{ "apiVersion": "v1", "topic": { "id": "ai-approves-code", "title": "Can AI approve code changes without a person?", "group": "Reviewing agent code", "summary": "Where organizations let an AI reviewer approve or merge a change on its own, which changes still need a person, and what happened after.", "passages": 31, "url": "https://the-ai-record.com/topics/ai-approves-code", "json": "https://the-ai-record.com/api/v1/topics/ai-approves-code.json" }, "passages": [ { "id": "anthropic-agent-approval-never-counts-as-persons-2026", "text": "The change sets the tier, not the author. A classifier reads the change and picks its risk tier. … An agent's approval never counts as a person's, either. Automated review can clear a low-risk change, but it can't fill a slot that calls for a human.", "context": "From the section on human approval, where the post sets three risk tiers for changes to Claude Code's repos, needing no, one or two human approvals.", "speaker": null, "speakerId": null, "speakerUrl": null, "speakerLevel": null, "role": null, "voice": "organization", "organization": "Anthropic", "organizationId": "anthropic", "organizationUrl": "https://the-ai-record.com/organizations/anthropic", "aiVendor": true, "work": { "title": "How the Claude Code team does code review", "type": "post", "date": "2026-10-15", "publisher": "claude.dev Blog (Anthropic)", "locator": "Layer by layer: 5. Human approval, scaled by risk", "url": "https://claude.dev/blog/solving-code-review-at-anthropic/" }, "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": [ "ai-approves-code", "autonomy-and-oversight" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/anthropic-agent-approval-never-counts-as-persons-2026", "json": "https://the-ai-record.com/api/v1/passages/anthropic-agent-approval-never-counts-as-persons-2026.json" }, { "id": "traderspost-builder-verifies-ci-runs-deep-review-2026", "text": "The builder verifies with targeted checks and runs a quick self-review. CI runs the deterministic harness. The deep review runs on request in an independent session, with the verdict returned to whoever asked. The author's watch loop handles threads and formal re-requests. Humans own the required approvals, and bot or agent verdicts do not satisfy them.", "context": null, "speaker": null, "speakerId": null, "speakerUrl": null, "speakerLevel": null, "role": null, "voice": "organization", "organization": "TradersPost", "organizationId": "traderspost", "organizationUrl": "https://the-ai-record.com/organizations/traderspost", "aiVendor": false, "work": { "title": "The AI Review Bot We Reverted", "type": "post", "date": "2026-10-13", "publisher": "TradersPost blog", "locator": "What we do instead today", "url": "https://blog.traderspost.io/article/the-ai-review-bot-we-built-and-reverted" }, "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", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/traderspost-builder-verifies-ci-runs-deep-review-2026", "json": "https://the-ai-record.com/api/v1/passages/traderspost-builder-verifies-ci-runs-deep-review-2026.json" }, { "id": "greptile-almost-fifth-prs-merged-without-human-review-2026", "text": "You get a pretty high degree of confidence on merge. Today, almost a fifth of all the pull … are merged without any human review or without any human testing. … that is a number that we care a lot about and want to bring higher and higher, of course, within the guardrails of producing really high quality code.", "context": null, "speaker": "Daksh Gupta", "speakerId": "daksh-gupta", "speakerUrl": "https://the-ai-record.com/people/daksh-gupta", "speakerLevel": "executive", "role": "Co-founder", "voice": "person", "organization": "Greptile", "organizationId": "greptile", "organizationUrl": "https://the-ai-record.com/organizations/greptile", "aiVendor": true, "work": { "title": "AI-Generated Code Is Already Competing With Human Code", "type": "talk", "date": "2026-09-27", "publisher": "AI Engineer (YouTube)", "locator": "11:50", "url": "https://www.youtube.com/watch?v=474j-n1Ltxc" }, "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": [ "autonomy-and-oversight", "code-review", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [ { "metric": "share-prs-merged-without-human-review", "value": 0.2, "unit": "share", "period": "as of the talk (almost a fifth)", "definition": "pull requests that Greptile reviews that are merged without any human review or human testing, per the speaker (unit of work: PRs)", "level": "human-out" } ], "url": "https://the-ai-record.com/passages/greptile-almost-fifth-prs-merged-without-human-review-2026", "json": "https://the-ai-record.com/api/v1/passages/greptile-almost-fifth-prs-merged-without-human-review-2026.json" }, { "id": "rewind-auto-approve-not-auto-merge-bot-approve-review-gates-2026", "text": "Auto-approve is not auto-merge. When Diff Vader approves, it posts an APPROVE review, the same thing a human reviewer clicking “approve” does. It does not push the merge button. The engineer merges (or GitHub’s native auto-merge does, if they enabled it), and every existing gate—CI, branch protection, required-reviewer counts—still applies.", "context": null, "speaker": "Dave North", "speakerId": "dave-north", "speakerUrl": "https://the-ai-record.com/people/dave-north", "speakerLevel": "leader", "role": "Leads the technical operations