GPT-6 SOL + Jev self-improving coding agent prompt
A copy-ready prompt template where GPT-6 SOL diagnoses a recurring failure and proposes a patch, Jev ranks the next step, tests verify the fix, and verified fixes are saved as project memory.
GPT-6 SOL + JEV: THE SELF-IMPROVING CODING AGENT PROMPT Give this to your AI Agent when the same failure keeps coming back: { "goal": "Turn one recurring coding failure into a verified fix and a reusable project lesson.", "inspect": ["repo", "tests", "run logs", "available tools", "Jev interface"], "workflow": [ "Find a repeated error, reproduce it, and record a baseline.", "GPT-6 SOL: diagnose the cause, propose one focused patch, and write a regression test.", "Jev: rank valid next steps. Code: run tests and record the results.", "Compare the patch with the baseline. Reject regressions and bound retries.", "Save the root cause, fix, and test evidence only after verification." ], "return": ["reproduction", "patch", "test results", "before/after metrics", "project lesson"], "rules": ["Use only granted tools.", "Confirm Jev access before calling it.", "Never claim a test passed without evidence."] } GPT-6 SOL investigates the cause and proposes a patch → Jev chooses the next bounded step → code runs the tests → verified fixes become project memory. The next run starts with a regression test and a record of what worked. Fail → fix → verify → remember Save this for your next build ↓
This post quotes another post: “Breaking Jev's decision layer into a 10-step agent blueprint”