No Figma. No Jira. No docs. How Gusto built a new product line with Claude Code | Eddie Kim (CTO)
Episode
51 min
Read time
2 min
Topics
Startups, Fundraising & VC, Leadership
AI-Generated Summary
Key Takeaways
- ✓Zero-documentation development: Eliminate tech specs, Figmas, Jira boards, and stand-ups for zero-to-one builds. Gusto's five-person team operated from a single whiteboard photo for ten weeks. The only structured process was a 24/7 open Zoom room where engineers dropped in to share screens, discuss features, and conduct code reviews in real time.
- ✓Trash-can engineering method: Treat code as disposable by opening real, human-ready pull requests and then closing them if the feature fails a group discussion. With AI-assisted coding, rebuilding from a v2 branch from scratch is faster than refactoring. This removes emotional attachment to code and accelerates product-shape decisions without a product manager.
- ✓Minimal agent stack: Build AI agent loops with two tools only — Cloudflare Workers for the agent runtime and Vercel AI SDK for model flexibility. No third-party memory or planning harnesses are needed. Memory is simply a tool that writes to a database column. This stack removes complexity and lets small teams ship production-grade agents quickly.
- ✓Non-engineer PR throughput: Gusto's designer, Katie, ranked in the 94th percentile for PR throughput across the entire 1,000-person R&D organization. She achieved this by pairing with engineers who reviewed her Claude-generated code, gave prompting feedback, and helped her develop taste for code quality — demonstrating that design-to-production contribution is replicable with deliberate mentorship.
- ✓Eval-driven bug fixing: When addressing customer-reported issues, write a failing eval first to reproduce the problem, then prompt Claude Code with a GitHub issue link to generate a fix, and confirm the solution by verifying the eval passes without breaking the existing eval suite. This replaces traditional debugging and produces a reviewable pull request automatically.
What It Covers
Gusto CTO Eddie Kim describes how four engineers and one designer built Gusto Cofounder, a new AI-powered product line, in ten weeks with zero meetings, no Figma files, no Jira board, no tech specs, and no dedicated product manager — using only Claude Code and a permanent Zoom room.
Key Questions Answered
- •Zero-documentation development: Eliminate tech specs, Figmas, Jira boards, and stand-ups for zero-to-one builds. Gusto's five-person team operated from a single whiteboard photo for ten weeks. The only structured process was a 24/7 open Zoom room where engineers dropped in to share screens, discuss features, and conduct code reviews in real time.
- •Trash-can engineering method: Treat code as disposable by opening real, human-ready pull requests and then closing them if the feature fails a group discussion. With AI-assisted coding, rebuilding from a v2 branch from scratch is faster than refactoring. This removes emotional attachment to code and accelerates product-shape decisions without a product manager.
- •Minimal agent stack: Build AI agent loops with two tools only — Cloudflare Workers for the agent runtime and Vercel AI SDK for model flexibility. No third-party memory or planning harnesses are needed. Memory is simply a tool that writes to a database column. This stack removes complexity and lets small teams ship production-grade agents quickly.
- •Non-engineer PR throughput: Gusto's designer, Katie, ranked in the 94th percentile for PR throughput across the entire 1,000-person R&D organization. She achieved this by pairing with engineers who reviewed her Claude-generated code, gave prompting feedback, and helped her develop taste for code quality — demonstrating that design-to-production contribution is replicable with deliberate mentorship.
- •Eval-driven bug fixing: When addressing customer-reported issues, write a failing eval first to reproduce the problem, then prompt Claude Code with a GitHub issue link to generate a fix, and confirm the solution by verifying the eval passes without breaking the existing eval suite. This replaces traditional debugging and produces a reviewable pull request automatically.
Notable Moment
During a five-hour airport layover after missing a connecting flight in London, Kim opened his laptop and prototype-built what became Gusto Cofounder entirely in Claude Code. By the time he landed in San Francisco, the core product concept was functional enough to pitch to engineers the following week.