group", "voice": "person", "organization": "Rewind", "organizationId": "rewind", "organizationUrl": "https://the-ai-record.com/organizations/rewind", "aiVendor": false, "work": { "title": "Review is the bottleneck now: How we let AI approve pull requests (safely)", "type": "post", "date": "2026-06-01", "publisher": "Rewind blog", "locator": "What an engineer actually sees", "url": "https://rewind.com/blog/ai-approve-pull-requests-safely/" }, "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": [ "autonomy-and-oversight", "code-review", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/rewind-auto-approve-not-auto-merge-bot-approve-review-gates-2026", "json": "https://the-ai-record.com/api/v1/passages/rewind-auto-approve-not-auto-merge-bot-approve-review-gates-2026.json" }, { "id": "rewind-diff-vader-ai-reviewer-only-reviewer-needed-low-risk-2026", "text": "So we built a system that fixes the allocation. It’s called Diff Vader: an AI reviewer that looks at every PR across our orgs and, for a carefully bounded set of low-risk changes, becomes the only reviewer needed, freeing human reviewers to spend their judgment where judgment actually matters.", "context": null, "speaker": "Dave North", "speakerId": "dave-north", "speakerUrl": "https://the-ai-record.com/people/dave-north", "speakerLevel": "leader", "role": "Leads the technical operations group", "voice": "person", "organization": "Rewind", "organizationId": "rewind", "organizationUrl": "https://the-ai-record.com/organizations/rewind", "aiVendor": false, "work": { "title": "Review is the bottleneck now: How we let AI approve pull requests (safely)", "type": "post", "date": "2026-06-01", "publisher": "Rewind blog", "locator": "Opening", "url": "https://rewind.com/blog/ai-approve-pull-requests-safely/" }, "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": [ "code-review", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/rewind-diff-vader-ai-reviewer-only-reviewer-needed-low-risk-2026", "json": "https://the-ai-record.com/api/v1/passages/rewind-diff-vader-ai-reviewer-only-reviewer-needed-low-risk-2026.json" }, { "id": "rewind-hard-rules-verdict-engine-cannot-override-auth-secrets-2026", "text": "It declares the hard rules the verdict engine is not allowed to override no matter what the council says: paths that touch authentication, authorization, secrets, encryption, and anything that changes who is allowed to approve future changes always require a human.", "context": null, "speaker": "Dave North", "speakerId": "dave-north", "speakerUrl": "https://the-ai-record.com/people/dave-north", "speakerLevel": "leader", "role": "Leads the technical operations group", "voice": "person", "organization": "Rewind", "organizationId": "rewind", "organizationUrl": "https://the-ai-record.com/organizations/rewind", "aiVendor": false, "work": { "title": "Review is the bottleneck now: How we let AI approve pull requests (safely)", "type": "post", "date": "2026-06-01", "publisher": "Rewind blog", "locator": "The council: many specialists, one question", "url": "https://rewind.com/blog/ai-approve-pull-requests-safely/" }, "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": [ "autonomy-and-oversight", "security", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/rewind-hard-rules-verdict-engine-cannot-override-auth-secrets-2026", "json": "https://the-ai-record.com/api/v1/passages/rewind-hard-rules-verdict-engine-cannot-override-auth-secrets-2026.json" }, { "id": "cursor-agentic-code-owner-approves-low-risk-prs-2026", "text": "we had code owners in our code base and they were kind of right most of the time, like 80% of the time. But for these 20% of the time, they cost a lot of bottlenecks for us internally. … So what we started doing was building this agentic code owner thing. And what it essentially does is look in at PRs and check in like, first of all, what's the risk of this? What's the risk level? … And if it is a low risk, it can just approve the PR …", "context": "Zakariasson is describing an internal Cursor tool that replaces some human code-owner reviews of pull requests.", "speaker": "Eric Zakariasson", "speakerId": "eric-zakariasson", "speakerUrl": "https://the-ai-record.com/people/eric-zakariasson", "speakerLevel": "practitioner", "role": "Engineer, Developer Experience and Product, Cursor", "voice": "person", "organization": "Cursor (Anysphere)", "organizationId": "cursor", "organizationUrl": "https://the-ai-record.com/organizations/cursor", "aiVendor": true, "work": { "title": "Building your own software factory", "type": "talk", "date": "2026-04-28", "publisher": "AI Engineer (YouTube)", "locator": "27:55", "url": "https://www.youtube.com/watch?v=rnDm57Py54A" }, "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": [ "code-review", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [ { "metric": "code-owner-correct-rate", "value": 80, "unit": "percent", "period": "as described in the 2026 talk", "definition": "share of the time code owners were right, in the speaker's words 'kind of right most of the time, like 80% of the time'", "level": "n/a" } ], "url": "https://the-ai-record.com/passages/cursor-agentic-code-owner-approves-low-risk-prs-2026", "json": "https://the-ai-record.com/api/v1/passages/cursor-agentic-code-owner-approves-low-risk-prs-2026.json" }, { "id": "intercom-controlled-pilot-100-prs-zero-reverts-2026", "text": "We started with a controlled pilot of