When we required 100% correctness before every single commit, it caused major serialization and slowdowns of effective throughput. Even a single small error, like an API change or typo, would cause the whole system to grind to a halt.
Wilson LinResearcher, Cursor (author of the Towards self-driving codebases post) · Practitioner, 
Cursor (Anysphere)
Post: Towards self-driving codebases, Cursor (own site), February 5, 2026, at Throughput and tradeoffs: Commit correctness.
Wilson Lin, Researcher, Cursor (author of the Towards self-driving codebases post). Built and ran the agent harness and the browser research project the post describes; an insider.
Cursor (Anysphere) sells AI or agent tools or services, so it has a reason to publish flattering numbers about AI. The passage stays in the archive; read it with that in mind.
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, 2026-11-08).
Exact character match under the 'Commit correctness' heading, in Cursor's own post.
Wilson Lin (Cursor (Anysphere)), “Towards self-driving codebases”, Cursor (own site), 2026-02-05, at Throughput and tradeoffs: Commit correctness. https://cursor.com/blog/self-driving-codebases Archived at https://the-ai-record.com/passages/cursor-requiring-100-percent-correctness-every-commit-slowdown-2026
Errors arise then get fixed quickly. The error rate remains small and constant, perhaps rarely completely clean but steady and manageable, not exploding or deteriorating. This may indicate that the ideal efficient system accepts some error rate, but a final "green" branch is needed where an agent regularly takes snapshots and does a quick fixup pass before release.
Wilson LinResearcher, Cursor (author of the Towards self-driving codebases post) · Practitioner, Cursor (Anysphere)
Post: Towards self-driving codebases, Cursor (own site), February 5, 2026, at Throughput and tradeoffs: Commit correctness.
The system peaked at ~1,000 commits per hour across 10M tool calls over a period of one week.
Cursor (Anysphere)Published by the organization itself (post), no named author
Post: Towards self-driving codebases, Cursor (own site), February 5, 2026.
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.
Wilson LinResearcher, Cursor (author of the Towards self-driving codebases post) · Practitioner, Cursor (Anysphere)
Post: Towards self-driving codebases, Cursor (own site), February 5, 2026, at Optimizing prompts.
Locking also caused too much contention. 20 agents would slow to the throughput of 1-3 with most time spent waiting on locks.
Wilson LinResearcher, Cursor (author of the Towards self-driving codebases post) · Practitioner, Cursor (Anysphere)
Post: Towards self-driving codebases, Cursor (own site), February 5, 2026, at Self-coordination.
Workers pick up tasks and are solely responsible for driving them to completion. They're unaware of the larger system. They don't communicate with any other planners or workers. They work on their own copy of the repo, and when done, they write up a single handoff that the system submits to the planner that requested the task.
Wilson LinResearcher, Cursor (author of the Towards self-driving codebases post) · Practitioner, Cursor (Anysphere)
Post: Towards self-driving codebases, Cursor (own site), February 5, 2026, at The final system design.
Something wrong? Report a correction. JSON: /api/v1/passages/cursor-requiring-100-percent-correctness-every-commit-slowdown-2026.json