> For the complete documentation index, see [llms.txt](https://agpt.co/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://agpt.co/docs/integrations/block-integrations/routines.md).

# Conductor Routines

Creates a Conductor routine (a saved prompt that runs a fresh agent whenever its webhook is called) or rotates a routine's webhook secret. Requires your own Conductor API key, created at [app.conductor.build/users/api-keys](https://app.conductor.build/users/api-keys) and added through AutoGPT’s credentials UI. Select that credential for each Conductor block; no server-wide default key is used.

## Conductor Manage Routine

### What it is

Create a Conductor routine (a saved prompt that runs a fresh agent in a project whenever its webhook URL is called) or rotate a routine's webhook secret. Returns the webhook URL.

### How it works

`create` posts `name`, `prompt`, `projectId`, `agent`, optional `model`/`effort`, `enabled` and a single webhook trigger to `POST /v0/routines`; `rotate_webhook_url` posts to `POST /v0/routines/{id}/rotate-secret`. Both responses include the trigger's `webhookUrl`, which the block surfaces as `webhook_url`; the plain routine listing in Get Account never includes it, so store the URL when you receive it. Rotating invalidates the previous URL.

### Inputs

| Input       | Description                                                                                                     | Type                                                                       | Required |
| ----------- | --------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------- | -------- |
| action      | create a webhook-triggered routine, or rotate\_webhook\_url to replace an existing routine's webhook URL        | "create" \| "rotate\_webhook\_url"                                         | No       |
| routine\_id | Routine ID (rotate\_webhook\_url)                                                                               | str                                                                        | No       |
| name        | Routine name (create)                                                                                           | str                                                                        | No       |
| prompt      | Prompt the agent runs each time the webhook fires (create)                                                      | str                                                                        | No       |
| project\_id | Project (repository) the routine runs in (create). Find IDs with Get Account.                                   | str                                                                        | No       |
| agent       | Agent that runs the routine                                                                                     | "claude" \| "codex" \| "cursor" \| "acp"                                   | No       |
| model       | Model id such as fable-5-1, opus-5-5-1m, sonnet-5-1m, gpt-6-astra or auto. Leave empty for Conductor's default. | str                                                                        | No       |
| effort      | Reasoning effort; leave empty for the default                                                                   | "" \| "none" \| "low" \| "medium" \| "high" \| "xhigh" \| "max" \| "ultra" | No       |
| enabled     | Whether the routine is enabled on creation                                                                      | bool                                                                       | No       |

### Outputs

| Output       | Description                                                                                                   | Type            |
| ------------ | ------------------------------------------------------------------------------------------------------------- | --------------- |
| error        | Error message if the operation failed                                                                         | str             |
| routine\_id  | ID of the routine                                                                                             | str             |
| webhook\_url | Webhook URL that triggers the routine. POST to it to run the routine; this is the only time the URL is shown. | str             |
| routine      | Full routine object                                                                                           | Dict\[str, Any] |

### Possible use case

**Wire up automation**: Create a routine such as "triage new issues" and send its `webhook_url` to another system that calls it on events.

**Credential hygiene**: Rotate a leaked webhook secret and update the caller with the new URL.

***


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://agpt.co/docs/integrations/block-integrations/routines.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.