{ "kind": "all", "value": "all", "collectionKey": "slides:all:all:all-document-kinds:all-producers:all-orientations", "filters": { "documentKinds": [], "sourceTypes": [], "orientations": [] }, "total": 319975, "page": 1846, "pageSize": 30, "pageCount": 10666, "rows": [ { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 5, "slideType": "timeline", "function": "present_framework", "notes": "The slide uses a maturity model framework to show the progression of AI capabilities.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/5", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-5", "loopMatches": [ { "to": 9, "from": 5, "name": "Maturity Curve", "slug": "36-maturity-curve", "bestFor": "Digital transformation, capability building, benchmarking", "matchId": "019dd95a-088b-72c8-b7df-ef1b695c53c3", "evidence": "p5 five-stage horizontal progression with 'At scale / Still early / Very early' tags; pp6-9 unpack drivers and end-state", "position": 1, "objective": "Plot agent maturity from token predictors to multi-agent systems", "structure": "Current Maturity Level -> The Gap to Next Level -> Required Capabilities -> The Roadmap", "confidence": 80, "description": "Show where you are on a progression and what it takes to reach the next level" } ], "arcBeatMatches": [ { "to": 9, "from": 2, "beatId": "019dd95a-0682-776c-8e39-eb31cb1a8081", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Situation & Context", "beatSlug": "consultants-gambit-situation-context", "evidence": "Section 01 'Agent evolution' establishes maturing field and multi-agent direction", "position": 1, "confidence": 82, "parentBeatName": "Setup", "parentBeatSlug": "setup" }, { "to": 12, "from": 4, "beatId": "019dd95a-0682-776c-8e39-fe448dff941c", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Facts (What)", "beatSlug": "triple-take-the-facts-what", "evidence": "Sections 01-02 inventory agent evolution and PMF cases", "position": 1, "confidence": 55, "parentBeatName": "Setup", "parentBeatSlug": "setup" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 6, "slideType": "industry_trends", "function": "summarize", "notes": "The slide uses a three-column layout to categorize the evolution of AI agents into community growth, framework development, and commercial proof-points.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/6", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-6", "loopMatches": [ { "to": 9, "from": 5, "name": "Maturity Curve", "slug": "36-maturity-curve", "bestFor": "Digital transformation, capability building, benchmarking", "matchId": "019dd95a-088b-72c8-b7df-ef1b695c53c3", "evidence": "p5 five-stage horizontal progression with 'At scale / Still early / Very early' tags; pp6-9 unpack drivers and end-state", "position": 1, "objective": "Plot agent maturity from token predictors to multi-agent systems", "structure": "Current Maturity Level -> The Gap to Next Level -> Required Capabilities -> The Roadmap", "confidence": 80, "description": "Show where you are on a progression and what it takes to reach the next level" } ], "arcBeatMatches": [ { "to": 9, "from": 2, "beatId": "019dd95a-0682-776c-8e39-eb31cb1a8081", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Situation & Context", "beatSlug": "consultants-gambit-situation-context", "evidence": "Section 01 'Agent evolution' establishes maturing field and multi-agent direction", "position": 1, "confidence": 82, "parentBeatName": "Setup", "parentBeatSlug": "setup" }, { "to": 12, "from": 4, "beatId": "019dd95a-0682-776c-8e39-fe448dff941c", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Facts (What)", "beatSlug": "triple-take-the-facts-what", "evidence": "Sections 01-02 inventory agent evolution and PMF cases", "position": 1, "confidence": 55, "parentBeatName": "Setup", "parentBeatSlug": "setup" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 7, "slideType": "industry_trends", "function": "summarize", "notes": "The slide uses a three-column layout to present distinct trends, each supported by metrics and visual evidence (screenshots/charts).", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/7", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-7", "loopMatches": [ { "to": 9, "from": 5, "name": "Maturity Curve", "slug": "36-maturity-curve", "bestFor": "Digital transformation, capability building, benchmarking", "matchId": "019dd95a-088b-72c8-b7df-ef1b695c53c3", "evidence": "p5 five-stage horizontal progression with 'At scale / Still early / Very early' tags; pp6-9 unpack drivers and end-state", "position": 1, "objective": "Plot agent maturity from token predictors to multi-agent systems", "structure": "Current Maturity Level -> The Gap to Next Level -> Required Capabilities -> The Roadmap", "confidence": 80, "description": "Show where you are on a progression and what it takes to reach the next level" } ], "arcBeatMatches": [ { "to": 9, "from": 2, "beatId": "019dd95a-0682-776c-8e39-eb31cb1a8081", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Situation & Context", "beatSlug": "consultants-gambit-situation-context", "evidence": "Section 01 'Agent evolution' establishes maturing field and multi-agent direction", "position": 1, "confidence": 82, "parentBeatName": "Setup", "parentBeatSlug": "setup" }, { "to": 12, "from": 4, "beatId": "019dd95a-0682-776c-8e39-fe448dff941c", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Facts (What)", "beatSlug": "triple-take-the-facts-what", "evidence": "Sections 01-02 inventory agent evolution and PMF cases", "position": 1, "confidence": 55, "parentBeatName": "Setup", "parentBeatSlug": "setup" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 8, "slideType": "comparison_table", "function": "compare_options", "notes": "The slide uses a process-flow diagram to contrast linear, gate-based workflows with iterative, feedback-loop-based autonomous agents.