Skip to the operations

AI

Claude Routines in a decision flow.

1 Claude Routines operation a decision flow can call directly, with the credentials your own contract issued. The response is data the rest of the flow reads, branches on, and keeps in the trace.

Category
AI
Type
Integration
Authentication
API key
Test environment
Production host only

Who they are

Saved Claude Code automations that run on demand.

Claude Code Routines package a saved prompt, repositories and connectors into an unattended coding session hosted by Anthropic. A routine can run on a schedule, from a GitHub event or through its experimental HTTP trigger. Each API trigger has its own token and creates a new Claude Code session when called.

What a flow can call

1 operation, each one a step you can place on the canvas.

  1. POST/v1/claude_code/routines/{routine_id}/fire

    Start a routine

    Set data.something_here to the text you want to append to the saved routine prompt.

Where it sits in the decision

AI calls have a natural place in a flow.

A model call is for the judgment a table cannot express — reading a document, summarising a file, weighing a narrative. Because the output is not deterministic, a flow constrains it with a schema and keeps the prompt and the response in the trace, so the reasoning behind a referral stays as inspectable as a rule.

Whatever Claude Routines returns is part of the run, so it is part of the record. When someone asks months later why an applicant was declined, the answer cites what came back at the time rather than re-fetching from a service whose answer has since changed.

  • 01Add Claude Routines as a connection authenticating with an API key.
  • 02Claude Routines has one host for both environments, so guard test runs with your own credentials and limits.
  • 03Place a Connection node and pick an operation — “Start a routine” is usually the first one a flow needs.
  • 04Map the response into the fields your rules read, then test the whole path before it carries live traffic.

Common questions

Using Claude Routines in a flow.

How do I connect Claude Routines to a decision flow?

Add Claude Routines as a connection in your workspace authenticating with an API key, with the credentials your own contract issued — ArboRule calls the provider as you, and never holds a contract on your behalf. Once the connection exists, any flow in the workspace can place a Connection node and choose one of its operations. The credentials live on the connection, not in the flow, so a policy owner can use Claude Routines in a decision without ever seeing the secret.

Can I test Claude Routines without touching production?

Claude Routines exposes one host for both environments, so there is no separate sandbox to point at. Test runs still execute in Sandbox and are recorded separately in decision history, but the call goes to the same place as production — so guard it with your own test credentials, rate limits, or data.

What can a flow call on Claude Routines?

1 operation: “Start a routine”. Each one is a step you place on the canvas and map into the fields your rules read, and most flows start with “Start a routine”. The list comes from the same manifest the engine uses to make the call, so this page cannot describe an operation the product does not have.

Where in a decision should Claude Routines be called?

A model call is for the judgment a table cannot express — reading a document, summarising a file, weighing a narrative. Because the output is not deterministic, a flow constrains it with a schema and keeps the prompt and the response in the trace, so the reasoning behind a referral stays as inspectable as a rule.

Also in AI

Ready when you are

Wire Claude Routines into a real decision.

Build the flow in Sandbox, connect your account, and watch the decision pull what it needs before it answers.

Read the docs