{
  "apiVersion": "v1",
  "topic": {
    "id": "context-for-agents",
    "title": "How do organizations give agents the knowledge they need?",
    "group": "Tools, models and knowledge",
    "summary": "Context files, skills, rules, internal knowledge graphs and tool connections that tell agents how the organization works.",
    "passages": 36,
    "url": "https://the-ai-record.com/topics/context-for-agents",
    "json": "https://the-ai-record.com/api/v1/topics/context-for-agents.json"
  },
  "passages": [
    {
      "id": "uber-engineers-built-over-3-600-agent-skills-2026",
      "text": "Engineers have built over 3,600 agent skills across the software development life cycle, and executed more than 30K agent skill executions per day.",
      "context": null,
      "speaker": "Uday Kiran Medisetty",
      "speakerId": "uday-kiran-medisetty",
      "speakerUrl": "https://the-ai-record.com/people/uday-kiran-medisetty",
      "speakerLevel": "practitioner",
      "role": "Distinguished Engineer",
      "voice": "person",
      "organization": "Uber",
      "organizationId": "uber",
      "organizationUrl": "https://the-ai-record.com/organizations/uber",
      "aiVendor": false,
      "work": {
        "title": "Running a Software Factory Efficiently at Uber Scale",
        "type": "post",
        "date": "2026-08-27",
        "publisher": "Uber engineering blog",
        "url": "https://www.uber.com/us/en/blog/efficient-software-factory/"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "training-and-skills",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/uber-engineers-built-over-3-600-agent-skills-2026",
      "json": "https://the-ai-record.com/api/v1/passages/uber-engineers-built-over-3-600-agent-skills-2026.json"
    },
    {
      "id": "uber-context-graph-150-node-edge-types-40-million-entries-2026",
      "text": "So we have one context graph, we took all of the information of how Uber runs into one context graph, this has 150 unique node and edge types, we have 40 million entries there right now, it captures all the way from how our mobile apps are built, to our backend, to our … all the design docs, Jira, incident bugs, everything is connected.",
      "context": "Medisetty is describing the single store of company context that Uber's agents read.",
      "speaker": "Uday Kiran Medisetty",
      "speakerId": "uday-kiran-medisetty",
      "speakerUrl": "https://the-ai-record.com/people/uday-kiran-medisetty",
      "speakerLevel": "practitioner",
      "role": "Distinguished Engineer, Uber",
      "voice": "person",
      "organization": "Uber",
      "organizationId": "uber",
      "organizationUrl": "https://the-ai-record.com/organizations/uber",
      "aiVendor": false,
      "work": {
        "title": "Agentic SDLC at Uber: Building Blocks for Uber's Software Factory",
        "type": "talk",
        "date": "2026-08-21",
        "publisher": "AI Engineer (YouTube)",
        "locator": "09:15",
        "url": "https://www.youtube.com/watch?v=17-YSUHo6Lk"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-03"
      },
      "topics": [
        "internal-tools",
        "context-for-agents"
      ],
      "functions": [
        "engineering",
        "company-wide"
      ],
      "figures": [
        {
          "metric": "context-graph-entries",
          "value": 40000000,
          "unit": "entries",
          "period": "at the time of the talk, 2026",
          "definition": "Entries in Uber's context graph",
          "level": "n/a"
        },
        {
          "metric": "context-graph-node-edge-types",
          "value": 150,
          "unit": "node and edge types",
          "period": "at the time of the talk, 2026",
          "definition": "Unique node and edge types in Uber's context graph",
          "level": "n/a"
        }
      ],
      "url": "https://the-ai-record.com/passages/uber-context-graph-150-node-edge-types-40-million-entries-2026",
      "json": "https://the-ai-record.com/api/v1/passages/uber-context-graph-150-node-edge-types-40-million-entries-2026.json"
    },
    {
      "id": "uber-managed-skills-marketplace-2500-skills-automated-reviews-2026",
      "text": "So what we built entire lifecycle around skills, so we have core skills and domain-specific skills, all of that go into a managed skills marketplace. We have 2,500 skills there right now, and it goes through a whole bunch of … automated reviews, which ensures a baseline skill quality for any skills that we have.",
      "context": "Medisetty is describing how Uber manages the agent skills its engineers build.",
      "speaker": "Uday Kiran Medisetty",
      "speakerId": "uday-kiran-medisetty",
      "speakerUrl": "https://the-ai-record.com/people/uday-kiran-medisetty",
      "speakerLevel": "practitioner",
      "role": "Distinguished Engineer, Uber",
      "voice": "person",
      "organization": "Uber",
      "organizationId": "uber",
      "organizationUrl": "https://the-ai-record.com/organizations/uber",
      "aiVendor": false,
      "work": {
        "title": "Agentic SDLC at Uber: Building Blocks for Uber's Software Factory",
        "type": "talk",
        "date": "2026-08-21",
        "publisher": "AI Engineer (YouTube)",
        "locator": "07:35",
        "url": "https://www.youtube.com/watch?v=17-YSUHo6Lk"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-03"
      },
      "topics": [
        "internal-tools",
        "autonomy-and-oversight",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [
        {
          "metric": "skills-in-marketplace",
          "value": 2500,
          "unit": "skills",
          "period": "at the time of the talk, 2026",
          "definition": "Skills in Uber's managed skills marketplace",
          "level": "n/a"
        }
      ],
      "url": "https://the-ai-record.com/passages/uber-managed-skills-marketplace-2500-skills-automated-reviews-2026",
      "json": "https://the-ai-record.com/api/v1/passages/uber-managed-skills-marketplace-2500-skills-automated-reviews-2026.json"
    },
    {
      "id": "boundary-architecture-md-small-stable-layers-compiler-2026",
      "text": "We built an architecture.md file. Instead of using … MD, just pick something that every model can just understand. This file has to be incredibly small, and it can only have things that will not change for months or for years. In our case, it's the layers of the compiler. … So now we have standards so anyone can use whatever they want.",
      "context": "Gupta is describing how the team sets shared standards when engineers choose their own AI tools.",
      "speaker": "Vaibhav Gupta",
      "speakerId": "vaibhav-gupta",
      "speakerUrl": "https://the-ai-record.com/people/vaibhav-gupta",
      "speakerLevel": "executive",
      "role": "Co-founder and Chief Executive",
      "voice": "person",
      "organization": "Boundary (BoundaryML)",
      "organizationId": "boundary",
      "organizationUrl": "https://the-ai-record.com/organizations/boundary",
      "aiVendor": true,
      "work": {
        "title": "Fighting Slop with Slop",
        "type": "talk",
        "date": "2026-07-31",
        "publisher": "AI Engineer (YouTube)",
        "locator": "2:10",
        "url": "https://www.youtube.com/watch?v=AMiyLItEtLA"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-01"
