Everybody is saying, “It’s not the model, it’s the harness,” but almost nobody stops to explain what a harness actually is. So I did. I built one live on the show: a Sentry bug-debugging harness for my company ChatPRD, using the Claude Agent SDK, a custom terminal UI built with the Ink library, and opinionated adapters for Sentry, Linear, GitHub, and Vercel. The harness handles evidence gathering, root-cause analysis, and follow-up artifact creation, all without me needing to type “dear agent, please fix this bug” ever again. I also walk through the architecture, share the code structure, and give you the exact process I used so you can build your own harness for any repetitive, structured workflow in your business.
Listen or watch on YouTube, Spotify, or Apple Podcasts
What you’ll learn:
What a harness actually is
When to build a harness versus when to stick with a general-purpose tool like Claude Code or Codex
How to encode specific permissions into a harness
The three components every harness needs
How I used GPT-5.5 and Claude Opus to build the harness code itself (and where they both initially resisted)
How to structure the artifacts your harness produces so the whole team can use the output
Brought to you by:
** Bolt.new**—Turn your idea into a real product
** Customer.io**—Build customer engagement campaigns from a single prompt
In this episode, we cover:
([00:00](https://www.youtube.com/watch?v=ofS-4RRw9zw)) What is an AI harness?
([03:19](https://www.youtube.com/watch?v=ofS-4RRw9zw&t=199s)) When to build a harness
([04:33](https://www.youtube.com/watch?v=ofS-4RRw9zw&t=273s)) Why Claire picked bug triage
([06:00](https://www.youtube.com/watch?v=ofS-4RRw9zw&t=360s)) Why not just use Claude Code?
([07:48](https://www.youtube.com/watch?v=ofS-4RRw9zw&t=468s)) Demo: The custom harness interface
([11:04](https://www.youtube.com/watch?v=ofS-4RRw9zw&t=664s)) Architecture: runs, tasks, tools, and artifacts
([13:44](https://www.youtube.com/watch?v=ofS-4RRw9zw&t=824s)) Building it with Codex and Claude
([15:08](https://www.youtube.com/watch?v=ofS-4RRw9zw&t=908s)) Code map and file layout
([16:51](https://www.youtube.com/watch?v=ofS-4RRw9zw&t=1011s)) A look at the code
([19:18](https://www.youtube.com/watch?v=ofS-4RRw9zw&t=1158s)) The live investigation result
([21:01](https://www.youtube.com/watch?v=ofS-4RRw9zw&t=1261s)) How to build your own harness
Tools referenced:
• Claude Agent SDK (Anthropic): [https://code.claude.com/docs/en/agent-sdk/overview](https://code.claude.com/docs/en/agent-sdk/overview)
• Claude Sonnet 4.6 (model used inside the harness): [https://www.anthropic.com/news/claude-sonnet-4-6](https://www.anthropic.com/news/claude-sonnet-4-6)
• Claude Opus (used to build the harness): [https://www.anthropic.com/claude/opus](https://www.anthropic.com/claude/opus)
• GPT-5.5 (Codex, used to build the harness): [https://openai.com/index/introducing-gpt-5-5/](https://openai.com/index/introducing-gpt-5-5/)
• Ink (terminal UI library for Node.js): [https://github.com/vadimdemedes/ink](https://github.com/vadimdemedes/ink)
• Sentry (error monitoring): [https://sentry.io/](https://sentry.io/)
• Linear (project management): [https://linear.app/](https://linear.app/)
• GitHub: [https://github.com/](https://github.com/)
• Vercel: [https://vercel.com/](https://vercel.com/)
Where to find Claire Vo:
ChatPRD: [https://www.chatprd.ai/](https://www.chatprd.ai/)
Website: [https://clairevo.com/](https://clairevo.com/)
LinkedIn: [https://www.linkedin.com/in/clairevo/](https://www.linkedin.com/in/clairevo/)
Production and marketing by [https://penname.co/](https://penname.co/). For inquiries about sponsoring the podcast, email [[email protected]](/cdn-cgi/l/email-protection).