over 100 PRs through the AI approval pipeline. The results: zero reverts of AI-approved PRs, and a 6–16x improvement in time-to-approval at the 75th percentile. Since then, the system has scaled significantly. In the first four weeks of broader rollout, 497 PRs went fully autonomous, with Claude writing the code and our AI approval system reviewing, approving, and shipping to production.", "context": null, "speaker": null, "speakerId": null, "speakerUrl": null, "speakerLevel": null, "role": null, "voice": "organization", "organization": "Intercom (renamed Fin in May 2026)", "organizationId": "intercom", "organizationUrl": "https://the-ai-record.com/organizations/intercom", "aiVendor": true, "work": { "title": "AI is approving our pull requests: Here's how we made it safe", "type": "post", "date": "2026-04-21", "publisher": "Intercom Blog", "locator": "The data", "url": "https://www.intercom.com/blog/ai-is-approving-our-pull-requests-heres-how-we-made-it-safe" }, "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": [ "code-review", "coding-agents", "measuring-impact", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [ { "metric": "ai-approved-pilot-reverts", "value": 0, "unit": "count", "period": "controlled pilot of over 100 PRs", "definition": "Reverts of AI-approved PRs in the pilot", "level": "human-out" }, { "metric": "fully-autonomous-prs", "value": 497, "unit": "count", "period": "first four weeks of broader rollout", "definition": "PRs where Claude wrote the code and the AI approval system reviewed, approved and shipped it", "level": "human-out" } ], "url": "https://the-ai-record.com/passages/intercom-controlled-pilot-100-prs-zero-reverts-2026", "json": "https://the-ai-record.com/api/v1/passages/intercom-controlled-pilot-100-prs-zero-reverts-2026.json" }, { "id": "intercom-over-93-prs-agent-driven-19-2026", "text": "Today, over 93% of our pull requests (PRs) across our two main codebases are Agent-driven. And over 19% are auto-approved with no human reviewer in the loop.", "context": null, "speaker": null, "speakerId": null, "speakerUrl": null, "speakerLevel": null, "role": null, "voice": "organization", "organization": "Intercom (renamed Fin in May 2026)", "organizationId": "intercom", "organizationUrl": "https://the-ai-record.com/organizations/intercom", "aiVendor": true, "work": { "title": "AI is approving our pull requests: Here's how we made it safe", "type": "post", "date": "2026-04-21", "publisher": "Intercom Blog", "locator": "Introduction", "url": "https://www.intercom.com/blog/ai-is-approving-our-pull-requests-heres-how-we-made-it-safe" }, "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", "code-review", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [ { "metric": "agent-driven-pr-share", "value": 0.93, "unit": "share", "period": "April 2026, two main codebases", "definition": "Share of pull requests that are Agent-driven, as Intercom states it", "level": "unclear" }, { "metric": "auto-approved-pr-share", "value": 0.19, "unit": "share", "period": "April 2026, two main codebases", "definition": "Share of pull requests auto-approved with no human reviewer in the loop", "level": "human-out" } ], "url": "https://the-ai-record.com/passages/intercom-over-93-prs-agent-driven-19-2026", "json": "https://the-ai-record.com/api/v1/passages/intercom-over-93-prs-agent-driven-19-2026.json" }, { "id": "ona-agent-approve-review-person-always-clicks-merge-2026", "text": "The AI agent can approve the review, but a person always clicks the merge button. That merge is the traceable approval event for SOC 2: the agent handles the review workload, the human controls what ships.", "context": null, "speaker": null, "speakerId": null, "speakerUrl": null, "speakerLevel": null, "role": null, "voice": "organization", "organization": "Ona", "organizationId": "ona", "organizationUrl": "https://the-ai-record.com/organizations/ona", "aiVendor": true, "work": { "title": "How auto-approving low-risk PRs with AI cut our lead time by 74%", "type": "post", "date": "2026-04-09", "publisher": "Ona blog", "locator": "Governance", "url": "https://ona.com/stories/auto-approving-low-risk-prs" }, "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": [ "autonomy-and-oversight", "code-review", "ai-approves-code", "regulated-ai" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/ona-agent-approve-review-person-always-clicks-merge-2026", "json": "https://the-ai-record.com/api/v1/passages/ona-agent-approve-review-person-always-clicks-merge-2026.json" }, { "id": "ona-engineers-cannot-self-classify-change-low-risk-2026", "text": "First, engineers cannot self-classify a change as low-risk. An Ona Automation evaluates every PR against objective criteria automatically, which removes the temptation to game the system and makes the boundary auditable.", "context": null, "speaker": null, "speakerId": null, "speakerUrl": null, "speakerLevel": null, "role": null, "voice": "organization", "organization": "Ona", "organizationId": "ona", "organizationUrl": "https://the-ai-record.com/organizations/ona", "aiVendor": true, "work": { "title": "How auto-approving low-risk PRs with AI cut our lead time by 74%", "type": "post", "date": "2026-04-09", "publisher": "Ona blog", "locator": "The policy", "url": "https://ona.com/stories/auto-approving-low-risk-prs" }, "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": [ "code-review", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/ona-engineers-cannot-self-classify-change-low-risk-2026", "json": "https://the-ai-record.com/api/v1/passages/ona-engineers-cannot-self-classify-change-low-risk-2026.json" }, { "id": "ona-engineers-waited-median-2-hours-49-minutes-first-approval-2026", "text": "Our engineers waited a median of 2 hours 49 minutes for their first PR approval. Four weeks after we let an AI agent approve low-risk PRs, that dropped to 3.8 minutes, lead time fell 74%, and deploys tripled, all with the same size team.", "context": null, "speaker": null, "speakerId": null, "speakerUrl": null, "speakerLevel": null, "role": null, "voice": "organization", "organization": "Ona", "organizationId": "ona", "organizationUrl": "https://the-ai-record.com/organizations/ona", "aiVendor": true, "work": { "title": "How auto-approving low-risk PRs with AI cut our lead time by 74%", "type": "post", "date": "2026-04-09", "publisher": "Ona blog", "locator": "Opening", "url": "https://ona.com/stories/auto-approving-low-risk-prs" }, "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": [ "code-review", "developer-productivity", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [ { "metric": "median-time-to-first-pr-approval-before", "value": 169, "unit": "minutes", "period": "before 2026-03-13", "definition": "Median time to first approval on a pull request", "level": "n/a" }, { "metric": "median-time-to-first-pr-approval-after", "value": 3.8, "unit": "minutes", "period": "four weeks after the AI agent began approving low-risk PRs", "definition": "Median time to first approval; the agent approves the review, a human still merges", "level": "human-approves" }, { "metric": "lead-time-change", "value": -0.74, "unit": "share", "period": "four weeks after vs before", "definition": "Change in median lead time", "level": "human-approves" } ], "url": "https://the-ai-record.com/passages/ona-engineers-waited-median-2-hours-49-minutes-first-approval-2026", "json": "https://the-ai-record.com/api/v1/passages/ona-engineers-waited-median-2-hours-49-minutes-first-approval-2026.json" }, { "id": "anthropic-run-code-review-nearly-every-pr-16-54-2026", "text": "We run Code Review on nearly every PR at Anthropic. Before, 16% of PRs got substantive review comments. Now 54% do. It won't approve PRs — that's still a human call — but it closes the gap so reviewers can actually cover what's shipping.", "context": null, "speaker": null, "speakerId": null, "speakerUrl": null, "speakerLevel": null, "role": null, "voice": "organization", "organization": "Anthropic", "organizationId": "anthropic", "organizationUrl": "https://the-ai-record.com/organizations/anthropic", "aiVendor": true, "work": { "title": "Bringing Code Review to Claude Code", "type": "post", "date": "2026-03-09", "publisher": "claude.com (Anthropic)", "locator": "Managing the review bottleneck", "url": "https://claude.com/resources/articles/code-review" }, "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": [ "code-review", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [ { "metric": "prs-with-substantive-review-comments", "value": 0.54, "unit": "share", "period": "after Code Review, before March 2026 (up from 16%)", "definition": "share of Anthropic PRs receiving substantive review comments; the post does not define 'substantive'", "level": "human-approves" } ], "url": "https://the-ai-record.com/passages/anthropic-run-code-review-nearly-every-pr-16-54-2026", "json": "https://the-ai-record.com/api/v1/passages/anthropic-run-code-review-nearly-every-pr-16-54-2026.json" }, { "id": "customer-io-ai-approving-over-60-percent-prs-feedback-minutes-2025", "text": "The AI is approving over 60% of all PRs. For those PRs, engineers get feedback in minutes, not hours.", "context": null, "speaker": "Joey Bates", "speakerId": "joey-bates", "speakerUrl": "https://the-ai-record.com/people/joey-bates", "speakerLevel": "practitioner", "role": "Developer Enablement", "voice": "person", "organization": "Customer.io", "organizationId": "customer-io", "organizationUrl": "https://the-ai-record.com/organizations/customer-io", "aiVendor": false, "work": { "title": "How we taught AI to approve pull requests (not just review them)", "type": "post", "date": "2025-11-10", "publisher": "Customer.io", "locator": "Results: Speed and cognitive relief", "url": "https://customer.io/learn/how-we-work/how-we-taught-ai-to-approve-pull-requests" }, "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": [ "code-review", "adoption-and-usage", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [ { "metric": "share-prs-ai-approved", "value": 0.6, "unit": "share", "definition": "Share of all PRs the AI approves (stated as \"over 60%\")", "level": "human-out" } ], "url": "https://the-ai-record.com/passages/customer-io-ai-approving-over-60-percent-prs-feedback-minutes-2025", "json": "https://the-ai-record.com/api/v1/passages/customer-io-ai-approving-over-60-percent-prs-feedback-minutes-2025.json" }, { "id": "customer-io-high-risk-prs-flagged-human-review-took-day-2025", "text": "High-risk PRs that the system flagged for human review took about a day to approve. That's longer than the baseline. This is correct behavior. These are architectural changes, infrastructure modifications, and breaking changes. They need time and human judgment.", "context": null, "speaker": "Joey