Verification Loops: Never Trust an Unrun Edit
Harness Engineering
60-100 minutes0/4 steps0%
Step 1 of 4
Verify at the write boundary
The cheapest catch-point is the moment of the edit.
First time here? Paste the Context Pack first so the AI understands your project - open it from the header above.
Prompt Capsule
Implement write-time verification. On every file write or edit: run the appropriate fast check for the file type (python: compile/ruff; js/ts: esbuild parse or tsc; json/yaml: parse) within a second-scale budget; on failure, revert the write (or never apply it - validate a staged copy) and return the exact error with line numbers to the model as the tool result; on success, return a confirmation including the check that ran. Wire this into the edit tool itself so no write path skips it. Test with a deliberately broken edit and confirm the revert-and-teach cycle produces a corrected second attempt.
Paste into EmergentFull Build: complete implementation prompt with explicit requirements
Quick is short. Full Build is recommended for most steps. Strict forces real logic when the AI keeps faking output.
Actual change check
Expected after this step
Every write checked, failures reverted with teaching errors.
Should NOT happen
- An existing feature broke
- A button only logs to console
- Data disappears after refresh
- Errors fail silently with no visible state
This is what should exist before you continue. If reality does not match, do not move on.
Track what changed, failed, or needs follow-up. Notes export with the flow.
Pass the Verify Gate to complete this step