AI apps with live state.
Call a model from a server function, stream the result into rows your UI is already subscribed to, and run long agent loops as durable workflows that survive restarts. The model, the state, and the realtime layer live in one server.
AI products are mostly plumbing: a model call, a place to stream tokens, a way to push partial results to the client, durable state for multi-step agents, and background jobs for the slow parts. Stitched together from a model SDK, a queue, a websocket service, and a database, it's a lot of moving parts to keep coherent.
Models from a server function
ctx.llm calls a model from inside a Pylon function with the same typed db, auth, and schedule context as the rest of your backend. The call sits next to the data it reads and the rows it writes.
Stream into live state
Write partial results to a row as they arrive and every db.useQuery watching it re-renders token output, status updates, and intermediate steps live. The existing sync engine pushes those changes, so you do not need a separate streaming channel.
Durable agent loops
Multi-step agents run as durable workflows that call tools, wait for results, sleep, retry, and continue. Pylon checkpoints every step so a deploy or crash does not lose the run. Background jobs handle slow work after the request returns.
Ship it on Pylon.
Scaffold an app in seconds, deploy free on Cloud, scale when you need to.