How General Intelligence used agents to build an agent platform on Vercel
Not a pilot. General Intelligence deployed agents across 4,000+ preview branches—shipping 10 PRs per engineer, per day.
Why it matters
General Intelligence built an agent-native platform (Cofounder) by operating as one themselves, migrating to Vercel to give their CTO agent 100% programmatic control of the cloud. This is a case study in infrastructure-as-bottleneck for agentic workflows—and a signal that cloud platforms designed for humans are becoming limiting for teams running agent-first development.
The key facts
8 to know8-person team (5 engineers) shipping 10 PRs and 70+ commits per engineer per day
4,000+ preview branches with ~100 parallel app versions running at any moment
90% of SRE work automated through Vercel + their own agent (Cofounder)
$5,000 token budget per engineer per month
Migrated full-stack Python backend from Render to Vercel for agent-native control
Cofounder platform provides customers with managed Vercel deployments, GitHub repos, and automated domain/SSL provisioning
6.5x month-over-month growth in internal engineering capacity driven by coding agents
CTO agent operates end-to-end: code → Git branch → preview environment → browser testing on live URL
Go to the source
Vercel Blogvercel.com
Publisher excerpt: General Intelligence on Vercel Migrating Cofounder's Python backend to Vercel Running Cofounder as a multi-tenant app on Vercel 8-person team (5 engineers) shipping 10 PRs and 70+ commits per engineer, per day 4,000+ preview branches with ~100 parallel app versions running at any moment 90% of SRE…