Ship a product in 72 hours with a bot team
Three SpaceX engineers used a Grok Bot team to go from an empty repo to a product with 433 PRs, with agents reproducing bugs and merging autonomously except for human gates on migrations and deploys.
Done withGrok Bot
- What they did
- Three SpaceX engineers ran one chief-of-staff bot that spawned specialist bots, each limited to a single job description. Bots earned write access only after drafting changes first, then reproduced bugs, attached video proof, and opened PRs. They merged autonomously except at the four human gates on migrations, deploys, money, and permissions.
- How it went
- The team hit 433 PRs in 72 hours from an empty repo. Launch day showed 4,000 games and 2,000 users but $0 revenue. One later month reached 2,500 PRs merged.
- Worth knowing
- They logged every one of the 40 on-air failures plus the extracted rule for each.
Try it yourself with Grok Bot
Build [product description] from an empty repo [repo URL] using a team of bots, with one agent per feature and others reproducing and fixing bugs. Open small PRs, and merge them yourselves only when tests and review checks pass. Stop and ask me before running any database migration or deploying, showing me exactly what will run.
Want help getting this working? Join the Vibe Coding Academy ↗ Run by Alex Finn, who also runs this site.
Source: X · Sep 20, 2026
Related use cases
Plan and book a short-notice work trip
Grok Bot researched flights and booked the one Vince picked, though he had to take over the computer to fill in data and found it harder than booking himself.
Run content creation with specialized bots
Creators use bots to study outlier YouTube videos, and run newsletters with research, drafting, editing and scheduling bots; one experiment made 44 thumbnail proposals.
Create a subtitled video from one prompt
Agent Mode in Grok Imagine made a 36-second video with matching scenes from different angles, a storyline and subtitles.
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
Hand narrow code changes to Devin for pull requests
A team used Devin for a month on small fixes like chart formatting and API edge cases, with tests and PRs; a complex full-stack task went poorly.
Build a booking and payment app for tattoo artists
A former programmer used Replit Agent over a weekend to build a booking app with calendar, Google OAuth, Stripe deposits and notifications, though time zones and UI needed back-and-forth.
Get 5 like this every morning
The best things people got an AI agent to do, each with the prompt to try it.