{
  "apiVersion": "v1",
  "topic": {
    "id": "employee-built-agents",
    "title": "Who builds an organization's agents: every team, or a central group?",
    "group": "Tools, models and knowledge",
    "summary": "Whether agents are built by the teams that use them or by a central platform team, and how many get built.",
    "passages": 7,
    "url": "https://the-ai-record.com/topics/employee-built-agents",
    "json": "https://the-ai-record.com/api/v1/topics/employee-built-agents.json"
  },
  "passages": [
    {
      "id": "vercel-tripod-engineer-data-scientist-expert-human-in-loop-2026",
      "text": "What the working model that we've used for all of our internal agent development is basically a tripod. It's a GTM engineer, a data scientist, and then the best person, the best subject matter expert in that function. And they sit down shoulder to shoulder and document the best practice for that particular function and then encode that in workflows that ultimately form an agent. We then keep a human in the loop so that human will basically QA the agent. The agent won't be allowed to autonomously execute its action. And then over time as the subject matter expert has less feedback for the agent, we finally pull that person.",
      "context": "Vercel's COO explains how her team builds internal agents ('GTM' is go-to-market).",
      "speaker": "Jeanne DeWitt Grosser",
      "speakerId": "jeanne-dewitt-grosser",
      "speakerUrl": "https://the-ai-record.com/people/jeanne-dewitt-grosser",
      "speakerLevel": "executive",
      "role": "Chief Operating Officer, Vercel",
      "voice": "person",
      "organization": "Vercel",
      "organizationId": "vercel",
      "organizationUrl": "https://the-ai-record.com/organizations/vercel",
      "aiVendor": true,
      "work": {
        "title": "Going from 10 to 1 SDRs. How We Deployed AI Across our Sales Org with Vercel's COO",
        "type": "talk",
        "date": "2026-11-04",
        "publisher": "SaaStr AI (YouTube); talk at SaaStr AI Annual 2026",
        "locator": "03:24",
        "url": "https://www.youtube.com/watch?v=wXHLbr4W-8s"
      },
      "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": [
        "team-structure",
        "employee-built-agents",
        "autonomy-and-oversight"
      ],
      "functions": [
        "company-wide"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/vercel-tripod-engineer-data-scientist-expert-human-in-loop-2026",
      "json": "https://the-ai-record.com/api/v1/passages/vercel-tripod-engineer-data-scientist-expert-human-in-loop-2026.json"
    },
    {
      "id": "ramp-on-call-assistant-begins-investigating-moment-incident-2026",
      "text": "We have on-call assistant that begins investigating the moment an incident is declared. We have Testo, a QA-focused agent. Our data team built Ramp research, creating an entirely custom tool set for the agent that's built on top of Inspect's access to our data warehouses. Our product operations team built Voice of the Customer, which synthesizes feedback from all the sources we have access to and compiles reports for teams. These, along with 200 other custom agents, all run on the Inspect's platform.",
      "context": "Bruggeman lists agents that teams at Ramp built on the Inspect platform.",
      "speaker": "Zach Bruggeman",
      "speakerId": "zach-bruggeman",
      "speakerUrl": "https://the-ai-record.com/people/zach-bruggeman",
      "speakerLevel": "practitioner",
      "role": "Principal engineer, Ramp",
      "voice": "person",
      "organization": "Ramp",
      "organizationId": "ramp",
      "organizationUrl": "https://the-ai-record.com/organizations/ramp",
      "aiVendor": false,
      "work": {
        "title": "@Inspect fix this | Zach Bruggeman Principal Software Engineer at Ramp, Runtime 2026",
        "type": "talk",
        "date": "2026-11-02",
        "publisher": "Modal (YouTube)",
        "locator": "07:16",
        "url": "https://www.youtube.com/watch?v=VTu6wAKgiwY"
      },
      "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": "2026-11-05"
      },
      "topics": [
        "internal-tools",
        "coding-agents",
        "employee-built-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [
        {
          "metric": "custom-agents",
          "value": 200,
          "unit": "agents",
          "period": "as described in 2026",
          "definition": "custom agents running on the Inspect platform in addition to those he lists, per the speaker ('200 other custom agents')",
          "level": "n/a"
        }
      ],
      "url": "https://the-ai-record.com/passages/ramp-on-call-assistant-begins-investigating-moment-incident-2026",
      "json": "https://the-ai-record.com/api/v1/passages/ramp-on-call-assistant-begins-investigating-moment-incident-2026.json"
    },
    {
      "id": "stripe-anyone-could-build-deploy-workflow-specific-agents-2026",
      "text": "Anyone could build and deploy workflow-specific agents that could use tools. Over 4,000 agents were built using this system.",
      "context": null,
      "speaker": "Sharadh Krishnamurthy",
      "speakerId": "sharadh-krishnamurthy",
      "speakerUrl": "https://the-ai-record.com/people/sharadh-krishnamurthy",
      "speakerLevel": "leader",
      "role": "Engineering manager, Agent Foundation team",
      "voice": "person",
      "organization": "Stripe",
      "organizationId": "stripe",
      "organizationUrl": "https://the-ai-record.com/organizations/stripe",
      "aiVendor": false,
      "work": {
        "title": "Stripe developer blog",
        "type": "post",
        "date": "2026-07-30",
        "publisher": "Stripe developer blog",
        "url": "https://stripe.dev/blog/meet-stripes-knowledge-ai-platform"
      },
      "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",
        "employee-built-agents"
      ],
      "functions": [
