What problem does it solve? Lambda-style serverless functions time out on long-running workloads like AI agent streams, WebSocket servers, and SSE endpoints, and they run far from your database. This Skill guides you through defining, developing, deploying, and managing long-running serverless functions that run next to your Neon Postgres branch with DATABASE_URL injected automatically. ## Core Features & Use Cases - Long-Running Handlers: Deploy web-standard fetch handlers on Node.js 24 with a 15-minute time-to-first-byte budget, supporting streaming agents, WebSocket servers, and SSE endpoints that stay alive while bytes flow. - Branch-Scoped Backends: Each Neon branch runs its own function version at its own URL against its own isolated database, with infrastructure declared as code in neon.ts and deployed via the Neon CLI. - Function Triggers: Schedule cron invocations or react to object-storage upload events that POST to your function, with parsing helpers for delivery payloads. - Use Case: Build an AI agent with the Vercel AI SDK that streams multi-step tool-calling responses directly to the browser, queries Postgres through a pooled connection, and authenticates callers with JWT verification — all without hitting your web host's serverless timeout. ## Quick Start Ask the AI to create a Neon Function in neon.ts with a Hono handler that queries Postgres and deploy it with neon deploy.
