Review a feature and pass the findings to an engineer
One developer had an agent inspect a feature for problems, then handed the issue list to an engineer whose agent fixed most of them.
- What they did
- Dare Obasanjo asked an AI agent to examine a feature and write down every problem it could spot. He then passed that list to an engineer. The engineer used their own agent to work through the items, and the follow-up arrived as an automated reply.
- How it went
- The reply reported that most of the issues had been handled. It did not say how many problems were found or which ones still needed work.
- Tips
- Have the agent separate each issue clearly so another person can pick them up easily. Ask it to pause before any sending, filing, or other irreversible step.
Try it yourself with Codex
Inspect the [feature name] in [repo or app] and make a complete list of issues you find, including bugs, edge cases, confusing UX, and missing tests. For each item, give a short title, what you saw, and a suggested fix, and order the list by seriousness. After you finish, stop and show me the full list for approval before you file anything in [issue tracker] or send it to [engineer name].
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Run coding agents in parallel with tmux and Markdown specs
Manuel Schipper uses separate tmux panes and numbered Markdown specs to keep several coding agents moving at once.
Check upgrade risks before you ship
A ReAct agent reviewed dependency data for a planned cloud upgrade and blocked it when it found an incompatible SDK version.
Deploy a project and register a domain from one agent flow
A custom agent can set up a Cloudflare account, buy a domain, and ship an app with only brief approval steps.
Build a staged agent pipeline for PRs
Create a multi-step system that assigns issues, tests changes, and leaves the final merge to a person.
Review Linux kernel patches before they land
Google’s Sashiko scans Linux kernel submissions and flags bugs that human reviewers missed.
Create a CLI coding agent from a Python LLM base
Claude Code turned Simon Willison’s Python LLM template into a working CLI coding agent from two prompts.