# Checklist: an agent under control

AI Workshop · episode 4: Steering the agent
https://mihalkevich.com/en/workshop/steering

- [ ] For any task touching more than one file I asked for a plan first and read it
- [ ] The plan names the files to change and how the result will be verified
- [ ] Every step ends with a check: typecheck, a test, the page open in a browser
- [ ] Edits are targeted: file → spot → change → what not to touch
- [ ] Before a risky step there's a commit or checkpoint to return to
- [ ] Three failed attempts in a row — stop: narrow the task, add context or take the step myself

## Harness in this episode

Steering is the manual layer of the harness: a plan and a check after each step catch mistakes while they cost minutes, not days.

## Official documentation

- [Claude Code — common workflows](https://code.claude.com/docs/en/common-workflows)
- [Claude Code — best practices](https://code.claude.com/docs/en/best-practices)
- [Claude Code — checkpointing](https://code.claude.com/docs/en/checkpointing)

— mihalkevich school