Bates", "speakerId": "joey-bates", "speakerUrl": "https://the-ai-record.com/people/joey-bates", "speakerLevel": "practitioner", "role": "Developer Enablement", "voice": "person", "organization": "Customer.io", "organizationId": "customer-io", "organizationUrl": "https://the-ai-record.com/organizations/customer-io", "aiVendor": false, "work": { "title": "How we taught AI to approve pull requests (not just review them)", "type": "post", "date": "2025-11-10", "publisher": "Customer.io", "locator": "Results: Safety validation", "url": "https://customer.io/learn/how-we-work/how-we-taught-ai-to-approve-pull-requests" }, "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": [ "autonomy-and-oversight", "code-review", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/customer-io-high-risk-prs-flagged-human-review-took-day-2025", "json": "https://the-ai-record.com/api/v1/passages/customer-io-high-risk-prs-flagged-human-review-took-day-2025.json" }, { "id": "customer-io-taught-ai-approve-pull-requests-500-approved-2025", "text": "We taught AI to approve pull requests for merging. After 500 AI-approved PRs: zero production incidents, and merge time dropped from 3.5 hours to 33 minutes.", "context": null, "speaker": "Joey Bates", "speakerId": "joey-bates", "speakerUrl": "https://the-ai-record.com/people/joey-bates", "speakerLevel": "practitioner", "role": "Developer Enablement", "voice": "person", "organization": "Customer.io", "organizationId": "customer-io", "organizationUrl": "https://the-ai-record.com/organizations/customer-io", "aiVendor": false, "work": { "title": "How we taught AI to approve pull requests (not just review them)", "type": "post", "date": "2025-11-10", "publisher": "Customer.io", "locator": "Article summary", "url": "https://customer.io/learn/how-we-work/how-we-taught-ai-to-approve-pull-requests" }, "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": [ "code-review", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [ { "metric": "ai-approved-prs", "value": 500, "unit": "count", "definition": "AI-approved pull requests at the time of writing", "level": "human-out" }, { "metric": "median-merge-time-ai-approved", "value": 33, "unit": "minutes", "definition": "Median time to merge for PRs that got AI approval; baseline 3.5 hours before the AI review system", "level": "human-out" } ], "url": "https://the-ai-record.com/passages/customer-io-taught-ai-approve-pull-requests-500-approved-2025", "json": "https://the-ai-record.com/api/v1/passages/customer-io-taught-ai-approve-pull-requests-500-approved-2025.json" }, { "id": "uber-still-require-engineer-review-every-pr-green-lane-2026", "text": "right now we still require an engineer to review every PR … goes in. … Once the more confidence we get in our risk scoring and we can also back test it with years of data, right? We have all of this data and the more confidence we have in our AI code reviews, then maybe for some class of low risk PRs, we could enable, we call it green lane like auto landing.", "context": "Answering the host's question whether human code review will always exist.", "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": "Uber's AI infra, from the inside", "type": "podcast", "date": "2026-10-14", "publisher": "The Pragmatic Engineer (YouTube)", "locator": "59:37", "url": "https://www.youtube.com/watch?v=MDUYSMJmi8A" }, "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": [ "ai-approves-code", "code-review", "reading-agent-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/uber-still-require-engineer-review-every-pr-green-lane-2026", "json": "https://the-ai-record.com/api/v1/passages/uber-still-require-engineer-review-every-pr-green-lane-2026.json" }, { "id": "warp-reviewer-agent-surfaces-issues-inconsistencies-human-2026", "text": "The reviewer agent surfaces issues and inconsistencies; the human makes the final call on quality and correctness.", "context": null, "speaker": null, "speakerId": null, "speakerUrl": null, "speakerLevel": null, "role": null, "voice": "organization", "organization": "Warp", "organizationId": "warp", "organizationUrl": "https://the-ai-record.com/organizations/warp", "aiVendor": true, "work": { "title": "Set up your software factory", "type": "docs", "date": "2026-10-28", "publisher": "Warp docs", "locator": "5. Human review: merge the PR", "url": "https://docs.warp.dev/guides/agent-workflows/set-up-a-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": [ "code-review", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/warp-reviewer-agent-surfaces-issues-inconsistencies-human-2026", "json": "https://the-ai-record.com/api/v1/passages/warp-reviewer-agent-surfaces-issues-inconsistencies-human-2026.json" }, { "id": "anthropic-goal-at-most-one-human-in-loop-per-pr-2026", "text": "So the goal is that most pull requests in the Claude Code repos … merge with at most one human in the loop, who can be the author, with no increase in reverts or incidents. To measure human time, we track human approvals per PR (median and 95th percentile), human comments, and how long a PR waits on a person. Revert and incident rates are the guardrail: if they rise, we haven't saved human time, we've only moved it.", "context": null, "speaker": null, "speakerId": null, "speakerUrl": null, "speakerLevel": null, "role": null, "voice": "organization", "organization": "Anthropic", "organizationId": "anthropic", "organizationUrl": "https://the-ai-record.com/organizations/anthropic", "aiVendor": true, "work": { "title": "How