> For the complete documentation index, see [llms.txt](https://docs.tonic.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tonic.ai/fabricate/data-agent-chat/data-agent-db-chat-memory.md).
# Managing Data Agent chats
Data Agent chats have a size limit. As you interact with the Data Agent, Fabricate updates the percentage of the size limit that you have used.
As you get closer to the limit, the response time can slow down.
To prevent response time issues, and to keep your chats focused, you can create multiple chats. For example, for a more complex database, you might use different chats to manage different areas of the data.
## Viewing the chat usage
To display a summary of the chat usage, hover over the usage icon.
Data Agent usage tooltip with the chat usage summary
To add the token count to the cost breakdown, press the Shift key.
Usage tooltip with token counts
To display additional details about the chat caching:
1. Click the usage icon. This pins the panel open.
2. Click **Show more**.
Usage tooltip that is pinned open with Show more selected
To hide the additional details, click **Show less**.
To unpin the panel, click the icon again.
## Creating a new chat
To start a new chat, at the top of the Data Agent:
1. Click the + icon.
New chat menu
2. From the dropdown:
1. To create a completely new empty chat, select **New Chat**.
2. To create a new chat that starts with a summary of the current chat, select **Summarize and fork**.
## Renaming a chat
To rename a chat:
1. Double-click the chat name.
2. In the field, type the new name.
3. Press Enter.
## Deleting a chat
To delete a chat:
1. Hover over the chat name.
2. Click the delete icon.
Delete icon for a Data Agent chat
---
# 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.tonic.ai/fabricate/data-agent-chat/data-agent-db-chat-memory.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.