      },
      "topics": [
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/boundary-architecture-md-small-stable-layers-compiler-2026",
      "json": "https://the-ai-record.com/api/v1/passages/boundary-architecture-md-small-stable-layers-compiler-2026.json"
    },
    {
      "id": "block-machine-readable-view-every-service-orchestrators-2026",
      "text": "So we built a company world … based on the entirety of our 25,000 repo …, right? And this was a machine readable view of every single service and how they all connect. And this allowed orchestrators and the agents that they delegated to to pull context in as needed and understand the landscape as they implement. And this enabled multiple agents to explore different parts of the system in parallel.",
      "context": "Jones is describing the shared view of Block's code that its agent orchestrator draws on.",
      "speaker": "Angie Jones",
      "speakerId": "angie-jones",
      "speakerUrl": "https://the-ai-record.com/people/angie-jones",
      "speakerLevel": "leader",
      "role": "Led AI enablement and the agent engineering org at Block, as she describes in the talk; now VP of Developer Experience, Agentic AI Foundation",
      "voice": "person",
      "organization": "Block",
      "organizationId": "block",
      "organizationUrl": "https://the-ai-record.com/organizations/block",
      "aiVendor": false,
      "work": {
        "title": "Building an Autonomous Engineering Org",
        "type": "talk",
        "date": "2026-06-28",
        "publisher": "AI Engineer (YouTube)",
        "locator": "15:23",
        "url": "https://www.youtube.com/watch?v=whue9_YquGA"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-04"
      },
      "topics": [
        "internal-tools",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [
        {
          "metric": "code-base-size",
          "value": 25000,
          "unit": "repos",
          "period": "as the speaker states it",
          "definition": "'25,000 repo' followed by a word the two whisper passes disagree on and that is cut from the quote; read as repositories in Block's code base",
          "level": "n/a"
        }
      ],
      "url": "https://the-ai-record.com/passages/block-machine-readable-view-every-service-orchestrators-2026",
      "json": "https://the-ai-record.com/api/v1/passages/block-machine-readable-view-every-service-orchestrators-2026.json"
    },
    {
      "id": "cloudflare-code-tells-model-what-front-guessing-2026",
      "text": "the code tells the model what's in front of it, but it does not tell the model who owns the service, what the dependencies are, … what databases are being talked to, what conventions are that the teams considers non-negotiable … they reduce the amount of guessing the models have to do. And one thing we learned the hard way is that even with the decent context file, it is better than having none. And when the model stops guessing, the quality goes up everywhere else.",
      "context": "Explaining why Cloudflare invested in Backstage, its internal developer portal, and AGENTS.md files as context for coding agents.",
      "speaker": "Rajesh Bhatia",
      "speakerId": "rajesh-bhatia",
      "speakerUrl": "https://the-ai-record.com/people/rajesh-bhatia",
      "speakerLevel": "leader",
      "role": "Senior Director of Engineering, Cloudflare",
      "voice": "person",
      "organization": "Cloudflare",
      "organizationId": "cloudflare",
      "organizationUrl": "https://the-ai-record.com/organizations/cloudflare",
      "aiVendor": true,
      "work": {
        "title": "From Assisted to Delegated: Cloudflare's AI Engineering Stack (interview, Background Agents Summit 2026)",
        "type": "talk",
        "date": "2026-05-06",
        "publisher": "Ona (YouTube)",
        "locator": "16:24",
        "url": "https://www.youtube.com/watch?v=MbLdrAZFQRs"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-03"
      },
      "topics": [
        "internal-tools",
        "coding-agents",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/cloudflare-code-tells-model-what-front-guessing-2026",
      "json": "https://the-ai-record.com/api/v1/passages/cloudflare-code-tells-model-what-front-guessing-2026.json"
    },
    {
      "id": "block-remote-first-machine-readable-decisions-code-designs-2026",
      "text": "First, because we are remote-first, decisions, code, designs, and progress are recorded and machine readable, giving AI a useful operating model to learn from and act on.",
      "context": null,
      "speaker": null,
      "speakerId": null,
      "speakerUrl": null,
      "speakerLevel": null,
      "role": null,
      "voice": "organization",
      "organization": "Block",
      "organizationId": "block",
      "organizationUrl": "https://the-ai-record.com/organizations/block",
      "aiVendor": false,
      "work": {
        "title": "Block, Inc. Q1 2026 Shareholder Letter (Form 8-K, Exhibit 99.1)",
        "type": "filing",
        "date": "2026-05-07",
        "publisher": "SEC EDGAR",
        "locator": "To Our Shareholders",
        "url": "https://www.sec.gov/Archives/edgar/data/1512673/000119312526212032/d132441dex991.htm"
      },
      "grade": "A",
      "gradeMeaning": "A filing or earnings call the organization answers for.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-04"
      },
      "topics": [
        "ai-across-the-company",
        "context-for-agents"
      ],
      "functions": [
        "company-wide"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/block-remote-first-machine-readable-decisions-code-designs-2026",
      "json": "https://the-ai-record.com/api/v1/passages/block-remote-first-machine-readable-decisions-code-designs-2026.json"
    },
    {
      "id": "coatue-agents-should-see-what-humans-see-via-api-2026",
      "text": "Very simple philosophy. We use our screens. We look at stuff. We do work. Every single thing that a human can see in pixels on the screen, an agent in your building should be able to see via API. The analogy I use is imagine you brought the smartest people ever, the greatest investors alive, and you brought them into your company, but you gave them a computer without logins to 75% of your services. It's almost immaterial how smart … system is if it doesn't have the tools to actually action that.",
      "context": "Long is describing the inputs an agent needs to do investing work, the first part of his framework.",
      "speaker": "Frank Long",
      "speakerId": "frank-long",
      "speakerUrl": "https://the-ai-record.com/people/frank-long",
      "speakerLevel": "practitioner",
      "role": "Works at Coatue",
      "voice": "person",
      "organization": "Coatue",
      "organizationId": "coatue",
      "organizationUrl": "https://the-ai-record.com/organizations/coatue",
      "aiVendor": false,
      "work": {
        "title": "AI Agents Will Upend Investing Even More Than Coding - Frank Long, Coatue",
        "type": "talk",
        "date": "2026-11-06",
        "publisher": "AI Engineer (YouTube)",
        "locator": "01:36",
        "url": "https://www.youtube.com/watch?v=AYFcmnQrZCg"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-06"
      },
      "topics": [
        "context-for-agents",
