What a harness is and how to build one with Claude Agent SDK
Episode
24 min
Read time
2 min
Topics
Leadership, Artificial Intelligence, Software Development
AI-Generated Summary
Key Takeaways
- ✓Harness definition: A harness is simply code wrapped around an AI agent to make it more effective for a specific use case. It requires three components: specific context, specific actions, and specific outcomes. No AI is required inside the harness itself — the wrapper can be entirely deterministic logic surrounding an AI call.
- ✓When to build a harness: Build one when the same workflow requires the same setup and the same outputs repeatedly — bug triage, PR preparation, support escalation, migration management, or structured research. The trigger is any workflow combining deterministic steps with AI reasoning where consistency and repeatability matter more than open-ended flexibility.
- ✓Opinionated tool adapters over generic MCPs: Rather than giving the agent broad MCP access to Sentry or Linear, build narrow adapters that call only the specific API fields relevant to the task. This prevents the agent from wandering through irrelevant data and produces faster, more precise outputs without requiring additional prompting each run.
- ✓Encode permissions and outcomes in code, not prompts: Harnesses allow hard-coded tool policies — for example, an investigate-only mode that blocks file writes entirely. Desired artifacts like Linear tickets, HTML reports, and bug summaries are defined structurally in the harness, so they generate consistently without relying on the agent to remember instructions from a skill or system prompt.
- ✓Build with an agent SDK, prompt very specifically: When using Claude Agent SDK or OpenAI's equivalent to generate the harness itself, models default to overly deterministic outputs and resist embedding AI logic. Counteract this by specifying the exact workflow steps, tool list, custom prompt locations, and artifact structure before generating — vague prompts produce scaffolding without agentic behavior.
What It Covers
Host Christina Cacioppo demystifies the term "harness" by building a live Sentry bug-triage harness using the Claude Agent SDK, connecting it to Sentry, Vercel, Linear, and GitHub, and demonstrating how structured code around AI agents produces more consistent, controlled outcomes than general-purpose coding tools alone.
Key Questions Answered
- •Harness definition: A harness is simply code wrapped around an AI agent to make it more effective for a specific use case. It requires three components: specific context, specific actions, and specific outcomes. No AI is required inside the harness itself — the wrapper can be entirely deterministic logic surrounding an AI call.
- •When to build a harness: Build one when the same workflow requires the same setup and the same outputs repeatedly — bug triage, PR preparation, support escalation, migration management, or structured research. The trigger is any workflow combining deterministic steps with AI reasoning where consistency and repeatability matter more than open-ended flexibility.
- •Opinionated tool adapters over generic MCPs: Rather than giving the agent broad MCP access to Sentry or Linear, build narrow adapters that call only the specific API fields relevant to the task. This prevents the agent from wandering through irrelevant data and produces faster, more precise outputs without requiring additional prompting each run.
- •Encode permissions and outcomes in code, not prompts: Harnesses allow hard-coded tool policies — for example, an investigate-only mode that blocks file writes entirely. Desired artifacts like Linear tickets, HTML reports, and bug summaries are defined structurally in the harness, so they generate consistently without relying on the agent to remember instructions from a skill or system prompt.
- •Build with an agent SDK, prompt very specifically: When using Claude Agent SDK or OpenAI's equivalent to generate the harness itself, models default to overly deterministic outputs and resist embedding AI logic. Counteract this by specifying the exact workflow steps, tool list, custom prompt locations, and artifact structure before generating — vague prompts produce scaffolding without agentic behavior.
Notable Moment
When building the harness using both Claude Code and Codex simultaneously, both models repeatedly resisted adding AI logic and kept producing fully deterministic code. Codex ultimately built the better harness — but implemented it using the Claude Agent SDK, spanning two competing AI ecosystems in a single project.
