What it does
An experiment in checking an agent's work before handing it to another agent, with Jev helping review the evidence.
Agent tooling
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
An experiment in checking an agent's work before handing it to another agent, with Jev helping review the evidence.
You can borrow this project's checklist rules if your team uses AI assistants for programming tasks. It sets up a step-by-step check to confirm that an assistant actually tested its work before passing the results to a person or another bot, keeping sloppy answers from slipping through unnoticed.
A programmer can review the sample files to adapt these guidelines into your existing assistant setup. Because this project is an experimental set of offline rules rather than a finished, ready-to-run program, your developer must write custom code to make it work with your live workflow.