        "agent-permissions"
      ],
      "functions": [
        "company-wide"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/coatue-agents-should-see-what-humans-see-via-api-2026",
      "json": "https://the-ai-record.com/api/v1/passages/coatue-agents-should-see-what-humans-see-via-api-2026.json"
    },
    {
      "id": "coatue-decades-of-filed-notes-poised-us-for-ai-2026",
      "text": "And just as importantly, we have a culture that is super, super rigorous and built from the ground up to capture all this insight. For decades, we filed every single note about every single trade, about every … decision we made or didn't make, about what went well and what didn't go well. And that's poised us to expose us to AI.",
      "context": "Long is describing the firm's internal context, the records an AI system can draw on.",
      "speaker": "Frank Long",
      "speakerId": "frank-long",
      "speakerUrl": "https://the-ai-record.com/people/frank-long",
      "speakerLevel": "practitioner",
      "role": "Works at Coatue",
      "voice": "person",
      "organization": "Coatue",
      "organizationId": "coatue",
      "organizationUrl": "https://the-ai-record.com/organizations/coatue",
      "aiVendor": false,
      "work": {
        "title": "AI Agents Will Upend Investing Even More Than Coding - Frank Long, Coatue",
        "type": "talk",
        "date": "2026-11-06",
        "publisher": "AI Engineer (YouTube)",
        "locator": "03:00",
        "url": "https://www.youtube.com/watch?v=AYFcmnQrZCg"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-06"
      },
      "topics": [
        "ai-across-the-company",
        "context-for-agents"
      ],
      "functions": [
        "company-wide"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/coatue-decades-of-filed-notes-poised-us-for-ai-2026",
      "json": "https://the-ai-record.com/api/v1/passages/coatue-decades-of-filed-notes-poised-us-for-ai-2026.json"
    },
    {
      "id": "ramp-laminar-adopts-concept-deferred-tools-most-2026",
      "text": "Laminar adopts the concept of deferred tools: most of the tools are hidden behind a tool with a way for product teams to choose which tools they don’t want to defer.",
      "context": null,
      "speaker": "Sam Kronick",
      "speakerId": "sam-kronick",
      "speakerUrl": "https://the-ai-record.com/people/sam-kronick",
      "speakerLevel": "practitioner",
      "role": "Author of Ramp's \"Building Laminar\" engineering blog post",
      "voice": "person",
      "organization": "Ramp",
      "organizationId": "ramp",
      "organizationUrl": "https://the-ai-record.com/organizations/ramp",
      "aiVendor": false,
      "work": {
        "title": "Building Laminar: Ramp's Managed Agents Platform",
        "type": "post",
        "date": "2026-10-20",
        "publisher": "Ramp Builders blog",
        "url": "https://builders.ramp.com/post/building-laminar"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-07"
      },
      "topics": [
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/ramp-laminar-adopts-concept-deferred-tools-most-2026",
      "json": "https://the-ai-record.com/api/v1/passages/ramp-laminar-adopts-concept-deferred-tools-most-2026.json"
    },
    {
      "id": "ramp-skills-help-establish-more-consistent-baseline-2026",
      "text": "We’ve found that skills help to establish a more consistent baseline of performance for how well agents use tools.",
      "context": null,
      "speaker": "Sam Kronick",
      "speakerId": "sam-kronick",
      "speakerUrl": "https://the-ai-record.com/people/sam-kronick",
      "speakerLevel": "practitioner",
      "role": "Author of Ramp's \"Building Laminar\" engineering blog post",
      "voice": "person",
      "organization": "Ramp",
      "organizationId": "ramp",
      "organizationUrl": "https://the-ai-record.com/organizations/ramp",
      "aiVendor": false,
      "work": {
        "title": "Building Laminar: Ramp's Managed Agents Platform",
        "type": "post",
        "date": "2026-10-20",
        "publisher": "Ramp Builders blog",
        "url": "https://builders.ramp.com/post/building-laminar"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-07"
      },
      "topics": [
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/ramp-skills-help-establish-more-consistent-baseline-2026",
      "json": "https://the-ai-record.com/api/v1/passages/ramp-skills-help-establish-more-consistent-baseline-2026.json"
    },
    {
      "id": "stripe-organized-knowledge-reusable-procedures-model-specific-2026",
      "text": "We organized this knowledge into reusable procedures for the platform and model-specific documentation that an agent loads for the task at hand.",
      "context": null,
      "speaker": null,
      "speakerId": null,
      "speakerUrl": null,
      "speakerLevel": null,
      "role": null,
      "voice": "organization",
      "organization": "Stripe",
      "organizationId": "stripe",
      "organizationUrl": "https://the-ai-record.com/organizations/stripe",
      "aiVendor": false,
      "work": {
        "title": "Scaling Radar: Fighting fraud with agent-assisted machine learning",
        "type": "post",
        "date": "2026-10-19",
        "publisher": "Stripe developer blog",
        "locator": "Giving agents the experiment lifecycle",
        "url": "https://stripe.dev/blog/scaling-radar-fighting-fraud-with-agent-assisted-machine-learning"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-08"
      },
      "topics": [
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/stripe-organized-knowledge-reusable-procedures-model-specific-2026",
      "json": "https://the-ai-record.com/api/v1/passages/stripe-organized-knowledge-reusable-procedures-model-specific-2026.json"
    },
    {
      "id": "ramp-so-far-323-employees-pms-cx-agents-2026",
      "text": "So far, 323 employees (PMs, CX agents, salespeople, marketers, analysts) have made 6,500+ edits to what Glass knows.",
      "context": null,
      "speaker": "Eric Glyman",
      "speakerId": "eric-glyman",
      "speakerUrl": "https://the-ai-record.com/people/eric-glyman",
      "speakerLevel": "executive",
      "role": "Co-founder and co-CEO",
      "voice": "person",
      "organization": "Ramp",
      "organizationId": "ramp",
      "organizationUrl": "https://the-ai-record.com/organizations/ramp",
      "aiVendor": false,
      "work": {
        "title": "Ramp company blog (signed by CEO Eric Glyman)",
        "type": "post",
        "date": "2026-10-13",
        "publisher": "Ramp company blog (signed by CEO Eric Glyman)",
        "url": "https://ramp.com/blog/introducing-glass"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "sales-and-marketing",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/ramp-so-far-323-employees-pms-cx-agents-2026",
      "json": "https://the-ai-record.com/api/v1/passages/ramp-so-far-323-employees-pms-cx-agents-2026.json"
    },
    {
      "id": "spacex-grok-bot-memory-core-facts-logs-scratchpad-2026",
      "text": "We tried to model some of that here where the harness has, of course, these core facts. It also has these dated logs of kind of your past conversation history centrally. And then also these kind of scratch pad notes … little things that you've been working on right now that are designed to be ephemeral, and they will go away, but they might be relevant just for the next 30 minutes or an hour.",