Episode Transcript
A harness is some code around an AI agent that makes it more effective. Why we've seen people build these specific use case harnesses is sometimes with a specific job, you just wanna micromanage a little bit. You just wanna be more prescriptive about how that job gets done. I'm gonna show you how it works, and then we will talk about how I built it. So the inner face I built for my harness is a terminal UI. The harness core is run on Claude agent SDK, and then it's connected to Real Tools. So it's connected to Sentry, Vercel, and then it's connected to Linear and GitHub in terms of getting tasks done. I think we all have done good work, but then now I've realized that these agents can help us solve very, very specific problems by constraining that work. It's really, like, changed my mind about how work gets done. Everybody's saying it's not the model, it's the harness. But you know what not everybody is saying? What is a harness? In today's How I AI episode, I am going to demystify the idea of a harness, write my own harness, and show you how you can do the same, and explain to you why a custom harness makes sense and could be better than using quad code or codex alone. Let's get to it. This episode is brought to you by bolt.new, the AI app builder for people who have ideas and want to ship them. Most AI tools spit out code that looks great in a demo and falls apart the second you try to do anything real with it, or they lock you into their own platform with no real way out. Bolt is different. You describe what you wanna build, a startup MVP, a landing page, an internal tool, a side project, and Bolt generates production ready code in minutes. Connect Stripe or any other MCP, hook up your domain, and deploy it live. Founders are using Bolt to build businesses doing real revenue. Product managers are shipping prototypes their teams actually use. Designers and marketers are launching campaigns without waiting in line. Anyone can build. Engineering can ship. Everyone wins. You just need an idea and a weekend. Check it out at bolt.new/howiai. Before I get into how to build a harness, let's talk about what a harness is, and I am going to make it as simple as I can for all of you. A harness is some code around an AI agent. Yes. You heard it here first. A harness is just code around an AI agent that makes it more effective. Can that code have AI in it? Sure. Does that code have to have AI in it? Not necessarily. What is the goal of a harness? To make the AI better. It is so simple, and I feel like the way that people have been talking about this have made it such a mystery that I wanted …
Get the full transcript (4,278 words) + summary by email — free
One-time email with the complete transcript and AI summary of this episode. No account needed.
One email, no spam. We’ll also show you what SignalCast does.
You just read a 3-minute summary of a 21-minute episode.
Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
More from How I AI
I tested Grok Bot, Grok 4.6, and Cursor Origin - here’s my honest take
Aug 18 · 27 min
Stacking Benjamins
What to Build After You Hit "The Retirement Number" (SB1817)
Mar 18
More from How I AI
How a solo founder used Codex and ChatGPT to launch a fashion brand without engineers | Yana Welinder
Aug 17 · 32 min
Investing for Beginners
From Navigating Debt to Long-Term Wealth with Stephen Morris
Mar 10
Books, tools, and gear mentioned in this episode
SignalCast may earn commission on purchases via these links.
Tools
- VercelRecommended
“connecting it to Sentry, Vercel, Linear, and GitHub”
“💼 SPONSORS ["Customer.io", "url": "https://customer.io/howiai"]”
- Claude Agent SDKRecommended
by Anthropic
“Host Christina Cacioppo demystifies the term "harness" by building a live Sentry bug-triage harness using the Claude Agent SDK, connecting it to Sentry, Vercel, Linear, and GitHub”
- SentryRecommended
“building a live Sentry bug-triage harness using the Claude Agent SDK, connecting it to Sentry, Vercel, Linear, and GitHub”
- LinearRecommended
“connecting it to Sentry, Vercel, Linear, and GitHub”
“💼 SPONSORS ["Bolt", "url": "https://bolt.new/howiai"]”
More from How I AI
We summarize every new episode. Want them in your inbox?
I tested Grok Bot, Grok 4.6, and Cursor Origin - here’s my honest take
How a solo founder used Codex and ChatGPT to launch a fashion brand without engineers | Yana Welinder
Claude Code for normal people: skills, voice mode, and how to collaborate with AI
Build an AI code review bot in 30 minutes with Vercel Eve
ChatGPT Codex Voice + browser + Sites: an expert’s AI workflow | Nick Baumann (OpenAI)
Similar Episodes
Related episodes from other podcasts
Stacking Benjamins
Mar 18
What to Build After You Hit "The Retirement Number" (SB1817)
Investing for Beginners
Mar 10
From Navigating Debt to Long-Term Wealth with Stephen Morris
Mind Pump: Raw Fitness Truth
Mar 5
2807: Secrets To Extreme Butt Growth
Mind Pump: Raw Fitness Truth
Mar 4
2806: The BEST form of Strength Training for Women is Powerlifting. Challenge Me!
Mind Pump: Raw Fitness Truth
Feb 16
2795: The 8 Greatest Exercises for Fat Loss and Muscle Gain
Explore Related Topics
This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.
Read this week's AI & Machine Learning Podcast Insights — cross-podcast analysis updated weekly.
You're clearly into How I AI.
Every Monday, we deliver AI summaries of the latest episodes from How I AI and 192+ other podcasts. Free for one show.
Start My Monday DigestNo credit card · Unsubscribe anytime