> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/run-operations/agent/agent-context/knowledge-bases.md). # Knowledge Understand how maintained reference material gives the Agent organisation- specific knowledge. Knowledge gives the Agent maintained reference material it can search while doing the work. Typical examples include: * policies and procedures; * product information and technical manuals; * regulatory or internal guidance; * customer or supplier instructions; * other reference documents that should be reusable across tasks. ## Reference material, not the whole operation Knowledge is useful for questions such as: * what does the policy say? * which procedure applies? * what product guidance is relevant? * what rule should be followed in this case? It should not replace the systems where changing operational data belongs. For example, a delivery policy may belong in Knowledge. The current delivery date for a specific order usually belongs in the ERP. ## The Agent retrieves relevant material when needed When Knowledge is available, the Agent can search it for information relevant to the task instead of loading every document into every conversation. More documents are not automatically better. The goal is to make useful, maintained reference material easy to retrieve. ## Authority matters A signed policy, an old presentation, a customer email and a draft procedure can all contain useful information without being equally authoritative. When that distinction matters, make clear which source wins and when uncertainty needs a person. ## Keep maintained knowledge maintained Knowledge becomes risky when it looks current but is not. If a reference influences operational decisions, make sure the underlying material has an owner and is updated when the business rule changes. Use **Tables** for structured maintained mappings, **Skills** for reusable operating methods, and connected business systems for exact live records. Builders can manage Knowledge under **Build and improve → Intelligence**. --- # 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.lleverage.ai/run-operations/agent/agent-context/knowledge-bases.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.