> For the complete documentation index, see [llms.txt](https://docs.eesel.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.eesel.ai/integrations/knowledge.md).
# Knowledge
Build an AI knowledge base from your website, Confluence, Google Drive, Notion or uploaded files, so your agent answers from them and links the source.
An AI knowledge base is the set of documents your AI agent reads before it answers. In eesel you build it from your website, Google Drive, Notion, Confluence or your own files, and your agent answers from them with a link to the source.
Your AI teammate answers from the sources you connect here, wherever it works. It reads the pages, files and documents you pick, and every answer links back to the source it came from. The same teammate uses them in your helpdesk, in Slack and in the chat bubble.
{% hint style="info" %}
**Using Claude Code, Codex or Cursor?** Ask it to add knowledge to eesel with [eesel CLI](https://docs.eesel.ai/apis-and-developer-resources/cli). Point it to the [setup guide](https://docs.eesel.ai/getting-started/set-up-from-a-coding-agent).
**Using Claude.ai or ChatGPT?** Use the eesel connector (MCP). See [Claude and other assistants](/apis-and-developer-resources/use-eesel-from-claude-and-other-assistants.md) or [ChatGPT](/apis-and-developer-resources/use-eesel-from-chatgpt.md). If the eesel connector is already linked to the correct workspace, keep using it. For steps it cannot complete, use the dashboard.
**CLI details for your coding tool:** The CLI can crawl websites, upload files and show connection options with `eesel integrations connect`. Google Drive’s picker, Notion page sharing and Confluence credentials still need the steps in their guides. Check that imported content is ready, then test an answer. Confluence connected with an API token reads pages live instead of downloading them. You can also add knowledge in the dashboard.
{% endhint %}
| Source | How it connects | What your teammate reads | How it stays up to date |
| ----------------------------------------------------------------- | ------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------- |
| [**Website**](/integrations/knowledge/website.md) | Paste a URL | Pages found through your sitemap and links, up to 2,000 per crawl | Re-crawl when you re-save the integration |
| [**Google Drive**](/integrations/knowledge/google-drive.md) | Google sign-in, then pick files and folders | Docs, Sheets, Slides, modern Office files, PDFs and text files | Re-sync refreshes edits. New files need picking again |
| [**Notion**](/integrations/knowledge/notion.md) | Notion sign-in, or a token | The pages you share, their properties, nested pages and database records, up to 15,000 | Indexed when you connect. New pages do not show up straight away |
| [**Confluence**](/integrations/knowledge/confluence.md) | An Atlassian API token, or eesel's Atlassian Marketplace app. Cloud only | With a token, any page the connected account can see, read live. With the app, the spaces and pages you pick | With a token, always current, because nothing is copied. With the app, edited pages update on their own |
| [**Uploading Files**](/integrations/knowledge/uploading-files.md) | Upload in **Files**, or write in eesel | PDFs, Word documents, CSV, text and Markdown files. Your agent can write files too | Upload a file with the same name to replace it |
| [**AWS S3**](/integrations/knowledge/aws-s3.md) | An AWS access key, bucket and optional folder | PDFs, Word, Excel and PowerPoint files, and text files, up to 50 MB each | Re-sync to pick up new and changed files |
| [**Slite**](/integrations/knowledge/slite.md) | Ask us to turn it on | Your Slite wiki, or only the documents you list | Refreshes on a schedule, or ask your agent to sync it |
Not seeing your app? The [integrations overview](/integrations/overview.md) has the full list, and how to ask for one.
## FAQ
How do I train AI on my own data?
Connect the places your knowledge already lives, and your eesel agent answers from them. Add your website, Google Drive, Notion, Confluence or uploaded files from **Integrations**, or ask your agent in the dashboard chat to connect one. There is no training step to run. Your agent searches the indexed content when a question comes in, and links the page or file it used.
Can my AI agent answer from several knowledge sources at once?
Yes. Every source connected to an agent is searched together, so one answer can draw on your website, Confluence, Google Drive, Notion, your helpdesk and your files. Each connected app also has a toggle on its integration page, so you can take its content out without disconnecting it.
Can my AI agent change my documents?
No, not in your website, Google Drive or Confluence. Those connections only read. Notion has write actions you can switch on, such as creating a page or adding to one. Your agent can also write to its own **Files** list in eesel, where it saves documents such as summaries or notes.
---
# 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.eesel.ai/integrations/knowledge.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.