Overview
Use this progressive-autonomy workflow:
- Define change classes. Separate high-risk changes from low-risk or behavior-preserving changes.
- Establish evidence requirements. Decide which tests, checks, demonstrations, and review results
are needed for each class.
- Automate the preparation. Let agents explore, implement, run checks, and assemble a review
package before human attention is requested.
- Move the checkpoint gradually. Keep human approval where risk or uncertainty remains, and remove
or delay checkpoints only after the system has produced consistent evidence.
- Audit the classifier. Regularly inspect a sample of changes the system considered safe enough to
approve automatically.
- Improve review presentation. Use summaries, demonstrations, and walkthroughs to help the human
understand the behavioral effect quickly.
- Investigate every meaningful miss. Ask why the issue reached this point, which control should
have caught it, and what change would prevent recurrence.
- Add recurring checks when appropriate. A daily security review can inspect a different part of
the repository each time. A relatively simple model may produce useful results when the harness directs it to the right place with the right purpose.
- Feed findings back into the system. Update tests, procedures, task templates, review rules, or
code structure.
The resulting loop is not an instruction to run an agent endlessly. It is an engineering feedback loop: observe output, detect a failure, identify the process weakness, change the system, and evaluate the new behavior.