the Claude Code team does code review", "type": "post", "date": "2026-10-15", "publisher": "claude.dev Blog (Anthropic)", "locator": "The scarce resource: human time and attention", "url": "https://claude.dev/blog/solving-code-review-at-anthropic/" }, "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": [ "measuring-impact", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/anthropic-goal-at-most-one-human-in-loop-per-pr-2026", "json": "https://the-ai-record.com/api/v1/passages/anthropic-goal-at-most-one-human-in-loop-per-pr-2026.json" }, { "id": "anthropic-no-circuit-breakers-before-zero-human-merges-2026", "text": "We don't yet have circuit breakers that tighten approval when those numbers move; engineers here want them before more code moves to zero-human merges.", "context": "\"Those numbers\" are the revert and incident rates: the sentence before says noticing a bad merge still depends on the author, on-call, and the revert and incident dashboards.", "speaker": null, "speakerId": null, "speakerUrl": null, "speakerLevel": null, "role": null, "voice": "organization", "organization": "Anthropic", "organizationId": "anthropic", "organizationUrl": "https://the-ai-record.com/organizations/anthropic", "aiVendor": true, "work": { "title": "How the Claude Code team does code review", "type": "post", "date": "2026-10-15", "publisher": "claude.dev Blog (Anthropic)", "locator": "Layer by layer: 7. Fast detection, fast rollback", "url": "https://claude.dev/blog/solving-code-review-at-anthropic/" }, "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": [ "ai-approves-code", "autonomy-and-oversight" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/anthropic-no-circuit-breakers-before-zero-human-merges-2026", "json": "https://the-ai-record.com/api/v1/passages/anthropic-no-circuit-breakers-before-zero-human-merges-2026.json" }, { "id": "uber-currently-we-still-have-humans-approving-2026", "text": "Currently, we still have humans approving the code, but we see a short path in the near future to a percentage of our code landing automatically, having automatic approvals, right?", "context": "Will Bond is describing where Uber expects code review to go as it moves to an agentic software development life cycle.", "speaker": "Will Bond", "speakerId": "will-bond", "speakerUrl": "https://the-ai-record.com/people/will-bond", "speakerLevel": "practitioner", "role": "Staff Engineer, AI Foundations team, Development Platform organization", "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": "11:39", "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": [ "autonomy-and-oversight", "code-review", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/uber-currently-we-still-have-humans-approving-2026", "json": "https://the-ai-record.com/api/v1/passages/uber-currently-we-still-have-humans-approving-2026.json" }, { "id": "nordic-corporate-bank-removing-the-human-pull-request-step-2026", "text": "So as I said, doing pull requests … not an ideal situation. So we want to remove ourselves from that step to make it fully autonomous. I do think maybe that we need another like Opus 4.5 moment that LLM's, there's a new version that just is better. … But there are a lot of changes that could go straight to test. Like the document search could have gone without us approving it. But … it kind of needs to build this track record of doing stuff right before we trust it. So we're not quite there yet. But I think it's a matter of time.", "context": "Answering a question about taking the human out of the loop, the speaker says a person still approves the agent's pull requests and what would change that.", "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": "52:33", "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": [ "ai-approves-code", "autonomy-and-oversight" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/nordic-corporate-bank-removing-the-human-pull-request-step-2026", "json": "https://the-ai-record.com/api/v1/passages/nordic-corporate-bank-removing-the-human-pull-request-step-2026.json" }, { "id": "aircloset-cortex-went-all-ai-writes-code-2026", "text": "cortex went all-in: the AI writes the code, the AI reviews the code. What humans keep their hands on is \"tuning the prompts and guidelines themselves\" -- not making decisions inside each individual PR, but watching the system from above and adjusting.", "context": null, "speaker": "Ryosuke Tsuji", "speakerId": "ryosuke-tsuji", "speakerUrl": "https://the-ai-record.com/people/ryosuke-tsuji", "speakerLevel": "executive", "role": "CTO", "voice": "person", "organization": "airCloset", "organizationId": "aircloset", "organizationUrl": "https://the-ai-record.com/organizations/aircloset", "aiVendor": false, "work": { "title": "Human-on-the-Loop: AI Reviewing AI PRs at cortex -- 769 PRs/month while raising the quality bar", "type": "post", "date": "2026-05-26", "publisher": "DEV Community", "locator": "cortex's answer: move the reviewer role to AI as well", "url": "https://dev.to/ryantsuji/human-on-the-loop-ai-reviewing-ai-prs-at-cortex-769-prsmonth-while-raising-the-quality-bar-4lh5" }, "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": [ "code-review", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/aircloset-cortex-went-all-ai-writes-code-2026", "json": "https://the-ai-record.com/api/v1/passages/aircloset-cortex-went-all-ai-writes-code-2026.json" }, { "id": "aircloset-every-769-prs-ai-reviewer-first-2026", "text": "Every one of those 769 PRs had an AI reviewer as the first reviewer, with an average of 10.8 review-fix loop iterations per PR (max 56). 