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/8", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-8", "loopMatches": [ { "to": 9, "from": 5, "name": "Maturity Curve", "slug": "36-maturity-curve", "bestFor": "Digital transformation, capability building, benchmarking", "matchId": "019dd95a-088b-72c8-b7df-ef1b695c53c3", "evidence": "p5 five-stage horizontal progression with 'At scale / Still early / Very early' tags; pp6-9 unpack drivers and end-state", "position": 1, "objective": "Plot agent maturity from token predictors to multi-agent systems", "structure": "Current Maturity Level -> The Gap to Next Level -> Required Capabilities -> The Roadmap", "confidence": 80, "description": "Show where you are on a progression and what it takes to reach the next level" } ], "arcBeatMatches": [ { "to": 9, "from": 2, "beatId": "019dd95a-0682-776c-8e39-eb31cb1a8081", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Situation & Context", "beatSlug": "consultants-gambit-situation-context", "evidence": "Section 01 'Agent evolution' establishes maturing field and multi-agent direction", "position": 1, "confidence": 82, "parentBeatName": "Setup", "parentBeatSlug": "setup" }, { "to": 12, "from": 4, "beatId": "019dd95a-0682-776c-8e39-fe448dff941c", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Facts (What)", "beatSlug": "triple-take-the-facts-what", "evidence": "Sections 01-02 inventory agent evolution and PMF cases", "position": 1, "confidence": 55, "parentBeatName": "Setup", "parentBeatSlug": "setup" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 9, "slideType": "market_landscape", "function": "present_framework", "notes": "The slide uses a three-tier architecture: Orchestration Agent, Human-Agent SCM Team, and Data/Tool Landscape.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/9", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-9", "loopMatches": [ { "to": 9, "from": 5, "name": "Maturity Curve", "slug": "36-maturity-curve", "bestFor": "Digital transformation, capability building, benchmarking", "matchId": "019dd95a-088b-72c8-b7df-ef1b695c53c3", "evidence": "p5 five-stage horizontal progression with 'At scale / Still early / Very early' tags; pp6-9 unpack drivers and end-state", "position": 1, "objective": "Plot agent maturity from token predictors to multi-agent systems", "structure": "Current Maturity Level -> The Gap to Next Level -> Required Capabilities -> The Roadmap", "confidence": 80, "description": "Show where you are on a progression and what it takes to reach the next level" } ], "arcBeatMatches": [ { "to": 9, "from": 2, "beatId": "019dd95a-0682-776c-8e39-eb31cb1a8081", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Situation & Context", "beatSlug": "consultants-gambit-situation-context", "evidence": "Section 01 'Agent evolution' establishes maturing field and multi-agent direction", "position": 1, "confidence": 82, "parentBeatName": "Setup", "parentBeatSlug": "setup" }, { "to": 12, "from": 4, "beatId": "019dd95a-0682-776c-8e39-fe448dff941c", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Facts (What)", "beatSlug": "triple-take-the-facts-what", "evidence": "Sections 01-02 inventory agent evolution and PMF cases", "position": 1, "confidence": 55, "parentBeatName": "Setup", "parentBeatSlug": "setup" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 10, "slideType": "section_divider", "function": "transition", "notes": null, "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/10", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-10", "loopMatches": [], "arcBeatMatches": [ { "to": 17, "from": 10, "beatId": "019dd95a-0682-776c-8e39-efdc0c3bfe92", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Problem & Complication", "beatSlug": "consultants-gambit-problem-complication", "evidence": "PMF reached only narrowly; 6-dim assessment exposes capability gaps", "position": 2, "confidence": 82, "parentBeatName": "Complication", "parentBeatSlug": "complication" }, { "to": 12, "from": 4, "beatId": "019dd95a-0682-776c-8e39-fe448dff941c", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Facts (What)", "beatSlug": "triple-take-the-facts-what", "evidence": "Sections 01-02 inventory agent evolution and PMF cases", "position": 1, "confidence": 55, "parentBeatName": "Setup", "parentBeatSlug": "setup" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 11, "slideType": "market_landscape", "function": "analyze_data", "notes": "The slide uses a table to show growth metrics for specific companies and a process-oriented diagram to show maturity requirements.