> 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/ai-chat-powered-by-anthropic.md).

# Ask Chord: powered by Anthropic

Ask Chord runs on Anthropic's Claude, a large language model built for reliability, safety, and consistent performance. This page explains which models Ask Chord uses, how they're matched to specific tasks, and why we chose Anthropic.

### Models in use

Ask Chord uses three Claude models, each matched to a specific job, with a fallback model if Claude is unavailable.

| **Task**              | **Primary model** | **Fallback** |
| --------------------- | ----------------- | ------------ |
| Ask Chord chat        | Claude Opus 4.8   | GPT-5.5      |
| Insights agent        | Claude Sonnet 4.6 | GPT-5.5      |
| Audience smart naming | Claude Haiku 4.5  | —            |

**Ask Chord chat** handles conversational Q\&A, where reasoning depth and context-handling matter most.

**Insights agent** handles analysis and synthesis tasks that run after data is fetched, balancing quality with speed.

**Audience smart naming** generates concise names for saved audiences, a lightweight task suited to a fast, smaller model.

Why Anthropic

We evaluated several leading AI models against Chord's commerce use cases. Anthropic's Claude stood out for three reasons:

* **Output stability.** Claude produces consistent, structured responses across repeated and varied inputs, reducing unexpected results.
* **Reasoning quality.** Claude handles complex, multi-step logic reliably, which matters for tasks like forecasting, segmentation, and data interpretation.
* **Safety by design.** Anthropic builds safety and predictability into the core of their models, which aligns with how we think about trust in our platform.

### FAQs

**Will model updates affect my existing prompts or workflows?** No. All existing prompts, automations, and integrations continue to work as before. We will communicate any future model changes in advance.

**Is my data shared with Anthropic?** No. Your data is processed in accordance with Chord's existing privacy and data handling policies. See our privacy policy for full details.

**Who do I contact if I notice unexpected behavior?** Reach out to <help@chord.co> or contact your Chord account team.


---

# 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/ai-chat-powered-by-anthropic.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.