1 in 5 merged within 10 minutes, roughly half within 30 minutes. What humans do now is look at review outcomes and tune the review prompt and the guidelines themselves -- this is human-on-the-loop, not human-in-the-loop. Humans operate on the policy layer, not the execution layer.", "context": null, "speaker": "Ryosuke Tsuji", "speakerId": "ryosuke-tsuji", "speakerUrl": "https://the-ai-record.com/people/ryosuke-tsuji", "speakerLevel": "executive", "role": "CTO", "voice": "person", "organization": "airCloset", "organizationId": "aircloset", "organizationUrl": "https://the-ai-record.com/organizations/aircloset", "aiVendor": false, "work": { "title": "Human-on-the-Loop: AI Reviewing AI PRs at cortex -- 769 PRs/month while raising the quality bar", "type": "post", "date": "2026-05-26", "publisher": "DEV Community", "locator": "Start with last month's numbers", "url": "https://dev.to/ryantsuji/human-on-the-loop-ai-reviewing-ai-prs-at-cortex-769-prsmonth-while-raising-the-quality-bar-4lh5" }, "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": [ "code-review", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [ { "metric": "prs-merged", "value": 769, "unit": "pull requests", "period": "30 days, Apr 21 to May 21", "definition": "pull requests merged on cortex, airCloset's internal AI platform", "level": "human-out" }, { "metric": "avg-review-iterations", "value": 10.8, "unit": "iterations per PR", "period": "30 days, Apr 21 to May 21", "definition": "review-fix loop iterations per PR", "level": "human-out" } ], "url": "https://the-ai-record.com/passages/aircloset-every-769-prs-ai-reviewer-first-2026", "json": "https://the-ai-record.com/api/v1/passages/aircloset-every-769-prs-ai-reviewer-first-2026.json" }, { "id": "genentech-allowing-bot-merge-directly-into-main-branch-2026", "text": "we are allowing the bot to merge that directly into our main branch because we have integration tests, unit tests, etc., canary tests.", "context": null, "speaker": "Xiucheng Quek", "speakerId": "xiucheng-quek", "speakerUrl": "https://the-ai-record.com/people/xiucheng-quek", "speakerLevel": "practitioner", "role": "Software engineer", "voice": "person", "organization": "Genentech", "organizationId": "genentech", "organizationUrl": "https://the-ai-record.com/organizations/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", "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": [ "testing", "coding-agents", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/genentech-allowing-bot-merge-directly-into-main-branch-2026", "json": "https://the-ai-record.com/api/v1/passages/genentech-allowing-bot-merge-directly-into-main-branch-2026.json" }, { "id": "intercom-agent-strict-wont-approve-large-prs-2026", "text": "Our Agent is strict. It won’t approve large PRs. If a change is too big, too complex, or too broad in scope, it flags it and requires it to be broken down. Creating a direct, positive incentive for engineers to ship smaller, more incremental, well-scoped changes.", "context": null, "speaker": null, "speakerId": null, "speakerUrl": null, "speakerLevel": null, "role": null, "voice": "organization", "organization": "Intercom (renamed Fin in May 2026)", "organizationId": "intercom", "organizationUrl": "https://the-ai-record.com/organizations/intercom", "aiVendor": true, "work": { "title": "AI is approving our pull requests: Here's how we made it safe", "type": "post", "date": "2026-04-21", "publisher": "Intercom Blog", "locator": "Not just faster; safer", "url": "https://www.intercom.com/blog/ai-is-approving-our-pull-requests-heres-how-we-made-it-safe" }, "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": [ "code-review", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/intercom-agent-strict-wont-approve-large-prs-2026", "json": "https://the-ai-record.com/api/v1/passages/intercom-agent-strict-wont-approve-large-prs-2026.json" }, { "id": "cloudflare-bias-explicitly-toward-approval-meaning-single-2026", "text": "The bias is explicitly toward approval, meaning a single warning in an otherwise clean MR still gets approved_with_comments rather than a block.", "context": null, "speaker": "Ryan Skidmore", "speakerId": "ryan-skidmore", "speakerUrl": "https://the-ai-record.com/people/ryan-skidmore", "speakerLevel": "practitioner", "role": "Author of Cloudflare's \"Orchestrating AI Code Review at scale\" blog post", "voice": "person", "organization": "Cloudflare", "organizationId": "cloudflare", "organizationUrl": "https://the-ai-record.com/organizations/cloudflare", "aiVendor": true, "work": { "title": "Orchestrating AI Code Review at scale", "type": "post", "date": "2026-04-20", "publisher": "Cloudflare blog", "locator": "The coordinator helps keep things focused", "url": "https://blog.cloudflare.com/ai-code-review" }, "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": [ "code-review", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/cloudflare-bias-explicitly-toward-approval-meaning-single-2026", "json": "https://the-ai-record.com/api/v1/passages/cloudflare-bias-explicitly-toward-approval-meaning-single-2026.json" }, { "id": "cloudflare-metric-we-re-proudest-though-engineers-2026", "text": "That