{
  "apiVersion": "v1",
  "topic": {
    "id": "bugs-and-incidents",
    "title": "Can AI fix bugs and handle incidents?",
    "summary": "AI that triages and fixes bugs, responds to incidents, or takes on-call work.",
    "group": "Building software",
    "aliases": [
      "bug fixing",
      "on-call",
      "outages"
    ]
  },
  "passages": [
    {
      "id": "ramp-past-four-weeks-oca-assisted-575-1-2026",
      "text": "In the past four weeks, OCA assisted with 575 of the 1,220 PRs merged to address incidents.",
      "speaker": "Richard Marmorstein",
      "role": "Co-author of Ramp's OCA post (job title not stated)",
      "organization": "Ramp",
      "aiVendor": false,
      "work": {
        "title": "How we built OCA, our AI on-call assistant",
        "type": "post",
        "date": "2026-09-09",
        "publisher": "Ramp engineering blog",
        "url": "https://builders.ramp.com/post/how-we-built-oca-our-ai-on-call-assistant"
      },
      "grade": "B",
      "verification": {
        "status": "verified",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "coding-agents",
        "bugs-and-incidents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [
        {
          "metric": "agent-prs",
          "value": 575,
          "unit": "count",
          "period": "past four weeks, as of 2026-09",
          "definition": "incident-fix PRs assisted by OCA, Ramp's AI on-call assistant",
          "level": "human-approves"
        }
      ],
      "context": null,
      "url": "https://the-ai-record.com/passages/ramp-past-four-weeks-oca-assisted-575-1-2026"
    },
    {
      "id": "ramp-testo-last-30-days-caught-425-bugs-2026",
      "text": "Testo, in the last 30 days, caught 425 bugs.",
      "speaker": "Geoff Charles",
      "role": "Chief Product Officer (CPO)",
      "organization": "Ramp",
      "aiVendor": false,
      "work": {
        "title": "What product looks like when coding is solved | Geoff Charles (Ramp CPO)",
        "type": "talk",
        "date": "2026-09-25",
        "publisher": "Lenny's Podcast (YouTube channel); Geoff Charles's talk at the Lenny and Friends Summit, recorded 2026-09-10",
        "url": "https://www.youtube.com/watch?v=ZG8Mf3P9xzI"
      },
      "grade": "B",
      "verification": {
        "status": "verified",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "bugs-and-incidents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [
        {
          "metric": "function-agent-volume",
          "value": 425,
          "unit": "count",
          "period": "past 30 days, as of 2026-09-25",
          "definition": "engineering QA: bugs caught by Testo, a browser-based testing agent",
          "level": "unclear"
        }
      ],
      "context": null,
      "url": "https://the-ai-record.com/passages/ramp-testo-last-30-days-caught-425-bugs-2026"
    },
    {
      "id": "ramp-right-now-oca-human-loop-2026",
      "text": "Right now, OCA is human-in-the-loop.",
      "speaker": "Richard Marmorstein",
      "role": "Co-author of Ramp's OCA post (job title not stated)",
      "organization": "Ramp",
      "aiVendor": false,
      "work": {
        "title": "How we built OCA, our AI on-call assistant",
        "type": "post",
        "date": "2026-09-09",
        "publisher": "Ramp engineering blog",
        "url": "https://builders.ramp.com/post/how-we-built-oca-our-ai-on-call-assistant"
      },
      "grade": "B",
      "verification": {
        "status": "verified",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "bugs-and-incidents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "context": null,
      "url": "https://the-ai-record.com/passages/ramp-right-now-oca-human-loop-2026"
    },
    {
      "id": "uber-growing-share-sessions-arent-initiated-humans-automated-2026",
      "text": "a growing share of sessions aren’t initiated by humans, but by automated managed agents handling code review, self-healing CI failures, completing E2E PRs with visual validation, triaging on-call alerts, debugging incoming bugs, and handling a variety of code maintenance tasks with human reviews/escalations.",
      "speaker": "Uday Kiran Medisetty",
      "role": "Distinguished Engineer",
      "organization": "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",
      "verification": {
        "status": "verified",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "code-review",
        "bugs-and-incidents",
        "coding-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "context": null,
      "url": "https://the-ai-record.com/passages/uber-growing-share-sessions-arent-initiated-humans-automated-2026"
    },
    {
      "id": "monzo-alert-investigation-automatic-investigations-paging-alerts-production-2026",
      "text": "Alert investigation: automatic investigations of paging alerts in production",
      "speaker": null,
      "role": null,
      "organization": "Monzo",
      "aiVendor": false,
      "work": {
        "title": "Building Agent Chip: Monzo's in-house agentic tool",
        "type": "post",
        "date": "2026-08-13",
        "publisher": "Monzo blog",
