Inside Figma’s PM OS: skills, agents, and Auto XP

Key moments

The parts the AI thinks are worth your time, chosen from the creator's chapters. Click to jump.

1. 2:04The origin story of Figma’s PM OSShows how the internal AI workflow started and why the team built it.
2. 10:28How the repo works: skills, hooks, and private sub-reposExplains the system design behind the shared PM toolkit.
3. 22:08AutoXP: an automated growth PMCovers an AI agent running experiments with one human checkpoint.
4. 26:58Building a real-time writing assistant with JevConcrete example of a daily-use AI assistant in product work.

Chapters

From the creator's chapter list. Click to jump.

1. 0:00Episode preview
2. 0:51Introduction to Ezra Mechaber
3. 2:04The origin story of Figma’s PM OS
4. 6:30PM OS demo: the “chief of staff” setup
5. 10:28How the repo works: skills, hooks, and private sub-repos
6. 12:00How the skills got built, roasted, and whittled down
7. 14:15Build artifact, FigJam MCP, and coaching skills
8. 17:33Transitioning from the terminal to a local web front end
9. 19:30Bug bashing with Codex
10. 22:08AutoXP: an automated growth PM
11. 26:26Claire’s Experiment Engine backstory
12. 26:58Building a real-time writing assistant with Jev
13. 33:15Lightning round and final thoughts

About this video

Ezra Mechaber is a growth product manager at Figma whose goal is to be “lazy in the right places.” When he joined Figma, he found almost no one outside engineering using AI to get real work done, so he and a couple of fellow PMs turned his personal Claude Code setup into PM OS, a shared repo of 31 skills that every PM at Figma now uses. In this episode, Ezra walks me through his favorite skills, how he bug bashes with Codex, AutoXP—an automated growth PM that found a huge win on its very first experiment—and a real-time writing assistant he built with Jev. *What you’ll learn:* 1. Why PM OS is