "/slides/019dd923-5e88-73ef-bd59-174b7f7da09c/16", "deck": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c", "deckAnchor": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c#slide-16", "deckJson": "/decks/019dd923-5e88-73ef-bd59-174b7f7da09c.json" }, "components": [ { "bbox": null, "kind": "callout", "text": "All in to shape the future with confidence.", "attrs": null, "canon": { "kind": { "name": "Callout", "slug": "callout", "status": "active", "canonId": "019de52c-f8d3-761a-8953-7d37080de5e2", "version": 1, "description": "Highlighted callout box." }, "tool": { "name": "Visual emphasis", "slug": "visual-emphasis", "status": "active", "bestFor": null, "canonId": "019dd9e1-474b-736b-a8eb-a794dd88241c", "version": 1, "bodyDocId": null, "description": "Drawing the eye to one element above the rest of the slide.", "familyLabel": null }, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-04-24 16:25:32+00", "model": "or:google/gemini-3.1-flash-lite-preview", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "019dd952-340f-723f-8a13-8f4957584b50", "parentComponentId": null }, { "bbox": { "h": 0.225, "w": 0.385, "x": 0.048, "y": 0.695 }, "kind": "disclaimer", "text": "© 2025 Ernst & Young LLP. All Rights Reserved. 4713104. This publication contains information in summary form, current as of the date of publication, and is intended for general guidance only. It should not be regarded as comprehensive or a substitute for professional advice. Before taking any particular course of action, contact Ernst & Young or another professional advisor to discuss these matters in the context of your particular circumstances. We accept no responsibility for any loss or damage occasioned by your reliance on information contained in this publication. ey.com/ca", "attrs": null, "canon": { "kind": { "name": "Disclaimer", "slug": "disclaimer", "status": "active", "canonId": "91173477-d91f-4024-bbaf-d4f93e3f82dc", "version": 1, "description": "Legal/cautionary text that occupies most of the body of its slide." }, "tool": null, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:59.73+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "48b38fae-8267-458d-b4c1-f1e4d262d161", "parentComponentId": null }, { "bbox": { "h": 0.155, "w": 0.385, "x": 0.048, "y": 0.525 }, "kind": "disclaimer", "text": "EY refers to the global organization, and may refer to one or more, of the member firms of Ernst & Young Global Limited, each of which is a separate legal entity. Ernst & Young Global Limited, a UK company limited by guarantee, does not provide services to clients. Information about how EY collects and uses personal data and a description of the rights individuals have under data protection legislation are available via ey.com/privacy. EY member firms do not practice law where prohibited by local laws. For more information about our organization, please visit ey.com.", "attrs": null, "canon": { "kind": { "name": "Disclaimer", "slug": "disclaimer", "status": "active", "canonId": "91173477-d91f-4024-bbaf-d4f93e3f82dc", "version": 1, "description": "Legal/cautionary text that occupies most of the body of its slide." }, "tool": null, "subkind": null, "framework": null }, "subkind": null, "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:59.73+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "eaf7a583-c6fb-4a62-8c02-55113067a00d", "parentComponentId": null }, { "bbox": { "h": 0.338, "w": 0.385, "x": 0.048, "y": 0.139 }, "kind": "paragraph", "text": "EY is building a better working world by creating new value for clients, people, society and the planet, while building trust in capital markets. Enabled by data, AI and advanced technology, EY teams help clients shape the future with confidence and develop answers for the most pressing issues of today and tomorrow. EY teams work across a full spectrum of services in assurance, consulting, tax, strategy and transactions. Fueled by sector insights, a globally connected, multi-disciplinary network and diverse ecosystem partners, EY teams can provide services in more than 150 countries and territories. All in to shape the future with confidence.", "attrs": null, "canon": { "kind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "5f2affc0-941d-4d07-959d-4bfc1930cea4", "version": 1, "description": "Single prose block in the body of a slide." }, "tool": null, "subkind": { "name": "Paragraph", "slug": "paragraph", "status": "active", "canonId": "019de52c-fb80-75af-aa5c-a7a4bfac2433", "version": 1, "description": null }, "framework": null }, "subkind": "paragraph", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:59.73+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "4910ad89-43c1-4ced-a5fd-df50a11783f1", "parentComponentId": null }, { "bbox": { "h": 0.022, "w": 0.263, "x": 0.048, "y": 0.075 }, "kind": "title", "text": "EY | Building a better working world", "attrs": null, "canon": { "kind": { "name": "Title", "slug": "title", "status": "active", "canonId": "019de52c-f7dd-76d9-b848-b1f12bd85cf4", "version": 1, "description": "Slide title or headline." }, "tool": null, "subkind": { "name": "Headline", "slug": "headline", "status": "active", "canonId": "019de52c-fae1-7463-9a7c-d60668eced0d", "version": 1, "description": null }, "framework": null }, "subkind": "headline", "groupRole": null, "confidence": null, "extraction": { "at": "2026-05-02 18:05:59.73+00", "model": "google/gemini-3.1-flash-lite-preview-20260303", "runId": null, "seconds": null, "promptVersion": null }, "componentId": "622bd6e9-060b-43b3-943a-03972c490c64", "parentComponentId": null } ], "metrics": [], "tools": [], "frameworks": [], "arcBeats": [], "loops": [], "locked": true } ], "arcBeats": [ { "from": 3, "to": 4, "label": "Situation & Context", "description": "The deck provides an introduction to the current state and main challenges of data extraction" }, { "from": 4, "to": 5, "label": "Problem & Complication", "description": "The deck highlights the inefficiencies of current data extraction methods" }, { "from": 5, "to": 6, "label": "Solution & Approach", "description": "The deck presents Gen AI as a solution to improve data extraction efficiency" }, { "from": 8, "to": 13, "label": "Evidence & Proof", "description": "The deck provides a case study to demonstrate the effectiveness of Gen AI in data extraction" }, { "from": 14, "to": 14, "label": "Impact & Next Steps", "description": "The deck concludes with a call to action and a summary of the benefits of Gen AI in data extraction" } ], "loops": [ { "from": 3, "to": 6, "label": "Pattern Hunter", "description": "Identify patterns in current data extraction methods" }, { "from": 8, "to": 13, "label": "The Reveal", "description": "Reveal the benefits of Gen AI in data extraction" } ] }