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/11", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-11", "loopMatches": [ { "to": 12, "from": 11, "name": "Pattern Hunter", "slug": "02-pattern-hunter", "bestFor": "Time-pressed audiences, building consensus, when data is strong", "matchId": "019dd95a-088b-72c8-b7df-f39f00ba41ef", "evidence": "Cursor, Replit, Bolt, Lovable, V0, Windsurf revenue+user stats stack to a single PMF claim", "position": 2, "objective": "Aggregate vendor evidence into a PMF pattern", "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion", "confidence": 72, "description": "Group multiple pieces of evidence that together point to a pattern or conclusion" } ], "arcBeatMatches": [ { "to": 17, "from": 10, "beatId": "019dd95a-0682-776c-8e39-efdc0c3bfe92", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Problem & Complication", "beatSlug": "consultants-gambit-problem-complication", "evidence": "PMF reached only narrowly; 6-dim assessment exposes capability gaps", "position": 2, "confidence": 82, "parentBeatName": "Complication", "parentBeatSlug": "complication" }, { "to": 12, "from": 4, "beatId": "019dd95a-0682-776c-8e39-fe448dff941c", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Facts (What)", "beatSlug": "triple-take-the-facts-what", "evidence": "Sections 01-02 inventory agent evolution and PMF cases", "position": 1, "confidence": 55, "parentBeatName": "Setup", "parentBeatSlug": "setup" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 12, "slideType": "client_example", "function": "illustrate_case", "notes": "The slide uses a mix of specific company case studies and a summary of BCG's own client work to validate the thesis.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/12", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-12", "loopMatches": [ { "to": 12, "from": 11, "name": "Pattern Hunter", "slug": "02-pattern-hunter", "bestFor": "Time-pressed audiences, building consensus, when data is strong", "matchId": "019dd95a-088b-72c8-b7df-f39f00ba41ef", "evidence": "Cursor, Replit, Bolt, Lovable, V0, Windsurf revenue+user stats stack to a single PMF claim", "position": 2, "objective": "Aggregate vendor evidence into a PMF pattern", "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion", "confidence": 72, "description": "Group multiple pieces of evidence that together point to a pattern or conclusion" } ], "arcBeatMatches": [ { "to": 17, "from": 10, "beatId": "019dd95a-0682-776c-8e39-efdc0c3bfe92", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Problem & Complication", "beatSlug": "consultants-gambit-problem-complication", "evidence": "PMF reached only narrowly; 6-dim assessment exposes capability gaps", "position": 2, "confidence": 82, "parentBeatName": "Complication", "parentBeatSlug": "complication" }, { "to": 12, "from": 4, "beatId": "019dd95a-0682-776c-8e39-fe448dff941c", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Facts (What)", "beatSlug": "triple-take-the-facts-what", "evidence": "Sections 01-02 inventory agent evolution and PMF cases", "position": 1, "confidence": 55, "parentBeatName": "Setup", "parentBeatSlug": "setup" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 13, "slideType": "section_divider", "function": "transition", "notes": null, "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/13", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-13", "loopMatches": [], "arcBeatMatches": [ { "to": 17, "from": 10, "beatId": "019dd95a-0682-776c-8e39-efdc0c3bfe92", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Problem & Complication", "beatSlug": "consultants-gambit-problem-complication", "evidence": "PMF reached only narrowly; 6-dim assessment exposes capability gaps", "position": 2, "confidence": 82, "parentBeatName": "Complication", "parentBeatSlug": "complication" }, { "to": 17, "from": 13, "beatId": "019dd95a-0682-776c-8e3a-022aa9a7736c", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Implications (So What)", "beatSlug": "triple-take-the-implications-so-what", "evidence": "Section 03 reliability benchmarks and BCG capability framework", "position": 2, "confidence": 55, "parentBeatName": "Reflection", "parentBeatSlug": "reflection" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 14, "slideType": "industry_trends", "function": "summarize", "notes": "The slide highlights the shift in AI benchmarking from simple tasks to complex, multi-turn, and robust agent evaluation.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/14", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-14", "loopMatches": [ { "to": 15, "from": 14, "name": "Aha Moment", "slug": "03-aha-moment", "bestFor": "Data-heavy sections, research findings, analytical arguments", "matchId": "019dd95a-088b-72c8-b7df-f64c44f43b3b", "evidence": "p14 sets up agent benchmarks; p15 reveals METR exponential with 'month-long projects' dark callout", "position": 3, "objective": "Reveal the 7-month doubling capability insight", "structure": "The Problem/Question -> What the Data Shows -> The Insight", "confidence": 80, "description": "Establish a tension, present data, then deliver the insight that changes everything" } ], "arcBeatMatches": [ { "to": 17, "from": 10, "beatId": "019dd95a-0682-776c-8e39-efdc0c3bfe92", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Problem & Complication", "beatSlug": "consultants-gambit-problem-complication", "evidence": "PMF reached only narrowly; 6-dim assessment exposes capability gaps", "position": 2, "confidence": 82, "parentBeatName": "Complication", "parentBeatSlug": "complication" }, { "to": 17, "from": 13, "beatId": "019dd95a-0682-776c-8e3a-022aa9a7736c", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Implications (So What)", "beatSlug": "triple-take-the-implications-so-what", "evidence": "Section 03 reliability benchmarks and BCG capability framework", "position": 2, "confidence": 55, "parentBeatName": "Reflection", "parentBeatSlug": "reflection" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 15, "slideType": "industry_trends", "function": "quantify_impact", "notes": "The chart uses a logarithmic scale for task duration over time.