# Ask Mechanic

**Ask Mechanic** is Mechanic's built-in AI assistant. It can answer platform questions, help you find tasks, and explain how features work — all without leaving the app. It has access to Mechanic's full documentation and Shopify's API documentation.

Look for the **Ask Mechanic** button in the Mechanic app to get started, or press `Cmd/Ctrl + J` to toggle it from anywhere (see [Keyboard shortcuts](/app/keyboard-shortcuts.md)). No setup or external tools needed.

<figure><img src="/files/JEeak2aLWN4bV38f9PnR" alt="The Ask Mechanic panel open inside the Mechanic app"><figcaption></figcaption></figure>

{% hint style="warning" %}
Mechanic support covers the platform and tasks from the [task library](/resources/task-library.md). Custom tasks (including AI-generated tasks) are not covered by support — for help with custom task logic, ask in the [Mechanic Slack community](/resources/slack.md) or [hire a developer](/hire-a-developer.md).
{% endhint %}

## What you can ask

* "How do I subscribe to Shopify order creation events?"
* "What action types are available?"
* "How do I respond to action results?"
* "What integrations does Mechanic support?"
* "Find a task that auto-tags orders by discount code"

Ask Mechanic can also expand for more room or dock to the bottom of the app in a terminal-style view:

<figure><img src="/files/tAGatn2G7cp5HEah1G8B" alt="Ask Mechanic docked to the bottom of the Mechanic app"><figcaption></figcaption></figure>

## For developers

If you're writing tasks in an external AI coding tool (like Claude Code or Cursor), Mechanic also offers tools that connect your editor to the task library and docs. See [Using AI with Mechanic](/ai.md).


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://learn.mechanic.dev/app/ask-mechanic.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.