is fast enough that most engineers see the review comment before they have finished context-switching to another task. The metric we’re the proudest about, though, is that engineers have only needed to “break glass” 288 times (0.6% of merge requests).", "context": null, "speaker": "Ryan Skidmore", "speakerId": "ryan-skidmore", "speakerUrl": "https://the-ai-record.com/people/ryan-skidmore", "speakerLevel": "practitioner", "role": "Author of Cloudflare's \"Orchestrating AI Code Review at scale\" blog post", "voice": "person", "organization": "Cloudflare", "organizationId": "cloudflare", "organizationUrl": "https://the-ai-record.com/organizations/cloudflare", "aiVendor": true, "work": { "title": "Orchestrating AI Code Review at scale", "type": "post", "date": "2026-04-20", "publisher": "Cloudflare blog", "locator": "Show me the numbers! / The overview", "url": "https://blog.cloudflare.com/ai-code-review" }, "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": [ "autonomy-and-oversight", "measuring-impact", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [ { "metric": "break-glass-overrides", "value": 288, "unit": "count", "period": "March 10 to April 9, 2026", "definition": "Times an engineer commented break glass to force approval over the AI review; 0.6% of merge requests", "level": "human-out" } ], "url": "https://the-ai-record.com/passages/cloudflare-metric-we-re-proudest-though-engineers-2026", "json": "https://the-ai-record.com/api/v1/passages/cloudflare-metric-we-re-proudest-though-engineers-2026.json" }, { "id": "cloudflare-running-tens-thousands-merge-requests-approves-clean-2026", "text": "We've been running this system internally across tens of thousands of merge requests. It approves clean code, flags real bugs with impressive accuracy, and actively blocks merges when it finds genuine, serious problems or security vulnerabilities.", "context": null, "speaker": "Ryan Skidmore", "speakerId": "ryan-skidmore", "speakerUrl": "https://the-ai-record.com/people/ryan-skidmore", "speakerLevel": "practitioner", "role": "Author of Cloudflare's \"Orchestrating AI Code Review at scale\" blog post", "voice": "person", "organization": "Cloudflare", "organizationId": "cloudflare", "organizationUrl": "https://the-ai-record.com/organizations/cloudflare", "aiVendor": true, "work": { "title": "Orchestrating AI Code Review at scale", "type": "post", "date": "2026-04-20", "publisher": "Cloudflare blog", "locator": "Introduction", "url": "https://blog.cloudflare.com/ai-code-review" }, "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": [ "code-review", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/cloudflare-running-tens-thousands-merge-requests-approves-clean-2026", "json": "https://the-ai-record.com/api/v1/passages/cloudflare-running-tens-thousands-merge-requests-approves-clean-2026.json" }, { "id": "customer-io-most-ai-code-review-tools-stop-comments-approves-2025", "text": "Most AI code review tools stop at comments. They suggest improvements, flag issues, and point out problems. We built a system that approves PRs for merging.", "context": null, "speaker": "Joey Bates", "speakerId": "joey-bates", "speakerUrl": "https://the-ai-record.com/people/joey-bates", "speakerLevel": "practitioner", "role": "Developer Enablement", "voice": "person", "organization": "Customer.io", "organizationId": "customer-io", "organizationUrl": "https://the-ai-record.com/organizations/customer-io", "aiVendor": false, "work": { "title": "How we taught AI to approve pull requests (not just review them)", "type": "post", "date": "2025-11-10", "publisher": "Customer.io", "locator": "Problem: The cognitive weight of waiting", "url": "https://customer.io/learn/how-we-work/how-we-taught-ai-to-approve-pull-requests" }, "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": [ "code-review", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/customer-io-most-ai-code-review-tools-stop-comments-approves-2025", "json": "https://the-ai-record.com/api/v1/passages/customer-io-most-ai-code-review-tools-stop-comments-approves-2025.json" }, { "id": "spotify-weve-merged-more-than-2-5-million-2026", "text": "we've merged more than 2.5 million automated maintenance PRs, the vast majority auto-merged with no human in the loop.", "context": null, "speaker": null, "speakerId": null, "speakerUrl": null, "speakerLevel": null, "role": null, "voice": "organization", "organization": "Spotify", "organizationId": "spotify", "organizationUrl": "https://the-ai-record.com/organizations/spotify", "aiVendor": false, "work": { "title": "Coding Is No Longer the Constraint: Scaling Developer Experience to Teams and Agents at Spotify", "type": "post", "date": "2026-06-03", "publisher": "Spotify engineering blog", "url": "https://engineering.atspotify.com/2026/6/code-with-claude-coding-is-no-longer-the-constraint" }, "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": [ "coding-agents", "autonomy-and-oversight", "ai-approves-code" ], "functions": [ "engineering" ], "figures": [], "url": "https://the-ai-record.com/passages/spotify-weve-merged-more-than-2-5-million-2026", "json": "https://the-ai-record.com/api/v1/passages/spotify-weve-merged-more-than-2-5-million-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." ] }