> For the complete documentation index, see [llms.txt](https://docs.jetadmin.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.jetadmin.io/workflow/workflows-and-ai/generate-a-workflow-with-ai.md).

# Generate a workflow with AI

Creating workflows using the Ask AI feature

Use **Ask AI** to draft workflow steps from a plain-language description, then review and test the result.

## Open Ask AI

1. Configure a supported trigger and open its workflow builder.
2. Select **Ask AI**.
3. Describe the available resource, input, condition, and desired result.

{% @arcade/embed url="<https://app.arcade.software/share/Sd6L8bPYmjApw4sEQ7on>" flowId="Sd6L8bPYmjApw4sEQ7on" %}

## Write a specific request

For a Tickets example:

> Use the ticket\_id input to find one record in my Tickets collection. If the record exists and its status is Open, change its status to In progress. If no record matches, do not update anything. Use the actual resource and field names available in this project.

Replace the example names and status values with your own. Describe the expected behavior for empty results, not just the successful path.

## Review the generated steps

Check the resource and collection, record ID binding, condition values, and write fields. Ensure the generated process targets only the intended record.

The existing walkthrough below shows a customer-email use case. It illustrates generation and review; it is a different example from the Tickets prompt.

{% @arcade/embed url="<https://app.arcade.software/share/kIdVDgdbOWiisMcS83oy>" flowId="kIdVDgdbOWiisMcS83oy" %}

<figure><img src="https://3448227606-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-LQ08RFAKZvFADEiXKFy%2Fuploads%2FRJsUUZPWCvOfNpRhUXwr%2FScreenshot%202025-08-31%20165254.png?alt=media&amp;token=6e014a4b-b528-42e8-99f0-e19d22516047" alt=""><figcaption></figcaption></figure>

## Test the result

Use a matching ticket, a ticket with another status, and a missing ID. Verify the stored data after each test. Review recipients before testing generated notification actions.

Generating a workflow does not add an agent that makes decisions at runtime. For that pattern, see [Run an agent in a workflow](/ai-agents/run-agents-in-apps-workflows-and-tasks/workflows-with-agents.md).


---

# 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://docs.jetadmin.io/workflow/workflows-and-ai/generate-a-workflow-with-ai.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.