> For the complete documentation index, see [llms.txt](https://support.sayprimer.com/primer/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://support.sayprimer.com/primer/chat/using-chat.md).

# Using Chat

What Primer's Chat can answer and do, how it shows where an answer came from, and how to give it context.

Chat is Primer's in-app assistant, and the page Primer opens on. Ask in plain language, or pick one of the suggested questions beside an empty chat. Chat keeps the conversation in context, so you can ask follow-ups without repeating yourself.

## What you can ask Chat

* **How Primer works** — how-to questions, answered from this help center.
* **Your account** — your plan, audience limits, and connected destinations.
* **Performance** — campaign and conversion performance, spend, engagement and trends, and the companies and people behind them.
* **Your audiences** — ask about one or all of them, or build, change and run one (see [Audiences in Chat](https://support.sayprimer.com/primer/chat/audiences-in-chat.md)).
* **Your reports** — open a report and ask about it.
* **Other companies** — look a company up and research it (see [Researching an account](https://support.sayprimer.com/primer/account-research/researching-an-account.md)).
* **Your earlier chats** — what was said in a previous conversation.

## Seeing where an answer came from

While Chat works it shows a live list of the steps it's taking; when it's done they fold behind **Worked for …**, which you can open again. Under an answer, the **sources** pill opens a **Sources** panel listing what the answer drew on — this help guide, your Primer data, your account, company data or your report — plus any **Notes** on how far the numbers can be read. When Chat can't find a grounded answer, it says so rather than inventing one.

## Tables, charts and the companies and people in an answer

* **Tables** have **Copy table**, which pastes cleanly into a spreadsheet, and **Download CSV**.
* **Charts** switch between **View as table** and **View as chart**.
* **Companies and people** named in an answer show a card on hover, with what Primer knows about them and what your own data says about their engagement.

## Giving Chat context

Use the context button in the chat header to add your **audiences**, **reports** or **datasets** to the conversation, so your questions are about them. An audience or report Chat brings into an answer opens in a panel beside the chat, and your next question is about what's open there.

## Suggested next steps

Under the latest answer, Chat may suggest next steps. Click one to send it as your next question.

## More

* [Managing your chats](https://support.sayprimer.com/primer/chat/managing-chats.md) — history, search, editing and regenerating.
* [Sharing a chat](https://support.sayprimer.com/primer/chat/sharing-a-chat.md) — send a link to a teammate.


---

# 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://support.sayprimer.com/primer/chat/using-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.
