How This Ex-Meta L8 Engineer Ships 40 PRs a Day with AI Agents | Kun Chen

Kun is an ex-L8 principal engineer at Meta and Microsoft who now ships 40 PRs a day without manually reviewing code. In our episode, he walked through the free tools he built to make that possible: Lavish for visual planning in HTML artifacts, Treehouse for parallel agents, and No Mistakes for catching AI coding errors before they make it to production.

Kun and I talked about:

(00:00) Why he doesn't review code anymore

(01:04) Agentic engineering: Plan, code, validate

(06:22) Demo: Fixing an AI tutor screen with agents

(08:40) Demo: Why HTML is better than markdown for planning

(19:53) How to turn a rough idea into an AI-ready spec

(23:21) How Kun runs 20-30 agents in parallel

(32:04) No Mistakes: Kun's free AI code review tool

(45:19) What Kun checks before merging AI-written code

(50:18) How to get better at agentic engineering

Thanks to our sponsors:

Linear: The AI agent platform for modern teams https://linear.app/behind-the-craft

Wispr Flow: 4x faster than typing with your voice https://ref.wisprflow.ai/peteryang

Riverside: All-in-one AI studio for podcasts and video https://creators.riverside.com/PeterYang

📌 Get the takeaways: https://creatoreconomy.so/p/how-this-ex-meta-l8-engineer-ships-40-prs-a-day-with-ai-kun-chen

📌 Get my personal AI operating system with all my skills and prompts: https://www.behindthecraft.com/

Where to find Kun:

GitHub: https://github.com/kunchenguid

X: https://x.com/kunchenguid

Kun's free tools from the episode:

Lavish (HTML editor): https://github.com/kunchenguid/lavish-axi

Treehouse: https://github.com/kunchenguid/treehouse

No Mistakes (AI code review): https://github.com/kunchenguid/no-mistakes

Subscribe to this channel - more interviews coming soon!