Are you an LLM? Read llms.txt for a summary of the docs, or llms-full.txt for the full context.
Skip to content

Build With A Coding Agent

Paste this into your coding agent:

Fetch this setup prompt and follow it to build and deploy my Amodal agent:
https://docs.amodalai.com/agent-setup/prompt.md

The prompt explains how to fetch the docs and API reference, collect missing configuration, connect source, deploy, and test the result.

Platform Token

The coding agent needs a pk_ platform automation token to create, configure, or deploy agents:

  1. Open Amodal and select your organization.
  2. Open Organization > Automation Tokens.
  3. Create an org-wide admin token for initial setup.

Once the agent exists, use an agent-bound operator token for routine deploys. The coding agent also needs the organization ID, source repository, and any runtime secrets the source references.

A platform token authorizes deployment operations. Chat smoke tests use a separate, short-lived runtime token; the setup prompt explains how to obtain one.

Docs And API Reference

The prompt fetches:

https://docs.amodalai.com/llms-full.txt
https://docs.amodalai.com/openapi.json

llms-full.txt contains the docs as text. openapi.json lists the supported automation endpoints, accepted token kinds, and documented parameters and request bodies. Response schemas are generic; inspect the returned status and JSON rather than assuming a fully specified response shape.