      "context": "Robinson has just compared the agent's memory to how a brain keeps relevant facts in mind, and is describing the three memory layers in the Grok Bot harness.",
      "speaker": "Lee Robinson",
      "speakerId": "lee-robinson",
      "speakerUrl": "https://the-ai-record.com/people/lee-robinson",
      "speakerLevel": "practitioner",
      "role": "Works on Grok Bot at SpaceX (formerly Cursor)",
      "voice": "person",
      "organization": "SpaceX (SpaceXAI)",
      "organizationId": "spacex",
      "organizationUrl": "https://the-ai-record.com/organizations/spacex",
      "aiVendor": true,
      "work": {
        "title": "Stanford CS146S: How always-on agents work",
        "type": "talk",
        "date": "2026-10-11",
        "publisher": "leerob (YouTube)",
        "locator": "33:51",
        "url": "https://www.youtube.com/watch?v=L1OBRtfPS34"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-07"
      },
      "topics": [
        "internal-tools",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/spacex-grok-bot-memory-core-facts-logs-scratchpad-2026",
      "json": "https://the-ai-record.com/api/v1/passages/spacex-grok-bot-memory-core-facts-logs-scratchpad-2026.json"
    },
    {
      "id": "atlassian-internal-benchmarks-agents-access-teamwork-graph-delivered-2026",
      "text": "In internal benchmarks, agents with access to the Teamwork Graph delivered 44% more accurate results while using 48% fewer tokens compared to agents operating without it.",
      "context": null,
      "speaker": null,
      "speakerId": null,
      "speakerUrl": null,
      "speakerLevel": null,
      "role": null,
      "voice": "organization",
      "organization": "Atlassian",
      "organizationId": "atlassian",
      "organizationUrl": "https://the-ai-record.com/organizations/atlassian",
      "aiVendor": true,
      "work": {
        "title": "Atlassian (own site)",
        "type": "post",
        "date": "2026-10-01",
        "publisher": "Atlassian (own site)",
        "url": "https://www.atlassian.com/blog/ai-at-work/ai-sdlc-transformation-playbook"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "ai-across-the-company",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/atlassian-internal-benchmarks-agents-access-teamwork-graph-delivered-2026",
      "json": "https://the-ai-record.com/api/v1/passages/atlassian-internal-benchmarks-agents-access-teamwork-graph-delivered-2026.json"
    },
    {
      "id": "stripe-vanilla-setup-required-roughly-20-days-engineering-2026",
      "text": "the vanilla setup required roughly 20 days of engineering effort, compared to 4 days when using the reusable prompts.",
      "context": null,
      "speaker": "David Dunne",
      "speakerId": "david-dunne",
      "speakerUrl": "https://the-ai-record.com/people/david-dunne",
      "speakerLevel": "practitioner",
      "role": "Software engineer, Local Payment Methods",
      "voice": "person",
      "organization": "Stripe",
      "organizationId": "stripe",
      "organizationUrl": "https://the-ai-record.com/organizations/stripe",
      "aiVendor": false,
      "work": {
        "title": "Stripe developer blog",
        "type": "post",
        "date": "2026-09-30",
        "publisher": "Stripe developer blog",
        "url": "https://stripe.dev/blog/stripes-payment-method-factory-orchestrating-agents-for-repeated-custom-integrations"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "ai-across-the-company",
        "context-for-agents",
        "developer-productivity"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/stripe-vanilla-setup-required-roughly-20-days-engineering-2026",
      "json": "https://the-ai-record.com/api/v1/passages/stripe-vanilla-setup-required-roughly-20-days-engineering-2026.json"
    },
    {
      "id": "uber-one-thing-we-learned-actually-writing-2026",
      "text": "One thing that we learned is that actually writing the skill was very easy, like teams just very quickly wrote a skill by asking Claude to write one, go over my previous PR reviews and write me a skill, but the hard part was how to run these skills at scale with consistent quality and low cost, and that required a lot of iterations, not only from the [uReview] team side, but also … for each team who was trying to write these rules.",
      "context": "Ameya Ketkar is describing how Uber's teams wrote their own code-review skills for uReview.",
      "speaker": "Ameya Ketkar",
      "speakerId": "ameya-ketkar",
      "speakerUrl": "https://the-ai-record.com/people/ameya-ketkar",
      "speakerLevel": "practitioner",
      "role": "Speaker, AI Engineer World's Fair 2026 (job title not stated)",
      "voice": "person",
      "organization": "Uber",
      "organizationId": "uber",
      "organizationUrl": "https://the-ai-record.com/organizations/uber",
      "aiVendor": false,
      "work": {
        "title": "Building uReview, Uber's Multi-Agent Code Review Engine (talk, AI Engineer World's Fair 2026)",
        "type": "talk",
        "date": "2026-08-28",
        "publisher": "AI Engineer (YouTube)",
        "locator": "09:44",
        "url": "https://www.youtube.com/watch?v=EL123UNokkI"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-03"
      },
      "topics": [
        "code-review",
        "internal-tools",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/uber-one-thing-we-learned-actually-writing-2026",
      "json": "https://the-ai-record.com/api/v1/passages/uber-one-thing-we-learned-actually-writing-2026.json"
    },
    {
      "id": "uber-single-entry-point-encompasses-more-than-1-2026",
      "text": "This single entry point encompasses more than 1,000 MCP servers across internal and third-party SaaS MCP",
      "context": null,
      "speaker": "Uday Kiran Medisetty",
      "speakerId": "uday-kiran-medisetty",
      "speakerUrl": "https://the-ai-record.com/people/uday-kiran-medisetty",
      "speakerLevel": "practitioner",
      "role": "Distinguished Engineer",
      "voice": "person",
      "organization": "Uber",
      "organizationId": "uber",
      "organizationUrl": "https://the-ai-record.com/organizations/uber",
      "aiVendor": false,
      "work": {
        "title": "Running a Software Factory Efficiently at Uber Scale",
        "type": "post",
        "date": "2026-08-27",
        "publisher": "Uber engineering blog",
        "url": "https://www.uber.com/us/en/blog/efficient-software-factory/"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/uber-single-entry-point-encompasses-more-than-1-2026",
      "json": "https://the-ai-record.com/api/v1/passages/uber-single-entry-point-encompasses-more-than-1-2026.json"
    },
    {
      "id": "uber-2500-skills-20000-skill-executions-per-day-2026",
      "text": "And we have 2,500 skills and … more than 20,000 skill executions per day across our fleet.",
      "context": "Medisetty is summarizing how much the managed skills are used.",
      "speaker": "Uday Kiran Medisetty",
      "speakerId": "uday-kiran-medisetty",
      "speakerUrl": "https://the-ai-record.com/people/uday-kiran-medisetty",
      "speakerLevel": "practitioner",