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/15", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-15", "loopMatches": [ { "to": 15, "from": 14, "name": "Aha Moment", "slug": "03-aha-moment", "bestFor": "Data-heavy sections, research findings, analytical arguments", "matchId": "019dd95a-088b-72c8-b7df-f64c44f43b3b", "evidence": "p14 sets up agent benchmarks; p15 reveals METR exponential with 'month-long projects' dark callout", "position": 3, "objective": "Reveal the 7-month doubling capability insight", "structure": "The Problem/Question -> What the Data Shows -> The Insight", "confidence": 80, "description": "Establish a tension, present data, then deliver the insight that changes everything" } ], "arcBeatMatches": [ { "to": 17, "from": 10, "beatId": "019dd95a-0682-776c-8e39-efdc0c3bfe92", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Problem & Complication", "beatSlug": "consultants-gambit-problem-complication", "evidence": "PMF reached only narrowly; 6-dim assessment exposes capability gaps", "position": 2, "confidence": 82, "parentBeatName": "Complication", "parentBeatSlug": "complication" }, { "to": 17, "from": 13, "beatId": "019dd95a-0682-776c-8e3a-022aa9a7736c", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Implications (So What)", "beatSlug": "triple-take-the-implications-so-what", "evidence": "Section 03 reliability benchmarks and BCG capability framework", "position": 2, "confidence": 55, "parentBeatName": "Reflection", "parentBeatSlug": "reflection" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 16, "slideType": "other", "function": "present_framework", "notes": "The slide presents a proprietary BCG framework for AI agent evaluation.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/16", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-16", "loopMatches": [ { "to": 17, "from": 16, "name": "Capability Gap", "slug": "48-capability-gap", "bestFor": "M&A strategy, digital transformation, organizational design", "matchId": "019dd95a-088b-72c8-b7df-fbe911d5d520", "evidence": "p16 defines 6 dimensions; p17 plots Low/Med/High maturity per dimension with limitations and what-needs-to-happen", "position": 4, "objective": "Diagnose where agents fall short across 6 capabilities", "structure": "Required Capabilities -> Current State -> The Gap -> Build vs Buy vs Partner Decision", "confidence": 78, "description": "Compare required capabilities vs. current capabilities to define the build/buy/partner decision" } ], "arcBeatMatches": [ { "to": 17, "from": 10, "beatId": "019dd95a-0682-776c-8e39-efdc0c3bfe92", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Problem & Complication", "beatSlug": "consultants-gambit-problem-complication", "evidence": "PMF reached only narrowly; 6-dim assessment exposes capability gaps", "position": 2, "confidence": 82, "parentBeatName": "Complication", "parentBeatSlug": "complication" }, { "to": 17, "from": 13, "beatId": "019dd95a-0682-776c-8e3a-022aa9a7736c", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Implications (So What)", "beatSlug": "triple-take-the-implications-so-what", "evidence": "Section 03 reliability benchmarks and BCG capability framework", "position": 2, "confidence": 55, "parentBeatName": "Reflection", "parentBeatSlug": "reflection" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 17, "slideType": "maturity_model", "function": "diagnose", "notes": "The slide uses a maturity model framework to map current AI agent capabilities against future requirements.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/17", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-17", "loopMatches": [ { "to": 17, "from": 16, "name": "Capability Gap", "slug": "48-capability-gap", "bestFor": "M&A strategy, digital transformation, organizational design", "matchId": "019dd95a-088b-72c8-b7df-fbe911d5d520", "evidence": "p16 defines 6 dimensions; p17 plots Low/Med/High maturity per dimension with limitations and what-needs-to-happen", "position": 4, "objective": "Diagnose where agents fall short across 6 capabilities", "structure": "Required Capabilities -> Current State -> The Gap -> Build vs Buy vs Partner Decision", "confidence": 78, "description": "Compare required capabilities vs. current capabilities to define the build/buy/partner decision" } ], "arcBeatMatches": [ { "to": 17, "from": 10, "beatId": "019dd95a-0682-776c-8e39-efdc0c3bfe92", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Problem & Complication", "beatSlug": "consultants-gambit-problem-complication", "evidence": "PMF reached only narrowly; 6-dim assessment exposes capability gaps", "position": 2, "confidence": 82, "parentBeatName": "Complication", "parentBeatSlug": "complication" }, { "to": 17, "from": 13, "beatId": "019dd95a-0682-776c-8e3a-022aa9a7736c", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Implications (So What)", "beatSlug": "triple-take-the-implications-so-what", "evidence": "Section 03 reliability benchmarks and BCG capability framework", "position": 2, "confidence": 55, "parentBeatName": "Reflection", "parentBeatSlug": "reflection" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 18, "slideType": "section_divider", "function": "transition", "notes": null, "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/18", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-18", "loopMatches": [], "arcBeatMatches": [ { "to": 23, "from": 18, "beatId": "019dd95a-0682-776c-8e39-f35192ff20f5", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Solution & Approach", "beatSlug": "consultants-gambit-solution-approach", "evidence": "Section 04 introduces MCP and how it slots into enterprise architecture", "position": 3, "confidence": 82, "parentBeatName": "Turn", "parentBeatSlug": "turn" }, { "to": 27, "from": 18, "beatId": "019dd95a-0682-776c-8e3a-0662ddf93f56", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Action (Now What)", "beatSlug": "triple-take-the-action-now-what", "evidence": "Section 04 + key points prescribe MCP-based enterprise build", "position": 3, "confidence": 55, "parentBeatName": "Resolution", "parentBeatSlug": "resolution" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 19, "slideType": "other", "function": "present_framework", "notes": "The slide uses a layered architecture diagram to explain the MCP protocol stack.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/19", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-19", "loopMatches": [ { "to": 21, "from": 19, "name": "Zoom In", "slug": "06-zoom-in", "bestFor": "Technical deep-dives, case studies, detailed analysis", "matchId": "019dd95a-088b-72c8-b7df-fc112746e8be", "evidence": "p19 protocol primitives, p20 unified flow, p21 overlays MCP onto 4 of 6 capability gaps", "position": 5, "objective": "Zoom from MCP overview into mechanics and gap-fit", "structure": "The Big Picture -> Key Area of Focus -> Specific Detail -> Implication", "confidence": 75, "description": "Start broad, then progressively focus on specific details that prove your point" } ], "arcBeatMatches": [ { "to": 23, "from": 18, "beatId": "019dd95a-0682-776c-8e39-f35192ff20f5", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Solution & Approach", "beatSlug": "consultants-gambit-solution-approach", "evidence": "Section 04 introduces MCP and how it slots into enterprise architecture", "position": 3, "confidence": 82, "parentBeatName": "Turn", "parentBeatSlug": "turn" }, { "to": 27, "from": 18, "beatId": "019dd95a-0682-776c-8e3a-0662ddf93f56", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Action (Now What)", "beatSlug": "triple-take-the-action-now-what", "evidence": "Section 04 + key points prescribe MCP-based enterprise build", "position": 3, "confidence": 55, "parentBeatName": "Resolution", "parentBeatSlug": "resolution" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 20, "slideType": "other", "function": "present_framework", "notes": "The slide uses a process flow to explain the technical architecture of MCP.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/20", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-20", "loopMatches": [ { "to": 21, "from": 19, "name": "Zoom In", "slug": "06-zoom-in", "bestFor": "Technical deep-dives, case studies, detailed analysis", "matchId": "019dd95a-088b-72c8-b7df-fc112746e8be", "evidence": "p19 protocol primitives, p20 unified flow, p21 overlays MCP onto 4 of 6 capability gaps", "position": 5, "objective": "Zoom from MCP overview into mechanics and gap-fit", "structure": "The Big Picture -> Key Area of Focus -> Specific Detail -> Implication", "confidence": 75, "description": "Start broad, then progressively focus on specific details that prove your point" } ], "arcBeatMatches": [ { "to": 23, "from": 18, "beatId": "019dd95a-0682-776c-8e39-f35192ff20f5", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Solution & Approach", "beatSlug": "consultants-gambit-solution-approach", "evidence": "Section 04 introduces MCP and how it slots into enterprise architecture", "position": 3, "confidence": 82, "parentBeatName": "Turn", "parentBeatSlug": "turn" }, { "to": 27, "from": 18, "beatId": "019dd95a-0682-776c-8e3a-0662ddf93f56", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Action (Now What)", "beatSlug": "triple-take-the-action-now-what", "evidence": "Section 04 + key points prescribe MCP-based enterprise build", "position": 3, "confidence": 55, "parentBeatName": "Resolution", "parentBeatSlug": "resolution" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 21, "slideType": "diagnosis", "function": "diagnose", "notes": "The slide uses a numbered list format to map MCP's role against six identified agent capability gaps.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/21", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-21", "loopMatches": [ { "to": 21, "from": 19, "name": "Zoom In", "slug": "06-zoom-in", "bestFor": "Technical deep-dives, case studies, detailed analysis", "matchId": "019dd95a-088b-72c8-b7df-fc112746e8be", "evidence": "p19 protocol primitives, p20 unified flow, p21 overlays MCP onto 4 of 6 capability gaps", "position": 5, "objective": "Zoom from MCP overview into mechanics and gap-fit", "structure": "The Big Picture -> Key Area of Focus -> Specific Detail -> Implication", "confidence": 75, "description": "Start broad, then progressively focus on specific details that prove your point" } ], "arcBeatMatches": [ { "to": 23, "from": 18, "beatId": "019dd95a-0682-776c-8e39-f35192ff20f5", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Solution & Approach", "beatSlug": "consultants-gambit-solution-approach", "evidence": "Section 04 introduces MCP and how it slots into enterprise architecture", "position": 3, "confidence": 82, "parentBeatName": "Turn", "parentBeatSlug": "turn" }, { "to": 27, "from": 18, "beatId": "019dd95a-0682-776c-8e3a-0662ddf93f56", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Action (Now What)", "beatSlug": "triple-take-the-action-now-what", "evidence": "Section 04 + key points prescribe MCP-based enterprise build", "position": 3, "confidence": 55, "parentBeatName": "Resolution", "parentBeatSlug": "resolution" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 22, "slideType": "industry_trends", "function": "summarize", "notes": "The chart uses a line graph to compare Github stars over time for various AI frameworks, highlighting MCP's steep growth trajectory.