What a harness is and how to build one with Claude Agent SDK
About this episode
Claire Vo explains what an AI harness is and demonstrates how to build one using the Claude Agent SDK.
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. 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…
Sponsors
Bolt.new, Customer.io
More episodes of How I AI
- How the founder of Morning Brew built a Claude content machine that never runs out of ideas and never sounds like slop | Alex Lieberman
- This solo builder runs 24/7 local AI on his own hardware | Alex Finn
- GPT-5.6 Sol vs. Claude Fable: Why OpenAI’s new model crushes my benchmark
- How I run autonomous coding agents from my phone with OpenAI Symphony + Linear | Alessio Fanelli (Kernel Labs)
- Sonnet 5 review: I ran 64 generations to find out if it's worth it
- No Figma. No Jira. No docs. How Gusto built a new product line with Claude Code | Eddie Kim (CTO)
Explore listener stats, chart rankings, contacts and more on the How I AI podcast page.