      "role": "Distinguished Engineer, Uber",
      "voice": "person",
      "organization": "Uber",
      "organizationId": "uber",
      "organizationUrl": "https://the-ai-record.com/organizations/uber",
      "aiVendor": false,
      "work": {
        "title": "Agentic SDLC at Uber: Building Blocks for Uber's Software Factory",
        "type": "talk",
        "date": "2026-08-21",
        "publisher": "AI Engineer (YouTube)",
        "locator": "08:27",
        "url": "https://www.youtube.com/watch?v=17-YSUHo6Lk"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-03"
      },
      "topics": [
        "adoption-and-usage",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [
        {
          "metric": "skill-executions-per-day",
          "value": 20000,
          "unit": "executions per day",
          "period": "at the time of the talk, 2026",
          "definition": "Agent skill executions across Uber's fleet (more than)",
          "level": "n/a"
        },
        {
          "metric": "skills-in-marketplace",
          "value": 2500,
          "unit": "skills",
          "period": "at the time of the talk, 2026",
          "definition": "Skills in Uber's managed skills marketplace",
          "level": "n/a"
        }
      ],
      "url": "https://the-ai-record.com/passages/uber-2500-skills-20000-skill-executions-per-day-2026",
      "json": "https://the-ai-record.com/api/v1/passages/uber-2500-skills-20000-skill-executions-per-day-2026.json"
    },
    {
      "id": "humanlayer-golden-patterns-by-hand-before-agent-2026",
      "text": "At HumanLayer, we like to build out what we call golden patterns by hand before setting the agent loose. These are just like idiomatic hand-written examples for the agent to follow because they're just pattern replicators and otherwise you're getting what's in the docs or what the agent knows from the internet.",
      "context": "Mistele describes how HumanLayer prepares the skill given to the agent that makes each change in its migration loop.",
      "speaker": "Kyle Mistele",
      "speakerId": "kyle-mistele",
      "speakerUrl": "https://the-ai-record.com/people/kyle-mistele",
      "speakerLevel": "executive",
      "role": "Co-founder, HumanLayer",
      "voice": "person",
      "organization": "HumanLayer",
      "organizationId": "humanlayer",
      "organizationUrl": "https://the-ai-record.com/organizations/humanlayer",
      "aiVendor": true,
      "work": {
        "title": "Loop Engineering from first principles",
        "type": "talk",
        "date": "2026-07-25",
        "publisher": "AI Engineer (YouTube)",
        "locator": "12:47",
        "url": "https://www.youtube.com/watch?v=xIt_mTQp6mY"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-03"
      },
      "topics": [
        "coding-agents",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/humanlayer-golden-patterns-by-hand-before-agent-2026",
      "json": "https://the-ai-record.com/api/v1/passages/humanlayer-golden-patterns-by-hand-before-agent-2026.json"
    },
    {
      "id": "keycard-notion-as-markdown-files-easier-for-agent-than-mcp-2026",
      "text": "I was playing with Notion and we used Notion a lot at Keycard, but I really just wanted all my Notion things available to me as Markdown files. And because … just made it easier for the agent to work with it instead of going through MCP",
      "context": "Livingstone is answering the moderator's question about how to control access to a memory store shared by many agents.",
      "speaker": "Ian Livingstone",
      "speakerId": "ian-livingstone",
      "speakerUrl": "https://the-ai-record.com/people/ian-livingstone",
      "speakerLevel": "executive",
      "role": "CEO and co-founder, Keycard",
      "voice": "person",
      "organization": "Keycard",
      "organizationId": "keycard",
      "organizationUrl": "https://the-ai-record.com/organizations/keycard",
      "aiVendor": true,
      "work": {
        "title": "The Great Loops Debate",
        "type": "talk",
        "date": "2026-07-17",
        "publisher": "AI Engineer (YouTube)",
        "locator": "40:42",
        "url": "https://www.youtube.com/watch?v=c35YoMdnI78"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-04"
      },
      "topics": [
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/keycard-notion-as-markdown-files-easier-for-agent-than-mcp-2026",
      "json": "https://the-ai-record.com/api/v1/passages/keycard-notion-as-markdown-files-easier-for-agent-than-mcp-2026.json"
    },
    {
      "id": "latent-patterns-run-model-without-skills-or-markdown-new-release-2026",
      "text": "Something I've done for a long time, and it's very silly, is I run a model … without any skills or any markdown. … actually, I get rid of all my skills and all my markdown and everything when the new model is released.",
      "context": "Huntley is answering the moderator's question on how he keeps a model from cheating when verifying its own work.",
      "speaker": "Geoffrey Huntley",
      "speakerId": "geoffrey-huntley",
      "speakerUrl": "https://the-ai-record.com/people/geoffrey-huntley",
      "speakerLevel": "practitioner",
      "role": "Creator of the Ralph loop; Latent Patterns",
      "voice": "person",
      "organization": "Latent Patterns",
      "organizationId": "latent-patterns",
      "organizationUrl": "https://the-ai-record.com/organizations/latent-patterns",
      "aiVendor": true,
      "work": {
        "title": "The Great Loops Debate",
        "type": "talk",
        "date": "2026-07-17",
        "publisher": "AI Engineer (YouTube)",
        "locator": "32:35",
        "url": "https://www.youtube.com/watch?v=c35YoMdnI78"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-04"
      },
      "topics": [
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/latent-patterns-run-model-without-skills-or-markdown-new-release-2026",
      "json": "https://the-ai-record.com/api/v1/passages/latent-patterns-run-model-without-skills-or-markdown-new-release-2026.json"
    },
    {
      "id": "nordic-corporate-bank-agent-wont-start-without-acceptance-criteria-2026",
      "text": "So then we thought, why don't we just remove ourselves from that first stage? And … do that work instead. So we did. And we gave him some instructions on how an Epic should be specified. It needs to have a description. It needs to have some acceptance criteria. … needs to have some certain level of confidence on how to implement it. And if … doesn't have that, he won't start. Then he will just ask a question back to the product owner, … him or her, and try to figure out the stuff he needs to be able to continue.",
      "context": "The speaker describes the rule the bank's agent follows before it starts work on a product owner's request.",
      "speaker": "Hallstein Brøtan",
      "speakerId": "hallstein-brotan",
      "speakerUrl": "https://the-ai-record.com/people/hallstein-brotan",
      "speakerLevel": "practitioner",
      "role": "Senior consultant, Novanet; developer on Nordic Corporate Bank's system",
      "voice": "person",
      "organization": "Nordic Corporate Bank",
      "organizationId": "nordic-corporate-bank",
      "organizationUrl": "https://the-ai-record.com/organizations/nordic-corporate-bank",
      "aiVendor": false,