Episode Transcript
We had no meetings. We had no tech specs. We had no Figmas. We had no Jira board where we tracked stories or tracked work. We had nothing. We used Cloudflare Worker for the actual agent loop and Vercel AI SDK. That's it. People get really intimidated by the idea of building an agent, and I'm like, literally, it's an agent SDK running somewhere in the cloud. And if you use AI SDK, you get to switch your model. That's it. It can look up files. It can have tools. It's really not that scary and complicated. Co founder was primarily built by five, How did you all make those precious decisions that only genius product managers can make about in or out of scope, decisions that only genius product managers can make about in or out of scope, will this matter? We would build features, and we'd just have a discussion. Like, does this make sense to have or not? If it is, then it would get code reviewed right then and there. And if not, we would just delete it. I call this the the trash can method of software engineering right now where you can actually trash all the code, start like a slash v two branch, and rebuild it from scratch. And it's totally reasonable to do because the cost of the code is so low. Welcome back to How I AI. I'm Claire Vaux, product leader and AI obsessive, here on a mission to help you build better with these new tools. Today, I have Eddie Kim, CTO and cofounder of Gusto, and he's gonna show us how he, three engineers, and one designer completely rebuilt their app in just ten weeks. This is not a small company, and yet they're shipping like they're a start up. Let's get to it. This episode is brought to you by Magic Patterns. Today's engineers use cursor and clawed code to shift features in hours that used to take weeks. If you're a designer or PM, you've probably felt a shift too. The pressure to move faster, validate sooner, and keep up with the team that's operating at a completely different speed. You've already tried AI prototyping tools to close that gap. But if your prototypes don't look like your actual product, it doesn't matter how fast you can build. You still end up redrawing it by hand. Magic patterns takes your product team from idea to production and works from your real design system. When you build a prototype, what you get back actually looks like your product. You'll validate faster, get alignment sooner, and when it's time to build, engineers can connect your prototype to cursor or cloud code with the MagicPatterns MCP to pick up where you left off. Your eng team has their AI advantage. Make MagicPatterns yours. Try it today at magicpatterns.com/howiai. Eddie, thank you for joining How iai. I'm so excited you reached out to chat because one of my favorite themes …
Get the full transcript (9,893 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 48-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
Claude Code for normal people: skills, voice mode, and how to collaborate with AI
Aug 10 · 43 min
Software Engineering Daily
Unlocking the Data Layer for Agentic AI with Simba Khadder
Apr 21
More from How I AI
Build an AI code review bot in 30 minutes with Vercel Eve
Aug 5 · 24 min
The Prof G Pod
The New Playbook for Resisting Authoritarianism — with Julia Angwin & Ami Fields-Meyer
Jul 16
Books, tools, and gear mentioned in this episode
SignalCast may earn commission on purchases via these links. As an Amazon Associate, SignalCast earns from qualifying purchases.
Tools
- Claude CodeRecommended
by Anthropic
“built Gusto Cofounder, a new AI-powered product line, in ten weeks with zero meetings, no Figma files, no Jira board, no tech specs, and no dedicated product manager — using only Claude Code and a permanent Zoom room.”
- Cloudflare WorkersRecommended
by Cloudflare
“Build AI agent loops with two tools only — Cloudflare Workers for the agent runtime and Vercel AI SDK for model flexibility.”
- Vercel AI SDKRecommended
by Vercel
“Build AI agent loops with two tools only — Cloudflare Workers for the agent runtime and Vercel AI SDK for model flexibility.”
by Figma
“built Gusto Cofounder, a new AI-powered product line, in ten weeks with zero meetings, no Figma files, no Jira board”
by Atlassian
“built Gusto Cofounder, a new AI-powered product line, in ten weeks with zero meetings, no Figma files, no Jira board, no tech specs”
Products
by Gusto
“Gusto CTO Eddie Kim describes how four engineers and one designer built Gusto Cofounder, a new AI-powered product line, in ten weeks with zero meetings, no Figma files, no Jira board, no tech specs, and no dedicated product manager.”
More from How I AI
We summarize every new episode. Want them in your inbox?
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)
From zero coding background to hardware hacker: How Cursor + a Raspberry Pi makes AI fun
Claude Opus 5 review: this model is brilliant (but annoying)
Similar Episodes
Related episodes from other podcasts
Software Engineering Daily
Apr 21
Unlocking the Data Layer for Agentic AI with Simba Khadder
The Prof G Pod
Jul 16
The New Playbook for Resisting Authoritarianism — with Julia Angwin & Ami Fields-Meyer
How I Built This
Jul 13
Sun Bum: Tom Rinks. The Secrets of a Master Brand Builder (2023)
10% Happier with Dan Harris
Jul 8
How To Communicate Effectively With Difficult People: When to Tell the Truth, When to Push Back, and Why Kindness Isn't the Same as Being Nice | Sharon Salzberg
Deep Questions with Cal Newport
Jul 6
Should I Turn Off the Internet? (Lessons From a Family That Did) | Monday Advice
Explore Related Topics
This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.
Read this week's Startups & Product 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