Docket – Per-commit evidence records for agent-written code
Docket is a new tool designed to provide per-commit evidence records for code generated by AI agents. It captures the 'implementation journey' of an agent, allowing human reviewers to focus their attention on areas where evidence is lacking.
Why it matters
As AI-generated code becomes more prevalent, tools that ensure transparency and auditability in the development process are becoming essential for software engineering.
A per-commit evidence record for agent-written code.
Coding agents produce code faster than anyone can verify it. The reviewer receives a finished diff with no implementation journey: no record of what the agent tried first, what it verified, or which lines nobody ever looked at. The harness already emits that journey and then throws it away at commit time.
Docket captures it, folds it against the diff, and produces a per-hunk evidence record — so review attention lands where there is no evidence.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in