> For the complete documentation index, see [llms.txt](https://docs.screendesk.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.screendesk.io/debug-with-ai/data-sources.md). # Knowledge The docs, files and past tickets AI reads before it answers. Knowledge is what AI reads before it answers: your help center, documents, procedures and solved tickets. [AI resolution](/debug-with-ai/ai-resolution.md) uses it to back its suggestions. Available on Pro and Enterprise. {% embed url="" %} Admins open **Settings → Knowledge** and click **Add knowledge**:
Settings, Knowledge
| Source | What to add | | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Website** | A help center, docs site or one page. Screendesk finds the pages; you choose which to keep and train. | | **Files** | PDF, DOCX, text or Markdown. Drop up to 10 at once. | | **Write** | A procedure or an answer, written in Screendesk. | | **Solved tickets** | Past tickets from Zendesk, Intercom, Freshdesk, Freshchat or Front, synced weekly. Front has no solved status, so its archived conversations are used. | A source is only used once it's **Trained**. A website can retrain itself weekly, so new articles are picked up. Each source has an audience: **Use in recommended replies** is used to investigate and in the drafted reply; **Internal only** is used to investigate but kept out of the reply. **Restricted**, never used, only remains on sources that already have it. Solved tickets are internal case memory: AI can learn from them, but a suggested fix still needs your docs behind it. {% hint style="info" %} AI not using a source? Check that it's trained, the right pages are included, and its audience isn't Restricted. {% endhint %} --- # 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.screendesk.io/debug-with-ai/data-sources.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.