        "url": "https://monzo.com/blog/building-agent-chip"
      },
      "grade": "B",
      "verification": {
        "status": "verified",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "bugs-and-incidents",
        "coding-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "context": null,
      "url": "https://the-ai-record.com/passages/monzo-alert-investigation-automatic-investigations-paging-alerts-production-2026"
    },
    {
      "id": "airbnb-agents-spin-up-then-triage-run-your-2026",
      "text": "agents spin up to then triage and run your on-call",
      "speaker": "Ahmad Al-Dahle",
      "role": "Chief Technology Officer",
      "organization": "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",
      "verification": {
        "status": "verified",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "bugs-and-incidents",
        "coding-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "context": null,
      "url": "https://the-ai-record.com/passages/airbnb-agents-spin-up-then-triage-run-your-2026"
    },
    {
      "id": "boundary-agents-run-baml-programs-inspect-transcripts-humans-triage-2026",
      "text": "What we did was we built a system that actually has agents constantly running and creating BAML programs. … We then look at the entire … transcripts, see what tools they use, see what happened, and obviously we as humans can inspect them. But more importantly, we can have agents go inspect them. And agents find what was good, what was bad. … And we can have humans collaborate with these issues to figure out which ones are real, which ones are hallucinations, which ones don't have taste as much as I hate to use that word. And then we can have agents go ahead and create fixes to these problems and go to address them.",
      "speaker": "Vaibhav Gupta",
      "role": "Co-founder and Chief Executive",
      "organization": "Boundary (BoundaryML)",
      "aiVendor": true,
      "work": {
        "title": "Fighting Slop with Slop",
        "type": "talk",
        "date": "2026-07-31",
        "publisher": "AI Engineer (YouTube)",
        "locator": "5:05",
        "url": "https://www.youtube.com/watch?v=AMiyLItEtLA"
      },
      "grade": "B",
      "verification": {
        "status": "verified",
        "reviewedOn": "2026-11-01"
      },
      "topics": [
        "autonomy-and-oversight",
        "bugs-and-incidents",
        "testing"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "context": "Gupta is describing how the team tests its programming language when it does not rely on reading every line of code.",
      "url": "https://the-ai-record.com/passages/boundary-agents-run-baml-programs-inspect-transcripts-humans-triage-2026"
    },
    {
      "id": "cognition-sre-use-case-internally-think-auto-triage-2026",
      "text": "The SRE use case, internally we think about it as auto triage Because we just want every message that comes in, and that’s an alert, that’s a bug report, to have Devin just start triaging it before anything else. And we’ve leaned into this use case so much though that we’ve basically tried to make it so that you don’t ever have to leave Slack to interact with this.",
      "speaker": "Walden Yan",
      "role": "Co-founder and Chief Product Officer",
      "organization": "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": "01:03:24",
        "url": "https://latent.space/p/cognition"
      },
      "grade": "C",
      "verification": {
        "status": "verified",
        "reviewedOn": "2026-11-01"
      },
      "topics": [
        "bugs-and-incidents",
        "coding-agents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "context": null,
      "url": "https://the-ai-record.com/passages/cognition-sre-use-case-internally-think-auto-triage-2026"
    },
    {
      "id": "posthog-63-changed-lines-are-files-already-2026",
      "text": "At PostHog, for example, 63% of changed lines are in files that already exist, and fix is our largest commit type at 40%.",
      "speaker": "Jina Yoon",
      "role": "Author, PostHog newsletter",
      "organization": "PostHog",
      "aiVendor": true,
      "work": {
        "title": "Can software factories actually work?",
        "type": "post",
        "date": "2026-08-11",
        "publisher": "PostHog newsletter",
        "locator": "What software factories are missing",
        "url": "https://posthog.com/newsletter/software-factories"
      },
      "grade": "B",
      "verification": {
        "status": "verified",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "bugs-and-incidents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [
        {
          "metric": "changed-lines-in-existing-files-share",
          "value": 0.63,
          "unit": "share",
          "definition": "Share of changed lines that are in files that already exist",
          "level": "n/a"
        },
        {
          "metric": "fix-commit-share",
          "value": 0.4,
          "unit": "share",
          "definition": "Share of commits whose type is fix",
          "level": "n/a"
        }
      ],
      "context": null,
