
How General Intelligence used agents to build an agent platform on Vercel
Quick Answer
General Intelligence migrated its Cofounder platform to Vercel to enable full programmatic control for AI agents, achieving 6.5x growth month-over-month.
Quick Take
General Intelligence migrated its Cofounder platform to Vercel to enable full programmatic control for AI agents, achieving 6.5x growth month-over-month. The 8-person team now ships an average of 10 PRs daily, with over 4,000 preview branches running concurrently, automating 90% of SRE tasks.
Key Points
- Cofounder allows founders to run companies entirely with AI agents across all departments.
- The team operates as a multi-tenant app, automating 90% of SRE work via Vercel.
- Engineers average 10 PRs and 70+ commits daily on a $5,000 monthly budget per engineer.
- Over 100 app versions run simultaneously, with 4,000+ preview branches in operation.
- Vercel's infrastructure enables full programmatic control, essential for agent-driven deployments.
Article Content
From source RSS / original summaryGeneral Intelligence on VercelMigrating Cofounder's Python backend to VercelRunning Cofounder as a multi-tenant app on Vercel8-person team (5 engineers) shipping 10 PRs and 70+ commits per engineer, per day4,000+ preview branches with ~100 parallel app versions running at any moment90% of SRE work automated through Vercel and their own agent (Cofounder)Cofounder launches with a managed Vercel account for every customerGeneral Intelligence is building a platform that lets any founder run a company entirely with AI agents.
Their vision is the one-person, billion-dollar company where every department is driven by agents. Their flagship product, Cofounder, gives founders a full team of agents that cover engineering, marketing, SEO, finance, sales, customer support, and operations. General Intelligence is an 8-person company with 5 engineers. To ship a platform that lets their customers run agentic companies, they had to operate as one themselves.
They wanted to use Cofounder's CTO agent to build out other agentic business functions, and their developers quickly learned that was an infrastructure problem, not an agent problem. For a complex, multi-tenant platform, the requirement was total programmatic control: every action a human could take on the underlying cloud platform had to be available to a coding agent through or APIs. That meant killing deployments, changing DNS, managing billing, editing configs, all of it.
Most cloud providers failed that test, and that's why General Intelligence migrated to Vercel. a CLIA coding agent runs dozens of processes in parallel. It queries logs as data, parses errors as input, and treats every dashboard click as a missing API. The bottleneck stops being how fast the agent can write code and becomes how much of the cloud it can actually reach. Most clouds aren't shaped for that pattern.
They're built for human developers: dashboards to click, consoles to read, APIs that cover some operations but stop short of others. The closer an agent gets to running development end-to-end, the more those gaps stack up. General Intelligence started out hosting on Render. It worked for the early product, but provisioning preview environments for the full stack was painful from day one. When they started building Cofounder's CTO agent, that pain became a blocker.
The platform had to be reachable end-to-end through code, and Render's Python support couldn't keep up with what the agent needed. "There are vendors that let an agent do 5% of the work, and vendors that let an agent do 50%," explained Pignanelli. "We needed a platform that would let an agent do 100%. " They evaluated vendors against that bar and made the choice to migrate to Vercel. Migrating to Vercel changed how General Intelligence builds software, and their engineers don't develop locally anymore.
Every change Cofounder's CTO agent makes goes straight to a Git branch, spins up a preview environment, and gets tested end-to-end by a browser agent on the live URL. General Intelligence has over 4,000 branches in flight. At any moment during a workday, around 100 versions of their app are running on Vercel, each on its own with a coding agent or browser agent operating it. Earlier this year, grew 6.
5x month-over-month, and most of that growth was internal engineering work: coding agents building business agents in Cofounder. preview environmentFluid computeToday, engineers ships an average of 10 PRs a day with 70+ commits each, on a token budget of $5,000 per engineer per month. General Intelligence runs a Python backend, and they were one of the first teams to migrate a complex.
They did it deliberately, because the agent had to drive deployments, configs, and compute across the whole stack, not just the frontend. full stack app VercelUnifying on one platform shrank the surface area for the team and the agent to one CLI, one API, and one observability layer. When something breaks, the agent and the developers have the full picture in one place.
When a founder spins up a company on Cofounder, they get more than a set of agents, they get a real GitHub repository and a managed Vercel deployment, provisioned automatically through. Each company also gets its own domain, with SSL and DNS handled automatically. Vercel for PlatformsThe engineering agent inside the customer's company is Cofounder's CTO, the same product General Intelligence uses internally. It runs the same workflow: branches, preview environments, browser agents testing the live URL.
General Intelligence will keep building their own company on the same products they ship to customers. As they add new departments and agents, Pignanelli says Vercel allows them to focus on the customer, not configuring the cloud underneath. General Intelligence is building, the first full-stack agent company platform. CofounderRead moreAgents need infrastructure built for agentsHow five engineers ship like a hundredWhat's next
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from Vercel AI
See more →
The Agent Stack
The Agent Stack by Vercel AI provides essential building blocks for creating production-grade agents, enabling seamless integration across multiple AI models and secure operations. It features components like AI Gateway for model routing, Workflow SDK for durable execution, and Vercel Connect for scoped access, streamlining agent development and deployment across various platforms.