      "work": {
        "title": "How We Built an Autonomous Development Workflow at Nordic Corporate Bank",
        "type": "talk",
        "date": "2026-06-29",
        "publisher": "NDC Conferences (YouTube); talk recorded at NDC in Oslo",
        "locator": "10:47",
        "url": "https://www.youtube.com/watch?v=p8M8--12h1Y"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-08"
      },
      "topics": [
        "context-for-agents",
        "autonomy-and-oversight"
      ],
      "functions": [
        "engineering",
        "product"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/nordic-corporate-bank-agent-wont-start-without-acceptance-criteria-2026",
      "json": "https://the-ai-record.com/api/v1/passages/nordic-corporate-bank-agent-wont-start-without-acceptance-criteria-2026.json"
    },
    {
      "id": "tessl-llms-just-the-engine-context-the-fuel-optimize-2026",
      "text": "But the way that I see it is they're just the engine. If you give the engine the wrong fuel, which is context, they're not going to perform. So and you can't do anything on the LLMs, at least not me, right? I'm just using the coding agent, I'm using whatever they give me. But I can optimize my context. And that's I think the message, doing this more in an engineered way than just copy and … things and hoping for the best.",
      "context": "Debois closes the talk by saying where he puts his effort when using a coding agent he did not build.",
      "speaker": "Patrick Debois",
      "speakerId": "patrick-debois",
      "speakerUrl": "https://the-ai-record.com/people/patrick-debois",
      "speakerLevel": "practitioner",
      "role": "Product DevRel Lead",
      "voice": "person",
      "organization": "Tessl",
      "organizationId": "tessl",
      "organizationUrl": "https://the-ai-record.com/organizations/tessl",
      "aiVendor": true,
      "work": {
        "title": "Context Is the New Code",
        "type": "talk",
        "date": "2026-05-03",
        "publisher": "AI Engineer (YouTube)",
        "locator": "23:45",
        "url": "https://www.youtube.com/watch?v=bSG9wUYaHWU"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-04"
      },
      "topics": [
        "coding-agents",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/tessl-llms-just-the-engine-context-the-fuel-optimize-2026",
      "json": "https://the-ai-record.com/api/v1/passages/tessl-llms-just-the-engine-context-the-fuel-optimize-2026.json"
    },
    {
      "id": "anthropic-context-engineering-good-set-fairly-simplistic-setup-reproducible-2026",
      "text": "When it comes to context management and context engineering, I think having a good set of actually fairly simplistic setup that is reproducible across engineers, with a good set of Claude MD setups, a good set of skills that really capture the essence of the role you're trying to do or the domain you're trying to operate in. I think that's really it and don't overthink it.",
      "context": null,
      "speaker": "Christian Ryan",
      "speakerId": "christian-ryan",
      "speakerUrl": "https://the-ai-record.com/people/christian-ryan",
      "speakerLevel": "leader",
      "role": "Applied AI lead",
      "voice": "person",
      "organization": "Anthropic",
      "organizationId": "anthropic",
      "organizationUrl": "https://the-ai-record.com/organizations/anthropic",
      "aiVendor": true,
      "work": {
        "title": "Let’s Talk Agentic Development: Spotify x Anthropic Live",
        "type": "post",
        "date": "2026-04-06",
        "publisher": "Spotify Engineering",
        "url": "https://engineering.atspotify.com/2026/4/anthropic-agentic-development"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-03"
      },
      "topics": [
        "training-and-skills",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/anthropic-context-engineering-good-set-fairly-simplistic-setup-reproducible-2026",
      "json": "https://the-ai-record.com/api/v1/passages/anthropic-context-engineering-good-set-fairly-simplistic-setup-reproducible-2026.json"
    },
    {
      "id": "stripe-built-central-internal-mcp-server-called-toolshed-2026",
      "text": "we built a central internal MCP server called Toolshed, which hosts more than 400 MCP tools",
      "context": null,
      "speaker": "Alistair Gray",
      "speakerId": "alistair-gray",
      "speakerUrl": "https://the-ai-record.com/people/alistair-gray",
      "speakerLevel": "practitioner",
      "role": "Software engineer, Leverage team",
      "voice": "person",
      "organization": "Stripe",
      "organizationId": "stripe",
      "organizationUrl": "https://the-ai-record.com/organizations/stripe",
      "aiVendor": false,
      "work": {
        "title": "Minions: Stripe’s one-shot, end-to-end coding agents",
        "type": "post",
        "date": "2026-02-09",
        "publisher": "Stripe developer blog",
        "url": "https://stripe.dev/blog/minions-stripes-one-shot-end-to-end-coding-agents"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "ai-across-the-company",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/stripe-built-central-internal-mcp-server-called-toolshed-2026",
      "json": "https://the-ai-record.com/api/v1/passages/stripe-built-central-internal-mcp-server-called-toolshed-2026.json"
    },
    {
      "id": "cursor-treat-model-brilliant-new-hire-prompts-2026",
      "text": "We found it was better to not instruct for things the model knows how to do, only things it doesn't know (e.g. multi-agent collaboration) or that are specific to the relevant domain (e.g. how to run tests, your deploy pipeline). Treat the model like a brilliant new hire who knows engineering but not your specific codebase and processes.",
      "context": null,
      "speaker": "Wilson Lin",
      "speakerId": "wilson-lin",
      "speakerUrl": "https://the-ai-record.com/people/wilson-lin",
      "speakerLevel": "practitioner",
      "role": "Researcher, Cursor (author of the Towards self-driving codebases post)",
      "voice": "person",
      "organization": "Cursor (Anysphere)",
      "organizationId": "cursor",
      "organizationUrl": "https://the-ai-record.com/organizations/cursor",
      "aiVendor": true,
      "work": {
        "title": "Towards self-driving codebases",
        "type": "post",
        "date": "2026-02-05",
        "publisher": "Cursor (own site)",
        "locator": "Optimizing prompts",
        "url": "https://cursor.com/blog/self-driving-codebases"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-08"
      },
      "topics": [
        "context-for-agents",
        "coding-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/cursor-treat-model-brilliant-new-hire-prompts-2026",
      "json": "https://the-ai-record.com/api/v1/passages/cursor-treat-model-brilliant-new-hire-prompts-2026.json"
    },
    {
      "id": "airbnb-main-success-driver-choosing-right-related-2025",
      "text": "the main success driver we saw was choosing the right related files (finding nearby files, good example files from the same project, filtering the dependencies for files that were relevant to the component, etc.), rather than getting the prompt engineering perfect.",
      "context": null,
      "speaker": "Charles Covey-Brandt",
      "speakerId": "charles-covey-brandt",
