> 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/build-and-improve/intelligence/knowledge.md).

# Knowledge

The product surface labels this area **Knowledge Bases**. It is where builders create and maintain reference material that the Agent can search and retrieve while doing work. Typical content includes policies, procedures, manuals, product documentation and internal guidance.

Knowledge Bases are builder-only: Project Builders and Owners can open and manage this surface. Operators are redirected away rather than seeing a read-only version.

## The Knowledge Bases surface

Builders can search Knowledge Bases by name, sort the list, switch between grid and list presentation, create a knowledge base and edit an existing one.

![The Knowledge Bases inventory with search, sorting, view controls and the create action.](https://3370306531-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlgSglJDQZxDZdn20CUcl%2Fuploads%2FCrayl5xrWlqKPCetAsBP%2Fknowledge-bases-list.png?alt=media)

A Knowledge Base should have a clear purpose and a recognisable body of source material rather than becoming a catch-all bucket for every document the Project has seen.

## What a Knowledge Base contains

Editing a Knowledge Base opens its document collection. You can upload source files or use **Write Something** to author text directly. Each document shows its processing state, such as **Ready**, while it is prepared for retrieval.

![The Knowledge Base editor showing source documents, processing state, Upload and Write Something.](https://3370306531-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlgSglJDQZxDZdn20CUcl%2Fuploads%2FKZOzDmMUABkeAMBhBG58%2Fknowledge-base-editor.png?alt=media)

Advanced configuration includes the **Primary Content Type**, which controls how documents are chunked for retrieval, and the embedding **Language**. Choose the language when creating the Knowledge Base: it cannot currently be changed after creation. Page-bound content can additionally include document title and page information.

Document capacity is an organisation-level plan limit, not a per-Knowledge-Base limit. Current limits are 10 documents on Free, 1,000 on Business and unlimited on Enterprise.

## When to use Knowledge

Use Knowledge Bases for maintained material that is primarily read as reference.

Use:

* **Tables** for structured maintained mappings and datasets;
* **Skills** for reusable operating instructions;
* **Files** for case material and general Project artefacts;
* source systems for authoritative live records.

## Make authority and provenance clear

Good Knowledge content makes it possible to understand where a retrieved statement came from and how current it is.

A plausible retrieved passage is still only as reliable as the source material behind it. If a policy or procedure changes, update the maintained source rather than relying on the Agent to infer that an older version is obsolete.


---

# 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://docs.lleverage.ai/build-and-improve/intelligence/knowledge.md?ask=<question>&goal=<endgoal>
```

`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.