        "company-wide"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/stripe-anyone-could-build-deploy-workflow-specific-agents-2026",
      "json": "https://the-ai-record.com/api/v1/passages/stripe-anyone-could-build-deploy-workflow-specific-agents-2026.json"
    },
    {
      "id": "ramp-our-most-successful-example-review-buddy-code-review-2026",
      "text": "Our most successful example of this has been review buddy, our code review agent. It started with engineers on another team hooking up a GitHub webhook to Inspect's API with a review-oriented prompt. They could just focus on making the code review part great while we provided them all the infrastructure to actually run this agent. Now, review buddy runs on every pull request at Ramp, and we've replaced all of our third-party code review tools.",
      "context": "Bruggeman describes Review Buddy, a code review agent built on Inspect's API and platform.",
      "speaker": "Zach Bruggeman",
      "speakerId": "zach-bruggeman",
      "speakerUrl": "https://the-ai-record.com/people/zach-bruggeman",
      "speakerLevel": "practitioner",
      "role": "Principal engineer, Ramp",
      "voice": "person",
      "organization": "Ramp",
      "organizationId": "ramp",
      "organizationUrl": "https://the-ai-record.com/organizations/ramp",
      "aiVendor": false,
      "work": {
        "title": "@Inspect fix this | Zach Bruggeman Principal Software Engineer at Ramp, Runtime 2026",
        "type": "talk",
        "date": "2026-11-02",
        "publisher": "Modal (YouTube)",
        "locator": "06:52",
        "url": "https://www.youtube.com/watch?v=VTu6wAKgiwY"
      },
      "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": "2026-11-05"
      },
      "topics": [
        "code-review",
        "coding-agents",
        "employee-built-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/ramp-our-most-successful-example-review-buddy-code-review-2026",
      "json": "https://the-ai-record.com/api/v1/passages/ramp-our-most-successful-example-review-buddy-code-review-2026.json"
    },
    {
      "id": "github-i-used-coding-agents-build-agents-automated-2026",
      "text": "I used coding agents to build agents that automated part of my job.",
      "context": null,
      "speaker": null,
      "speakerId": null,
      "speakerUrl": null,
      "speakerLevel": null,
      "role": null,
      "voice": "organization",
      "organization": "GitHub",
      "organizationId": "github",
      "organizationUrl": "https://the-ai-record.com/organizations/github",
      "aiVendor": true,
      "work": {
        "title": "GitHub blog",
        "type": "post",
        "date": "2026-03-31",
        "publisher": "GitHub blog",
        "url": "https://github.blog/ai-and-ml/github-copilot/agent-driven-development-in-copilot-applied-science/"
      },
      "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",
        "employee-built-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/github-i-used-coding-agents-build-agents-automated-2026",
      "json": "https://the-ai-record.com/api/v1/passages/github-i-used-coding-agents-build-agents-automated-2026.json"
    },
    {
      "id": "figma-pm-os-engineering-managers-data-scientists-fork-2026",
      "text": "And so we got a lot of feedback. And then we had a public channel. And so we started getting like all of the engineering managers started using it and asking us if we could like come help them talk about how to do knowledge work for engineering. Our data scientists have one that is like essentially a fork of this. And so we were getting a lot of feedback about what it was good at and what it wasn't good at.",
      "context": "Mechaber is describing who beyond product managers picked up Figma's PM OS.",
      "speaker": "Ezra Mechaber",
      "speakerId": "ezra-mechaber",
      "speakerUrl": "https://the-ai-record.com/people/ezra-mechaber",
      "speakerLevel": "practitioner",
      "role": "Growth product manager, Figma",
      "voice": "person",
      "organization": "Figma",
      "organizationId": "figma",
      "organizationUrl": "https://the-ai-record.com/organizations/figma",
      "aiVendor": true,
      "work": {
        "title": "The AI chief of staff that this Figma PM uses all day (How I AI, hosted by Claire Vo)",
        "type": "podcast",
        "date": "2026-11-02",
        "publisher": "How I AI (YouTube)",
        "locator": "13:25",
        "url": "https://www.youtube.com/watch?v=ztt8irafLMQ"
      },
      "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": "2026-11-07"
      },
      "topics": [
        "adoption-and-usage",
        "ai-across-the-company",
        "employee-built-agents"
      ],
      "functions": [
        "product",
        "engineering",
        "data"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/figma-pm-os-engineering-managers-data-scientists-fork-2026",
      "json": "https://the-ai-record.com/api/v1/passages/figma-pm-os-engineering-managers-data-scientists-fork-2026.json"
    },
    {
      "id": "stripe-built-agentic-mle-tools-instructions-agents-2026",
      "text": "We built Agentic MLE, short for machine learning engineer, to take on more of that work. It’s a set of tools and instructions that lets AI agents operate in Stripe's existing ML infrastructure, carrying an experiment from an idea to a result: explore the data, implement a feature, compute its historical values, train a model, and evaluate it against a baseline.",
      "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": [
        "employee-built-agents",
        "internal-tools"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/stripe-built-agentic-mle-tools-instructions-agents-2026",
      "json": "https://the-ai-record.com/api/v1/passages/stripe-built-agentic-mle-tools-instructions-agents-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."
  ]
}