      "speakerUrl": "https://the-ai-record.com/people/charles-covey-brandt",
      "speakerLevel": "practitioner",
      "role": "Author of the Airbnb engineering blog post on LLM test migration (role not stated on the page)",
      "voice": "person",
      "organization": "Airbnb",
      "organizationId": "airbnb",
      "organizationUrl": "https://the-ai-record.com/organizations/airbnb",
      "aiVendor": false,
      "work": {
        "title": "Accelerating Large-Scale Test Migration with LLMs",
        "type": "post",
        "date": "2025-03-13",
        "publisher": "Airbnb Engineering & Data Science (own site)",
        "locator": "3. Increasing the Context",
        "url": "https://airbnb.tech/?p=366"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-04"
      },
      "topics": [
        "migrations",
        "coding-agents",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/airbnb-main-success-driver-choosing-right-related-2025",
      "json": "https://the-ai-record.com/api/v1/passages/airbnb-main-success-driver-choosing-right-related-2025.json"
    },
    {
      "id": "uber-job-engineering-build-right-context-agents-2026",
      "text": "The job of engineering is, in some sense: ‘how do you build the right context for the agents to produce reliable output?’ You need to get really good at context engineering.",
      "context": null,
      "speaker": "Uday Kiran Medisetty",
      "speakerId": "uday-kiran-medisetty",
      "speakerUrl": "https://the-ai-record.com/people/uday-kiran-medisetty",
      "speakerLevel": "practitioner",
      "role": "Distinguished Engineer",
      "voice": "person",
      "organization": "Uber",
      "organizationId": "uber",
      "organizationUrl": "https://the-ai-record.com/organizations/uber",
      "aiVendor": false,
      "work": {
        "title": "Uber's AI infra, from the inside",
        "type": "interview",
        "date": "2026-10-14",
        "publisher": "The Pragmatic Engineer",
        "locator": "Takeaway 10",
        "url": "https://newsletter.pragmaticengineer.com/p/ubers-ai-infra-from-the-inside"
      },
      "grade": "C",
      "gradeMeaning": "An interview or press quote.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-08"
      },
      "topics": [
        "engineer-role",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/uber-job-engineering-build-right-context-agents-2026",
      "json": "https://the-ai-record.com/api/v1/passages/uber-job-engineering-build-right-context-agents-2026.json"
    },
    {
      "id": "airbnb-own-internal-agent-call-airchat-which-includes-2026",
      "text": "We have our own internal agent that we call AirChat, which [includes] basically all the necessary MCP organizational context,",
      "context": null,
      "speaker": "Ahmad Al-Dahle",
      "speakerId": "ahmad-al-dahle",
      "speakerUrl": "https://the-ai-record.com/people/ahmad-al-dahle",
      "speakerLevel": "executive",
      "role": "Chief Technology Officer",
      "voice": "person",
      "organization": "Airbnb",
      "organizationId": "airbnb",
      "organizationUrl": "https://the-ai-record.com/organizations/airbnb",
      "aiVendor": false,
      "work": {
        "title": "Latent Space (independent AI engineering publication)",
        "type": "interview",
        "date": "2026-10-02",
        "publisher": "Latent Space (independent AI engineering publication)",
        "url": "https://www.latent.space/p/airbnb"
      },
      "grade": "C",
      "gradeMeaning": "An interview or press quote.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "internal-tools",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/airbnb-own-internal-agent-call-airchat-which-includes-2026",
      "json": "https://the-ai-record.com/api/v1/passages/airbnb-own-internal-agent-call-airchat-which-includes-2026.json"
    },
    {
      "id": "cognition-devin-permanent-pm-memory-file-slack-channel-2026",
      "text": "So we have like some Slack channels internally, maybe a Slack channel dedicated to, a specific product like DeepWiki maybe. And you can imagine that, or you want a Devin that never stops, it’s just always awake, but it has this like memory dock that it can just maintain for itself about, okay, what are like the number one priorities of what we have to fix and prioritize? Who is responsible for some upcoming work?",
      "context": null,
      "speaker": "Walden Yan",
      "speakerId": "walden-yan",
      "speakerUrl": "https://the-ai-record.com/people/walden-yan",
      "speakerLevel": "executive",
      "role": "Co-founder and Chief Product Officer",
      "voice": "person",
      "organization": "Cognition",
      "organizationId": "cognition",
      "organizationUrl": "https://the-ai-record.com/organizations/cognition",
      "aiVendor": true,
      "work": {
        "title": "The Age of Async Agents: Cognition's Walden Yan and OpenInspect's Cole Murray",
        "type": "podcast",
        "date": "2026-05-28",
        "publisher": "Latent Space",
        "locator": "00:33:01",
        "url": "https://latent.space/p/cognition"
      },
      "grade": "C",
      "gradeMeaning": "An interview or press quote.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-01"
      },
      "topics": [
        "internal-tools",
        "coding-agents",
        "context-for-agents"
      ],
      "functions": [
        "engineering",
        "product"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/cognition-devin-permanent-pm-memory-file-slack-channel-2026",
      "json": "https://the-ai-record.com/api/v1/passages/cognition-devin-permanent-pm-memory-file-slack-channel-2026.json"
    },
    {
      "id": "tessl-turned-code-helpers-into-skill-onboarding-agents-2026",
      "text": "I had large pieces of code that I was using, maybe some helpers and some other pieces, and I just turned them into a skill. We had that into our product. It was an onboarding from … AI agents. People have … Node.js, all the various things, then they have different tools for packaging, and it is impossible to actually code that. Like it will require a lot of coding. But if I just say a skill says, please first figure out what their package manager is, then figure out what their ecosystem is, and then do these steps together with the user, you know, it … solved a lot more problems that we could ever code.",
      "context": "Debois describes turning code helpers into a skill for the onboarding of AI agents into Tessl's product.",
      "speaker": "Patrick Debois",
      "speakerId": "patrick-debois",
      "speakerUrl": "https://the-ai-record.com/people/patrick-debois",
      "speakerLevel": "practitioner",
      "role": "Product DevRel Lead",
      "voice": "person",
      "organization": "Tessl",
      "organizationId": "tessl",
      "organizationUrl": "https://the-ai-record.com/organizations/tessl",
      "aiVendor": true,
      "work": {
        "title": "Context Is the New Code",
        "type": "talk",
        "date": "2026-05-03",
        "publisher": "AI Engineer (YouTube)",
        "locator": "1:37",
        "url": "https://www.youtube.com/watch?v=bSG9wUYaHWU"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "reported",
        "meaning": "Not yet confirmed against the source by an independent second reader."
