[Discussion] Do AI coding agents say “done” too early for you too?
Summary
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.
Similar Articles
What evidence should AI coding agents leave before saying “done”?
Discusses the need for AI coding agents to provide evidence of their work before marking tasks as complete, exploring verification strategies and best practices.
Giving an AI coding agent a deterministic "architecture linter" so it stops faking "done"
The article describes giving an AI coding agent a deterministic architecture linter that checks Event Storming diagrams for mechanical gaps and open questions, ensuring the agent doesn't fake completion.
How do you know when an AI coding agent is actually done?
The author built OpenPitStop, an open-source tool that independently checks and verifies the work of AI coding agents, demonstrated on a broken application, and invites discussion on how to trust AI changes.
@gwenshap: People who say: "I never review the code my AI agent writes" Do you mean: "I used to review it, but it was perfect ever…
The post questions why people skip reviewing AI-generated code, suggesting it could be due to full trust from past perfection or lowered standards for faster progress.
The worst coding agent failure is when it says “done” too early
The article highlights a common failure mode in coding agents where they report tasks as 'done' while leaving hidden issues like insufficient tests, missed edge cases, and introduced bugs, creating a trust problem for developers.