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.
Joey BatesDeveloper Enablement · Practitioner, 
Customer.io
Post: How we taught AI to approve pull requests (not just review them), Customer.io, November 10, 2025, at Results: Safety validation.
Joey Bates, Developer Enablement. Wrote the post about the team’s own AI review system, so the figures come from the team that built and runs it.
Checked against the source by a first reader, then confirmed independently by a second reader who fetched the source without seeing the first reader's notes (Independent review agent (Claude Sonnet), blind second pass from passage text and citation only, no repository access, 2026-11-04).
Exact match of the multi-sentence passage in the Results section. Byline Joey Bates.
Joey Bates (Customer.io), “How we taught AI to approve pull requests (not just review them)”, Customer.io, 2025-11-10, at Results: Safety validation. https://customer.io/learn/how-we-work/how-we-taught-ai-to-approve-pull-requests Archived at https://the-ai-record.com/passages/customer-io-high-risk-prs-flagged-human-review-took-day-2025
The AI is approving over 60% of all PRs. For those PRs, engineers get feedback in minutes, not hours.
Joey BatesDeveloper Enablement · Practitioner, Customer.io
Post: How we taught AI to approve pull requests (not just review them), Customer.io, November 10, 2025, at Results: Speed and cognitive relief.
For PRs that got AI approval, merge time dropped from 3.5 hours to 33 minutes. That's 6.4x faster.
Joey BatesDeveloper Enablement · Practitioner, Customer.io
Post: How we taught AI to approve pull requests (not just review them), Customer.io, November 10, 2025, at Results: Speed and cognitive relief.
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.
Joey BatesDeveloper Enablement · Practitioner, Customer.io
Post: How we taught AI to approve pull requests (not just review them), Customer.io, November 10, 2025, at Problem: The cognitive weight of waiting.
Some changes are beyond automation: architectural decisions, complex trade-offs, and organizational implications. The system recognizes these boundaries and escalates.
Joey BatesDeveloper Enablement · Practitioner, Customer.io
Post: How we taught AI to approve pull requests (not just review them), Customer.io, November 10, 2025, at Lessons learned: Building systems engineers trust.
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.
Joey BatesDeveloper Enablement · Practitioner, Customer.io
Post: How we taught AI to approve pull requests (not just review them), Customer.io, November 10, 2025, at Article summary.
Something wrong? Report a correction. JSON: /api/v1/passages/customer-io-high-risk-prs-flagged-human-review-took-day-2025.json