      },
      "topics": [
        "product-and-design",
        "coding-agents",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/tessl-turned-code-helpers-into-skill-onboarding-agents-2026",
      "json": "https://the-ai-record.com/api/v1/passages/tessl-turned-code-helpers-into-skill-onboarding-agents-2026.json"
    },
    {
      "id": "dropbox-build-agent-loop-tools-context-ourselves-framework-lagged-2026",
      "text": "Ultimately, we opted to build the agent loop, tools, and the system for gathering context ourselves, and we connect directly to model providers instead of relying on a broad agent framework. That's because a framework we initially explored lagged behind the provider APIs we wanted to use and included more structure than Reclaim needed.",
      "context": null,
      "speaker": null,
      "speakerId": null,
      "speakerUrl": null,
      "speakerLevel": null,
      "role": null,
      "voice": "organization",
      "organization": "Dropbox",
      "organizationId": "dropbox",
      "organizationUrl": "https://the-ai-record.com/organizations/dropbox",
      "aiVendor": false,
      "work": {
        "title": "Evolving our calendar assistant Reclaim to be AI-native without starting over",
        "type": "post",
        "date": "2026-09-29",
        "publisher": "Dropbox.Tech",
        "locator": "Building the agent platform",
        "url": "https://dropbox.tech/machine-learning/evolving-calendar-assistant-reclaim-to-be-ai-native"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "reported",
        "meaning": "Not yet confirmed against the source by an independent second reader."
      },
      "topics": [
        "context-for-agents",
        "choosing-models"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/dropbox-build-agent-loop-tools-context-ourselves-framework-lagged-2026",
      "json": "https://the-ai-record.com/api/v1/passages/dropbox-build-agent-loop-tools-context-ourselves-framework-lagged-2026.json"
    },
    {
      "id": "uber-things-built-engineers-easier-agents-2026",
      "text": "All the things that we built to make life easier for engineers: it makes it easier for our agents as well!",
      "context": null,
      "speaker": "Uday Kiran Medisetty",
      "speakerId": "uday-kiran-medisetty",
      "speakerUrl": "https://the-ai-record.com/people/uday-kiran-medisetty",
      "speakerLevel": "practitioner",
      "role": "Distinguished Engineer",
      "voice": "person",
      "organization": "Uber",
      "organizationId": "uber",
      "organizationUrl": "https://the-ai-record.com/organizations/uber",
      "aiVendor": false,
      "work": {
        "title": "Uber's AI infra, from the inside",
        "type": "interview",
        "date": "2026-10-14",
        "publisher": "The Pragmatic Engineer",
        "locator": "Takeaway 11",
        "url": "https://newsletter.pragmaticengineer.com/p/ubers-ai-infra-from-the-inside"
      },
      "grade": "C",
      "gradeMeaning": "An interview or press quote.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-08"
      },
      "topics": [
        "internal-tools",
        "context-for-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/uber-things-built-engineers-easier-agents-2026",
      "json": "https://the-ai-record.com/api/v1/passages/uber-things-built-engineers-easier-agents-2026.json"
    },
    {
      "id": "openai-dots-agent-learns-no-loops-to-configure-2026",
      "text": "I think like having to set up and fiddle with your loops and, you know, figuring that out is something that, you know, maybe people got excited about, but I don't think this is the way that it's going to work. I think the way that it's going to work is how we're positioning and what we're shipping with dots, where you have an incredibly smart agent that works 24/7, understands your goals, understands your preferences, learns from feedback. And it's like, … not perfect. I will learn very much from making this available to our pro users. But over time, you just want … system that learns from what you want to achieve.",
      "context": "Asked about the shift from hand-built agent loops and graphs, Sottiaux describes the approach OpenAI took with its Dots personal agent.",
      "speaker": "Thibault Sottiaux",
      "speakerId": "thibault-sottiaux",
      "speakerUrl": "https://the-ai-record.com/people/thibault-sottiaux",
      "speakerLevel": "leader",
      "role": "Head of ChatGPT and Codex, OpenAI",
      "voice": "person",
      "organization": "OpenAI",
      "organizationId": "openai",
      "organizationUrl": "https://the-ai-record.com/organizations/openai",
      "aiVendor": true,
      "work": {
        "title": "OpenAI's Head of ChatGPT: We're entering a new era of AI (again)",
        "type": "podcast",
        "date": "2026-10-04",
        "publisher": "Lenny's Podcast (YouTube)",
        "locator": "03:19",
        "url": "https://www.youtube.com/watch?v=MM-C3JqCXBk"
      },
      "grade": "C",
      "gradeMeaning": "An interview or press quote.",
      "verification": {
        "status": "reported",
        "meaning": "Not yet confirmed against the source by an independent second reader."
      },
      "topics": [
        "context-for-agents"
      ],
      "functions": [
        "product"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/openai-dots-agent-learns-no-loops-to-configure-2026",
      "json": "https://the-ai-record.com/api/v1/passages/openai-dots-agent-learns-no-loops-to-configure-2026.json"
    },
    {
      "id": "openai-dots-built-on-research-memory-codex-harness-2026",
      "text": "But, you know, seriously, like … research, long persistent, long horizon tasks, this is something that we've worked on, you know, for more than two years. … And it's like, you know, it's just memory works very, very well in … and so we've put a lot of research in that. And, you know, all of this coming together on top of like the Codex harness and also the ability to just like run 24/7 with, you know, good productivity. That's what we launched with dots. And so it's the work of like many, many months.",
      "context": "Asked why Dots took so long to ship, Sottiaux describes the research OpenAI built it on.",
      "speaker": "Thibault Sottiaux",
      "speakerId": "thibault-sottiaux",
      "speakerUrl": "https://the-ai-record.com/people/thibault-sottiaux",
      "speakerLevel": "leader",
      "role": "Head of ChatGPT and Codex, OpenAI",
      "voice": "person",
      "organization": "OpenAI",
      "organizationId": "openai",
      "organizationUrl": "https://the-ai-record.com/organizations/openai",
      "aiVendor": true,
      "work": {
        "title": "OpenAI's Head of ChatGPT: We're entering a new era of AI (again)",
        "type": "podcast",
        "date": "2026-10-04",
        "publisher": "Lenny's Podcast (YouTube)",
        "locator": "15:14",
        "url": "https://www.youtube.com/watch?v=MM-C3JqCXBk"
      },
      "grade": "C",
      "gradeMeaning": "An interview or press quote.",
      "verification": {
        "status": "reported",
        "meaning": "Not yet confirmed against the source by an independent second reader."
      },
      "topics": [
        "context-for-agents"
      ],
      "functions": [
        "product",
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/openai-dots-built-on-research-memory-codex-harness-2026",
      "json": "https://the-ai-record.com/api/v1/passages/openai-dots-built-on-research-memory-codex-harness-2026.json"
    }
  ],
  "notice": [
    "Every passage is reproduced word for word from the cited source.",
    "Check the verification status: \"reported\" means not yet confirmed by an independent second reader.",
    "Organizations flagged aiVendor sell AI tools or services and have a reason to publish flattering numbers.",
    "An empty result means the archive holds nothing on it, not that nobody has said anything."
  ]
}