Skip to main content
The v2 API is in beta. Endpoints and response shapes may still change.
The v2 API runs Origami’s agent from your code. You send it a brief in plain English, it does the research and builds a table, and you read the result back. You work with three resources, all documented in the reference:
  • Agent — a worker in your org. Create one and reuse it.
  • Run — one brief and the work that follows. An agent does one run at a time.
  • Table — what the agent builds. Read its rows through the v1 Data API.

​
Start here

Quickstart

Start an agent, follow up, poll, and fetch the data — end to end.

Create an agent

The first call, and every field it takes.
Want the AI to do the work? Use v2. Already have the data and just need to read it or drop rows in? That’s the free v1 Data API.