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/22", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-22", "loopMatches": [ { "to": 23, "from": 22, "name": "Why Now", "slug": "15-why-now", "bestFor": "Sales pitches, fundraising, requesting immediate budget approval", "matchId": "019dd95a-088b-72c8-b7e0-0004a5637af7", "evidence": "p22 'de facto standard' momentum callout; p23 'how to think about MCP in your architecture'", "position": 6, "objective": "Justify why MCP adoption window is open now", "structure": "The Context (Trends) -> The Trigger Event -> The Window of Opportunity", "confidence": 65, "description": "Create temporal urgency by proving that the window of opportunity is opening or closing" } ], "arcBeatMatches": [ { "to": 23, "from": 18, "beatId": "019dd95a-0682-776c-8e39-f35192ff20f5", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Solution & Approach", "beatSlug": "consultants-gambit-solution-approach", "evidence": "Section 04 introduces MCP and how it slots into enterprise architecture", "position": 3, "confidence": 82, "parentBeatName": "Turn", "parentBeatSlug": "turn" }, { "to": 27, "from": 18, "beatId": "019dd95a-0682-776c-8e3a-0662ddf93f56", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Action (Now What)", "beatSlug": "triple-take-the-action-now-what", "evidence": "Section 04 + key points prescribe MCP-based enterprise build", "position": 3, "confidence": 55, "parentBeatName": "Resolution", "parentBeatSlug": "resolution" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 23, "slideType": "diagnosis", "function": "diagnose", "notes": "The slide uses a before-and-after framing to illustrate the architectural benefit of Model Context Protocol (MCP).", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/23", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-23", "loopMatches": [ { "to": 23, "from": 22, "name": "Why Now", "slug": "15-why-now", "bestFor": "Sales pitches, fundraising, requesting immediate budget approval", "matchId": "019dd95a-088b-72c8-b7e0-0004a5637af7", "evidence": "p22 'de facto standard' momentum callout; p23 'how to think about MCP in your architecture'", "position": 6, "objective": "Justify why MCP adoption window is open now", "structure": "The Context (Trends) -> The Trigger Event -> The Window of Opportunity", "confidence": 65, "description": "Create temporal urgency by proving that the window of opportunity is opening or closing" } ], "arcBeatMatches": [ { "to": 23, "from": 18, "beatId": "019dd95a-0682-776c-8e39-f35192ff20f5", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Solution & Approach", "beatSlug": "consultants-gambit-solution-approach", "evidence": "Section 04 introduces MCP and how it slots into enterprise architecture", "position": 3, "confidence": 82, "parentBeatName": "Turn", "parentBeatSlug": "turn" }, { "to": 27, "from": 18, "beatId": "019dd95a-0682-776c-8e3a-0662ddf93f56", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Action (Now What)", "beatSlug": "triple-take-the-action-now-what", "evidence": "Section 04 + key points prescribe MCP-based enterprise build", "position": 3, "confidence": 55, "parentBeatName": "Resolution", "parentBeatSlug": "resolution" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 24, "slideType": "risk_register", "function": "diagnose", "notes": "The slide uses a numbered list to map specific risks to a system architecture diagram.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/24", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-24", "loopMatches": [ { "to": 26, "from": 24, "name": "Pre Mortem", "slug": "19-pre-mortem", "bestFor": "Project kick-offs, risk management, building trust with skeptical stakeholders", "matchId": "019dd95a-088b-72c8-b7e0-041d413f6f30", "evidence": "p24 security risks, p25 A2A protocol fragmentation warning, p26 future architecture mitigation", "position": 7, "objective": "Surface failure modes and target-state guardrails", "structure": "The Future Disaster (Hypothetical) -> What Went Wrong -> The Prevention Plan", "confidence": 62, "description": "Build trust by anticipating failure modes before they happen and solving them in advance" } ], "arcBeatMatches": [ { "to": 26, "from": 24, "beatId": "019dd95a-0682-776c-8e39-f422f49a28f7", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Evidence & Proof", "beatSlug": "consultants-gambit-evidence-proof", "evidence": "Security treatment, A2A coexistence, target-state platform diagram", "position": 4, "confidence": 82, "parentBeatName": "Evidence", "parentBeatSlug": "evidence" }, { "to": 27, "from": 18, "beatId": "019dd95a-0682-776c-8e3a-0662ddf93f56", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Action (Now What)", "beatSlug": "triple-take-the-action-now-what", "evidence": "Section 04 + key points prescribe MCP-based enterprise build", "position": 3, "confidence": 55, "parentBeatName": "Resolution", "parentBeatSlug": "resolution" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 25, "slideType": "industry_trends", "function": "establish_context", "notes": "The slide uses a layered architecture diagram to show the relationship between agents, A2A, and MCP servers.