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

# Ask Chord

Ask Chord gives your team instant answers from your commerce data. No SQL, no analysts, no waiting. Ask questions in plain language and get accurate, warehouse-backed results in seconds.

It's built directly on your data and configured around your business logic, so answers reflect how your store actually works without generic benchmarks or approximations.

### What you can do with Ask Chord

**Ask questions in plain language.** Query revenue, customers, orders, products, and more through Ask Chord. Ask Chord retains conversation history, interprets intent, and enriches answers with real-time warehouse data.

**Monitor key metrics automatically.** Set threshold-based alerts on any metric with Monitors. Get notified when something changes without having to check manually.

**Configure Ask Chord for your business.** Use Context to add business-specific instructions.

### Documentation

| Page                                                                 | What it covers                                                        |
| -------------------------------------------------------------------- | --------------------------------------------------------------------- |
| [Chord MCP](/analyze-with-ai/mcp-setup.md)                           | Connecting your Chord data to Claude for plain-language data queries. |
| [Ask Chord](/analyze-with-ai/ai-chat.md)                             | Asking questions and working with answers.                            |
| Chord Monitors                                                       | Setting up automated metric alerts.                                   |
| [Chord Context](/analyze-with-ai/context.md)                         | Adding instructions and SQL pairs.                                    |
| [Ask Chord Use Cases](/analyze-with-ai/ai-chat/ai-chat-use-cases.md) | Example questions and workflows.                                      |
| [Chord FAQ](/get-started/faq.md)                                     | Common questions and answers.                                         |

*Questions or feedback? Reach out to* [*help@chord.co*](mailto:help@chord.co)*.*


---

# 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.chord.co/analyze-with-ai/ai-chat.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.