Researcher, Cursor (author of the Towards self-driving codebases post), Cursor (Anysphere).
Explore with your AI assistant
ChatGPT (opens in a new tab)Claude (opens in a new tab)Perplexity (opens in a new tab)Grok (opens in a new tab)
Opens a new chat with a prompt that points the assistant to this archive. What it writes is its own, not the archive's: check any quotation on its passage page before you rely on it. Or add the archive to your assistant as a connector: https://the-ai-record.com/mcp (how).
Byline on Cursor's post on its multi-agent harness; says the research project began as his personal side project.
Why their word counts: Built and ran the agent harness and the browser research project the post describes; an insider.
Profile from this source, checked 2026-11-07.
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.
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.
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.
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.
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.