> 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 how it grounds its replies in your account and this guide. > **Beta** — opened on request. Contact to request access. Chat is Primer's in-app assistant. Ask a question in plain language — the composer prompts you with *"Ask about spend, reach, audiences, or conversions…"* — and Chat answers by drawing on this help center and your own account. It keeps the recent conversation in context, so you can ask follow-ups without repeating yourself. ## What you can ask * **How Primer works** — how-to questions about features, answered from this help center. * **Your account** — your plan, audience slots, reveal limit, and connected destinations. * **Your reports** — interrogate a report you've already generated. * **Account research** — profile a company and infer its ICP (see [Researching an account](/primer/account-research/researching-an-account.md)). * **Performance** — analytics on delivery, spend, match rates, conversions, and trends. ## How Chat answers Chat streams its reply as it writes, showing a **Thinking…** indicator while it works. As it answers it shows the **steps** it took — the sources and tools it consulted — so you can see where an answer came from. Answers are **grounded**: how-to replies are drawn from this help center, and account or performance replies from your live data. When Chat can't find a grounded answer, it tells you it can't rather than inventing one. ## Suggested follow-ups After an answer, Chat may offer **follow-up suggestions** as clickable chips — for example, after it resolves a company it can offer to infer that company's ICP. Click one to send it as your next question. ## More * [Managing your chats](/primer/chat/managing-chats.md) — history, search, editing, and regenerating. * [Sharing a chat](/primer/chat/sharing-a-chat.md) — send a read-only 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=&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.