AI Workshop
Episode 10 of 10Upcoming
Viewer project review
Season finale: we take real viewer projects and fix them live — setup, prompts, harness.
The link arrives by email an hour before the stream
Sign up — a day before we'll send a reminder with the episode plan, and an hour before the start the stream link. The player appears on this page 15 minutes before the start.
What we'll show
- Two or three viewer projects: the setup, CLAUDE.md, permissions, checks
- Where the agent stumbles and why — from logs and diffs
- Targeted fixes live: a prompt, context, a hook, a test
- What's missing for a minimal harness
- Season wrap-up and what's next
What you take away
A review of your project (if you send one) and a list of concrete fixes.
Project self-check
- A newcomer (or an agent) runs the project from CLAUDE.md without questions
- The agent knows how to verify its work, and does
- Secrets aren't in the repo, the agent's permissions are minimal
- Tasks follow the template: goal, context, constraints, definition of done
- There's at least one automated harness layer: a hook, a test or an eval set
- You understand every line you ship to production
Harness in this episode
The final review tests the harness on someone else's project: which layers exist and which to add.
The full harness episodeWhat to have ready
- Want a review? Reply to the reminder email with a repo link or a description