Lauren Tan and Roman Ugarte join this episode of the Lightcone to go in deep on how they built and deployed Grok Bot. They explain how automated tests and codebase guardrails help agents check their own work, why bots should earn broader access over time, and why faster and cheaper execution makes direction and clear goal setting even more important.
Apply to Y Combinator: https://www.ycombinator.com/apply
Work at a startup: https://www.ycombinator.com/jobs
Try Grok Bot here: https://bit.ly/4tj7bpv
Chapters:
00:00 — Intro
03:36 — Giving Bots Real Jobs
06:49 — One Bot or a Team of Specialists
10:39 — Sharing Bots Across the Company
14:46 — Identity and Permissions for AI Coworkers
18:37 — Bot-to-Bot Collaboration and Trust
22:35 — The Workflow Behind 4,000 PRs a Month
26:00 — Teaching Agents to Write Code You Trust
29:01 — Building a Personal Software Factory
33:44 — The Future of AI Coworkers
36:47 — Rethinking the AI-Native Company
40:13 — Teaching Agents to Check Their Own Work
43:56 — How Much Code Review Is Enough?
47:33 — Codebase Guardrails That Save Tokens
52:20 — When Product Judgment Becomes the Bottleneck
56:29 — From Finance to AI Engineering + Outro