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/25", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-25", "loopMatches": [ { "to": 26, "from": 24, "name": "Pre Mortem", "slug": "19-pre-mortem", "bestFor": "Project kick-offs, risk management, building trust with skeptical stakeholders", "matchId": "019dd95a-088b-72c8-b7e0-041d413f6f30", "evidence": "p24 security risks, p25 A2A protocol fragmentation warning, p26 future architecture mitigation", "position": 7, "objective": "Surface failure modes and target-state guardrails", "structure": "The Future Disaster (Hypothetical) -> What Went Wrong -> The Prevention Plan", "confidence": 62, "description": "Build trust by anticipating failure modes before they happen and solving them in advance" } ], "arcBeatMatches": [ { "to": 26, "from": 24, "beatId": "019dd95a-0682-776c-8e39-f422f49a28f7", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Evidence & Proof", "beatSlug": "consultants-gambit-evidence-proof", "evidence": "Security treatment, A2A coexistence, target-state platform diagram", "position": 4, "confidence": 82, "parentBeatName": "Evidence", "parentBeatSlug": "evidence" }, { "to": 27, "from": 18, "beatId": "019dd95a-0682-776c-8e3a-0662ddf93f56", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Action (Now What)", "beatSlug": "triple-take-the-action-now-what", "evidence": "Section 04 + key points prescribe MCP-based enterprise build", "position": 3, "confidence": 55, "parentBeatName": "Resolution", "parentBeatSlug": "resolution" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 26, "slideType": "market_landscape", "function": "present_framework", "notes": "The slide uses a layered architecture diagram to illustrate the relationship between Agent Apps, the AI Platform, and LLM Providers.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/26", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-26", "loopMatches": [ { "to": 26, "from": 24, "name": "Pre Mortem", "slug": "19-pre-mortem", "bestFor": "Project kick-offs, risk management, building trust with skeptical stakeholders", "matchId": "019dd95a-088b-72c8-b7e0-041d413f6f30", "evidence": "p24 security risks, p25 A2A protocol fragmentation warning, p26 future architecture mitigation", "position": 7, "objective": "Surface failure modes and target-state guardrails", "structure": "The Future Disaster (Hypothetical) -> What Went Wrong -> The Prevention Plan", "confidence": 62, "description": "Build trust by anticipating failure modes before they happen and solving them in advance" } ], "arcBeatMatches": [ { "to": 26, "from": 24, "beatId": "019dd95a-0682-776c-8e39-f422f49a28f7", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Evidence & Proof", "beatSlug": "consultants-gambit-evidence-proof", "evidence": "Security treatment, A2A coexistence, target-state platform diagram", "position": 4, "confidence": 82, "parentBeatName": "Evidence", "parentBeatSlug": "evidence" }, { "to": 27, "from": 18, "beatId": "019dd95a-0682-776c-8e3a-0662ddf93f56", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Action (Now What)", "beatSlug": "triple-take-the-action-now-what", "evidence": "Section 04 + key points prescribe MCP-based enterprise build", "position": 3, "confidence": 55, "parentBeatName": "Resolution", "parentBeatSlug": "resolution" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 27, "slideType": "initiative_list", "function": "present_solution", "notes": "The slide uses a visual equation (Agents + MCP) and lists five key implementation steps, concluding with a reference to the appendix.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/27", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-27", "loopMatches": [ { "to": 27, "from": 27, "name": "So What Cascade", "slug": "41-so-what-cascade", "bestFor": "Data presentations, executive summaries, driving to recommendations", "matchId": "019dd95a-088b-72c8-b7e0-081a7cfc3d57", "evidence": "Numbered 1-5 actions: evals, MCP plan, orchestration platform, legal review, technical appendix", "position": 8, "objective": "Cascade analysis into 5 enterprise recommendations", "structure": "The Data -> So What? (Insight 1) -> So What? (Insight 2) -> So What? (The Action)", "confidence": 75, "description": "Chain insights together, each answering 'so what?' until you reach the actionable conclusion" } ], "arcBeatMatches": [ { "to": 29, "from": 27, "beatId": "019dd95a-0682-776c-8e39-f846edbd06d7", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Impact & Next Steps", "beatSlug": "consultants-gambit-impact-next-steps", "evidence": "Five numbered enterprise recommendations and team contact page", "position": 5, "confidence": 82, "parentBeatName": "Resolution", "parentBeatSlug": "resolution" }, { "to": 27, "from": 18, "beatId": "019dd95a-0682-776c-8e3a-0662ddf93f56", "arcName": "The Triple Take", "arcSlug": "triple-take", "beatName": "The Action (Now What)", "beatSlug": "triple-take-the-action-now-what", "evidence": "Section 04 + key points prescribe MCP-based enterprise build", "position": 3, "confidence": 