Harness Engineering
The same AI works well sometimes but repeats the same mistake elsewhere. What can I change besides the model?
- A static screenshot looks plausible
- Clicking Play does nothing
- The agent still reports “done”
playwright.click("Play")
✗ no state change
functionality: 1 / 51Independent evaluator2Playwright interaction3Screenshots + four criteriaFEEDBACK TO THE NEXT TURNThe evaluator returns the failed click, screenshot, and critique to the generator for another pass.
The run ends only after the live page works and the evaluator’s check passes.
A screenshot proves that a page can render. An evaluator that actually operates it proves whether the experience works.
When a failure repeats, improve the environment that exposes, records, and corrects it—not just the prompt.
The frontend renders but does not work: An independent evaluator operates the live page, captures screenshots, and checks the complete flow. Failed actions and specific critique return to the next turn instead of letting the generator grade itself.
A long task forgets between sessions: A feature list, progress file, startup script, and Git commits keep state in the project. The next session reads them, runs a basic check, and continues one unfinished item.
A large repository drifts: A short project map provides the entry point, structured docs hold the details, and custom lint and structural tests turn architecture rules into failures with a remediation path.
You can say this to an AI Agent
Do not rebuild the feature yet. Describe the repeated failure as: observable evidence → missing environmental support → file, tool, or check to add → how the result returns to the next turn → what counts as passing. Propose the smallest harness first, then implement it and verify it with real evidence.
Select page elements for precise AI edits
Click a button, text, or card, note the change, then copy its exact location to AI.
Open Selector Pro website↗