What evidence should AI coding agents leave before saying “done”?
Summary
Discusses the need for AI coding agents to provide evidence of their work before marking tasks as complete, exploring verification strategies and best practices.
Similar Articles
[Discussion] Do AI coding agents say “done” too early for you too?
Discussion about AI coding agents claiming completion prematurely, skipping checks, and making messy changes. The author is testing a system with planning and review gates to improve AI-coding workflows.
Outside verification has been the missing piece in my coding-agent runs
The author notes that external verification is a crucial missing component in effectively using AI coding agents.
AI coding agent output verification in 2026: read the diff, vibe check it, merge
A reflection on current practices for verifying AI coding agent output, noting that developers often skim diffs and merge without fully auditing the agent's session activity, raising concerns about code review culture in the age of AI.
@nykdotdev: Most agents are allowed to define "done" after they finish the work. That is backwards. Write the completion contract b…
Advises that AI agents should have completion contracts defined before starting work, specifying required outcomes, forbidden outcomes, evidence, and a completion rule, to separate convincing answers from completed tasks.
Building an evidence layer for AI agents that create software
The author introduces Flows, an execution and verification layer for software-building AI agents that requires proof before marking tasks complete, with a successful test on a real multi-module application.