> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orbitagents.xyz/llms.txt
> Use this file to discover all available pages before exploring further.

# Automations

> Chain your agents into multi-step flows on a visual canvas.

<Note>
  **Coming soon.** Automations are in build. This page is a preview of how they'll work — details may change before launch.
</Note>

Automations let you chain your agents into a multi-step flow on a visual canvas — so instead of one agent doing one job, a sequence of steps runs end to end.

## The pieces

* **Automation** — the whole flow.
* **Entry point** — the *one* existing agent that kicks it off.
* **Follow-up steps** — what happens next: a Claude call, a tool call, a transformation, or handing off to another existing agent.

Only agents that are already active in your Orbit dashboard can be placed on the canvas — automations connect the team you already have.

## What starts an automation

The entry point can fire on any of:

* **A schedule** — at a set time or cadence.
* **From a previous step** — when an earlier step completes.
* **An external event** — something happening outside Orbit.

(Any of these can trigger it — they're OR'd together.)

## What can be an entry point

It depends on the agent's underlying engine:

* **Cowork agent** — schedule triggers.
* **Claude Code routine** — all trigger types, via a per-routine fire link and token.
* **Codex / others** — varies by engine.

## Connecting a Claude Code routine

*(How-to coming with launch.)* You'll paste the routine's fire URL and token once, then use a Test button to confirm it's wired up — after which the routine can be an entry point for automations.

<Card title="For now: schedules & routines" icon="calendar" href="/claude-education/routines-schedules">
  Put a single agent on repeat today.
</Card>