scripod.com

No Figma. No Jira. No docs. How Gusto built a new product line with Claude Code | Eddie Kim (CTO)

How I AI

Jun 29
How I AI

How I AI

Jun 29

Shownote

Eddie Kim is the co-founder and CTO of the payroll and HR platform Gusto, which just crossed $1 billion in revenue and serves more than 500,000 small businesses. Recently he did something most CTOs don’t: he went back to writing code. With three other engineers and one designer, Eddie built Gusto Cofounder, a net-new AI product, from zero code to a tier-one launch in 10 weeks. He walks through how that team actually worked, why they threw out nearly every process, and how anyone can copy the approach. What you’ll learn: 1. The trash-can method: how to write, review, and delete a full PR as a product decision instead of a planning doc 2. The two-tool agent stack behind Gusto Cofounder 3. The exact “perma-Zoom” setup that replaced standups, retros, and Slack threads for 10 weeks 4. How a designer with no engineering background hit the 94th percentile for shipping code 5. The eval-first workflow Eddie uses to fix real customer bugs with Claude Code 6. How a non-technical leader can prototype an idea to win buy-in, then carry it all the way to production-quality code — Brought to you by: Magic Patterns [https://magicpatterns.com/howiai]—Prototypes that look like your product Jira Product Discovery [https://atlassian.com/howiai]—Prioritize with insights, build with confidence — In this episode, we cover: (00:00) Intro: five people, 10 weeks (02:38) The origins of Cofounder (08:32) Inside the 10-week build process (12:50) Building with no PMs (14:38) The “trash can” method (17:15) The stack architecture (19:10) Shipping to production from day one (22:03) How a designer became a top engineer (29:05) Demo: Cofounder over text and Slack (31:45) Demo: running a real payroll (36:26) Live coding with evals in Claude Code (39:39) Recap: prototype, small team, permission (43:17) Lightning round (48:44) Where to find Eddie and Cofounder — Tools referenced: • Gusto Cofounder (early access/waitlist): https://gusto.com/cofounder [https://gusto.com/cofounder] • Claude Code (Anthropic): https://claude.ai/code [https://claude.ai/code] • Cloudflare Workers: https://workers.cloudflare.com/ [https://workers.cloudflare.com/] • Vercel AI SDK: https://sdk.vercel.ai/ [https://sdk.vercel.ai/] • DX (engineering analytics): https://getdx.com/ [https://getdx.com/] • Wispr Flow (voice-to-text): https://wisprflow.ai [https://wisprflow.ai/] • OpenClaw: https://openclaw.ai/ [https://openclaw.ai/] — Other references: • Gusto (the main product, “Gusto Classic”): https://gusto.com [https://gusto.com/] • Mindbody (referenced as customer data source): https://www.mindbodyonline.com/ [https://www.mindbodyonline.com/] — Where to find Eddie Kim: LinkedIn: https://www.linkedin.com/in/edawerd/ [https://www.linkedin.com/in/edawerd/] — 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/] X: https://x.com/clairevo [https://x.com/clairevo] — Production and marketing by https://penname.co/ [https://penname.co/]. For inquiries about sponsoring the podcast, email jordan@penname.co.

Highlights

Gusto CTO Eddie Kim details how he and a tiny team of five built a new AI product, Gusto Cofounder, from scratch in just 10 weeks. They achieved this by discarding nearly all traditional engineering processes, including meetings, documentation, and project management tools, in favor of a radical, code-first approach.
00:00
Built in 10 weeks with 5 people, no meetings, no docs.
05:40
Long breaks often spark innovation.
08:33
Built in 10 weeks with no meetings, no tech specs, no Figma, no Jira.
12:51
Everyone acted as a PM.
14:38
Low cost of code makes discarding prototypes feasible
17:18
Building agents is not as intimidating as it seems
19:10
Ship a fake prototype, then chip away like marble.
22:04
Technical curiosity and team mentorship enable non-engineers to ship production code.
29:06
Gusto Cofounder integrates with existing data and supports multi-channel communication.
34:36
Act on ambitious ideas immediately rather than planning months ahead.
36:27
Write a failing eval, then fix the code to pass it
39:39
Keep the team small and skip the docs.
46:00
Hands-on coding reveals product insights

Chapters

Intro: five people, 10 weeks
00:00
The origins of Cofounder
02:38
Inside the 10-week build process
08:32
Building with no PMs
12:50
The “trash can” method
14:38
The stack architecture
17:15
Shipping to production from day one
19:10
How a designer became a top engineer
22:03
Demo: Cofounder over text and Slack
29:05
Demo: running a real payroll
31:45
Live coding with evals in Claude Code
36:26
Recap: prototype, small team, permission
39:39
Lightning round
43:17
Where to find Eddie and Cofounder
48:44

Transcript

Eddie Kim: We had no meetings, We had no tech specs. We had no Figma. We had no Jira board where we tracked stories or tracked work. We had nothing. We used Cloudflare Workers for the actual agent loop and Vercel AI SDK. That's it. Claire Vo: People get r...