      "url": "https://the-ai-record.com/passages/posthog-63-changed-lines-are-files-already-2026"
    },
    {
      "id": "shopify-over-roughly-six-weeks-weve-run-thousands-2026",
      "text": "Over roughly six weeks, we’ve run thousands of scans, produced over 300 findings ranging from defense-in-depth improvements to resolved security incidents.",
      "speaker": "Zack Deveau",
      "role": "Title not stated on Deveau's author page; the post is written from Shopify's Application Security team",
      "organization": "Shopify",
      "aiVendor": false,
      "work": {
        "title": "Building an agentic harness that outlasts the model",
        "type": "post",
        "date": "2026-07-29",
        "publisher": "Shopify engineering blog",
        "url": "https://shopify.engineering/building-an-agentic-harness-that-outlasts-the-model"
      },
      "grade": "B",
      "verification": {
        "status": "verified",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "bugs-and-incidents",
        "testing",
        "security"
      ],
      "functions": [
        "security"
      ],
      "figures": [
        {
          "metric": "function-agent-volume",
          "value": 300,
          "unit": "count",
          "period": "about six weeks, as of 2026-07-29",
          "definition": "application security: findings produced by an agent harness that scans public-facing apps",
          "level": "unclear"
        }
      ],
      "context": null,
      "url": "https://the-ai-record.com/passages/shopify-over-roughly-six-weeks-weve-run-thousands-2026"
    },
    {
      "id": "uber-early-data-shows-70-all-house-background-2026",
      "text": "Early data shows that 70% of all our in house background agents, tasks which is Minions are toil.",
      "speaker": "Abhishek Tibrewal",
      "role": "Senior Data Scientist, Platform Engineering",
      "organization": "Uber",
      "aiVendor": false,
      "work": {
        "title": "Engineering Enablement podcast by DX (DX sells developer-productivity measurement software); recording of Uber's talk at DX Annual",
        "type": "social",
        "date": "2026-06-22",
        "publisher": "Engineering Enablement podcast by DX (DX sells developer-productivity measurement software); recording of Uber's talk at DX Annual",
        "url": "https://getdx.com/podcast/ubers-journey-measuring-ai-impact-on-developer-productivity/"
      },
      "grade": "B",
      "verification": {
        "status": "verified",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "bugs-and-incidents",
        "where-agents-run"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "context": null,
      "url": "https://the-ai-record.com/passages/uber-early-data-shows-70-all-house-background-2026"
    },
    {
      "id": "genentech-now-generating-operation-logs-uh-uh-daily-2026",
      "text": "We are now generating operation logs uh uh or daily summary of the platform",
      "speaker": "Xiucheng Quek",
      "role": "Software engineer",
      "organization": "Genentech",
      "aiVendor": false,
      "work": {
        "title": "Background Agents for Genomics and Cloud Ops",
        "type": "talk",
        "date": "2026-05-07",
        "publisher": "YouTube video of a talk or interview (speaker in notes)",
        "url": "https://www.youtube.com/watch?v=GXDtw0EmoX0"
      },
      "grade": "B",
      "verification": {
        "status": "verified",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "bugs-and-incidents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "context": null,
      "url": "https://the-ai-record.com/passages/genentech-now-generating-operation-logs-uh-uh-daily-2026"
    },
    {
      "id": "openai-building-agent-handholds-change-all-way-2026",
      "text": "We are building an agent that \"handholds\" a change all the way to production — whether it's a code change or a change behind a feature flag. It observes the relevant monitoring graphs, but can also build its own dashboard to monitor important signals. More of our code changes are going to production with this kind of agent monitoring.",
      "speaker": "Venkat Venkataramani",
      "role": "VP of Engineering, Applied Infra",
      "organization": "OpenAI",
      "aiVendor": true,
      "work": {
        "title": "Inside OpenAI's agentic software factory",
        "type": "press",
        "date": "2026-09-15",
        "publisher": "The Pragmatic Engineer",
        "locator": "2. Death of the IDE & pull requests",
        "url": "https://newsletter.pragmaticengineer.com/p/openai-software-factory"
      },
      "grade": "C",
      "verification": {
        "status": "verified",
        "reviewedOn": "2026-10-31"
      },
      "topics": [
        "coding-agents",
        "bugs-and-incidents"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "context": null,
      "url": "https://the-ai-record.com/passages/openai-building-agent-handholds-change-all-way-2026"
    }
  ],
  "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 tooling and have a reason to publish flattering numbers.",
    "An empty result means the archive holds nothing on it, not that nobody has said anything."
  ]
}