55, "parentBeatName": "Resolution", "parentBeatSlug": "resolution" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 28, "slideType": "appendix", "function": "other", "notes": null, "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/28", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-28", "loopMatches": [], "arcBeatMatches": [ { "to": 29, "from": 27, "beatId": "019dd95a-0682-776c-8e39-f846edbd06d7", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Impact & Next Steps", "beatSlug": "consultants-gambit-impact-next-steps", "evidence": "Five numbered enterprise recommendations and team contact page", "position": 5, "confidence": 82, "parentBeatName": "Resolution", "parentBeatSlug": "resolution" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 29, "slideType": "team_bio", "function": "other", "notes": "Includes a list of co-authors and a footer showing the AI Platforms Group.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/29", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-29", "loopMatches": [], "arcBeatMatches": [ { "to": 29, "from": 27, "beatId": "019dd95a-0682-776c-8e39-f846edbd06d7", "arcName": "The Consultant's Gambit", "arcSlug": "consultants-gambit", "beatName": "Impact & Next Steps", "beatSlug": "consultants-gambit-impact-next-steps", "evidence": "Five numbered enterprise recommendations and team contact page", "position": 5, "confidence": 82, "parentBeatName": "Resolution", "parentBeatSlug": "resolution" } ], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 30, "slideType": "appendix", "function": "appendix", "notes": null, "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/30", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-30", "loopMatches": [], "arcBeatMatches": [], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 31, "slideType": "key_messages", "function": "summarize", "notes": "The slide uses a three-column layout to explain the accessibility and ecosystem of the Model Context Protocol.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/31", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-31", "loopMatches": [], "arcBeatMatches": [], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 32, "slideType": "market_landscape", "function": "present_solution", "notes": "The slide uses a grid layout to categorize MCP servers into four columns: Enterprise software, Desktop automation, Productivity tools, and Software Dev/Ops tools. A legend at the bottom defines the origin of the servers (Opensource, Vendor, Community).", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/32", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-32", "loopMatches": [], "arcBeatMatches": [], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 33, "slideType": "initiative_list", "function": "present_framework", "notes": "The diagram illustrates the interaction between Application Front-end, MCP Client, LLM, and MCP Servers/Systems, with numbered callouts corresponding to the list items.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/33", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-33", "loopMatches": [ { "to": 35, "from": 33, "name": "Paradox Resolver", "slug": "20-paradox-resolver", "bestFor": "Strategic pivots, innovation pitches, challenging conventional wisdom", "matchId": "019dd95a-088b-72c8-b7e0-0f0030d8184b", "evidence": "p33 best-practices framing, p34 contrasts both extremes, p35 prescribes 'lean MCP servers' middle path", "position": 9, "objective": "Reconcile monolith vs microservice MCP extremes", "structure": "The Apparent Contradiction -> Why Both Seem True -> The Deeper Truth That Reconciles", "confidence": 70, "description": "Introduce a seeming contradiction that captures attention, then resolve it with a deeper truth" } ], "arcBeatMatches": [], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true }, { "docId": "019dd923-5e88-73ef-bd5d-47815abb602b", "docSlug": "485b1e996a637b43", "documentTitle": "2025 AI Agents and the Model Context Protocol", "authorId": "BCG", "authorName": "BCG", "documentKindSlug": "consulting-deck", "documentKindLabel": "Consulting deck", "sourceTypeSlug": "strategy_consulting", "sourceTypeLabel": "Strategy consulting", "presentationDate": null, "orientation": "landscape", "aspectRatio": 1.778, "pageNumber": 34, "slideType": "comparison_table", "function": "compare_options", "notes": "The slide uses a visual comparison to illustrate architectural anti-patterns for MCP (Model Context Protocol) servers.", "imagePath": null, "matchCount": 1, "evidence": null, "slideHref": "/slides/019dd923-5e88-73ef-bd5d-47815abb602b/34", "deckHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b", "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-47815abb602b#slide-34", "loopMatches": [ { "to": 35, "from": 33, "name": "Paradox Resolver", "slug": "20-paradox-resolver", "bestFor": "Strategic pivots, innovation pitches, challenging conventional wisdom", "matchId": "019dd95a-088b-72c8-b7e0-0f0030d8184b", "evidence": "p33 best-practices framing, p34 contrasts both extremes, p35 prescribes 'lean MCP servers' middle path", "position": 9, "objective": "Reconcile monolith vs microservice MCP extremes", "structure": "The Apparent Contradiction -> Why Both Seem True -> The Deeper Truth That Reconciles", "confidence": 70, "description": "Introduce a seeming contradiction that captures attention, then resolve it with a deeper truth" } ], "arcBeatMatches": [], "imagePathAlt": null, "thumbSrc": null, "thumbSrcAlt": null, "locked": true } ] }