Quoting Jon Udell
- ID
- 2105
- Status
- summarized
- Published
- 29 Jun 2026, 5:57 AM
- Fetched
- 29 Jun 2026, 8:42 AM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Jun/28/jon-udell/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 8.0
- Created
- 29 Jun 2026, 8:48 AM
- Tags
- Audience
- developersvibe_coders
What happened
Simon Willison amplifies Jon Udell's call to reframe 'human in the loop' as 'agents in our loop,' arguing developers should invite AI agents into existing, reviewable workflows rather than ceding authority to black-box agentic processes that produce unreviewable outputs.
Why it matters
For developers and vibe coders building with AI agents, this directly shapes how you design agentic pipelines—keeping code review, testing, and ownership human-first prevents unmaintainable messes and keeps you in control.
Discussion angle
Ask the group: Have you ever had an AI agent spit out a massive PR you couldn't properly review? How do you practically enforce 'agents in our loop' with things like smaller, testable tasks or mandatory human sign-off gates?