How Factory scaled its cloud backend to one billion monthly requests on Vercel
Factory's non-technical teams now deploy dozens of times a day. Their secret: Droids handling builds and deployments end-to-end while engineers set guardrails.
Why it matters
Factory built its autonomous software platform by dogfooding it internally—using Droids to automate routine deployments and infrastructure tasks so engineers stay on product. This is agents in production, scaled: non-technical staff operating autonomous systems against live infrastructure.
The key facts
8 to knowOne billion daily API requests handled by single Vercel backend
350ms p95 response time
Droids deployed for self-serve internal tooling: dozens of deployments per day across non-engineering teams
Non-technical staff (account executives, solution architects) use Factory Desktop App or CLI to build and deploy autonomously
Engineers set guardrails; Droids handle builds, configuration, deployments end-to-end
Observability + WAF deployed for route-level protection after bot attacks on self-serve signups
Next.js runs entire cloud backend (API routes, middleware, webhook handlers, log pipelines)
Three-year growth trajectory without separate infrastructure team
Go to the source
Vercel Blogvercel.com
Publisher excerpt: Factory on Vercel Non-technical teams were bottlenecked on engineering Droids hit Vercel's APIs to build and deploy autonomously Going self-serve exposed Factory's backend to a new category of threat Observability and WAF handle protection at the network level One billion backend API requests…