> For the complete documentation index, see [llms.txt](https://support.incidentlake.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://support.incidentlake.com/everyday-tools/knowledge.md). # Knowledge Build the playbooks the assistant and your team reuse during a response. **Knowledge** is your organization’s living playbook. Active entries show up in search and are available to the Chat assistant. ## What a good entry looks like * **Title** — the situation, in words a responder would type * **Trigger keywords** — phrases that should bring this entry up (for example the service name and the symptom) * **Content** — what to check, who to call, and what “done” looks like * **Tags** — so you can filter the library later * **Active** — turn this on when the entry is ready for people and Chat to use You can attach images after the first save. ## Create or edit an entry Open **Knowledge**, choose **New Knowledge**, fill in the title and content, and save. From the list you can search as you type, filter by status or tags, or **Ask AI** to find entries by meaning when the exact words are not in the title. Each save creates a version. Open **Version history** to compare and restore an earlier version (restore writes a new current version; it does not erase the history). ## Keep the library trustworthy * Set a **review cycle** so entries that have not been updated in a while are flagged * Use the **Review required** filter when you are doing housekeeping * Mark an entry **Inactive** when it should no longer be used — it stays in the list but Chat will not rely on it ## AI-generated drafts After you publish an incident postmortem, Incident Lake may propose a knowledge draft distilled from that report. * **Approve** — the draft becomes an active knowledge item and is available to Chat * **Dismiss** — the draft is kept as inactive so you can turn it on later if you change your mind {% hint style="success" %} Approving a handful of high-quality drafts after real incidents is the fastest way to make Chat useful for the next similar event. {% 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://support.incidentlake.com/everyday-tools/knowledge.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.