> For the complete documentation index, see [llms.txt](https://replai-1.gitbook.io/replai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://replai-1.gitbook.io/replai-docs/use-cases/internal-knowledge-base.md).

# Internal knowledge base

## Internal knowledge base

Replai works well for internal knowledge when teams need grounded answers from approved content.

Internal assistants are useful for onboarding, policy lookup, IT help, and runbook discovery.

**Keywords:** Replai internal knowledge base, employee assistant, onboarding assistant, policy search

### Which sources work for internal knowledge?

Internal assistants can use the same supported sources as customer-facing assistants:

* GitBook
* Website crawler
* Q\&A snippets

Sources stay shared at the workspace level.

You can attach the same source to more than one assistant when the audience is the same.

### When should you use a separate assistant?

Use a separate assistant when access, audience, or tone differs.

That is common for:

* Company-wide onboarding
* Engineering or IT operations
* Policy and compliance content

### Why does Replai work for internal teams?

Replai only answers from connected content.

That keeps internal answers grounded in approved company material.

Replai also declines gracefully when the content does not support an answer.

### What should you watch for?

Watch for these risks:

* Sensitive content mixed into broad source scopes
* Old policy pages that conflict with current rules
* Long pages that combine several unrelated topics

{% hint style="warning" %}
Use separate assistants when different teams need different source access.
{% endhint %}

### Which metrics matter most?

Common internal metrics include:

* Deflection
* Unanswered questions
* Time to first answer
* Employee feedback

### Related links

* [Q\&A snippets](/replai-docs/connectors-sources/q-and-a-snippets.md)
* [Data isolation](/replai-docs/trust-and-privacy/right-to-erasure.md)
* [Support deflection](/replai-docs/use-cases/support-deflection.md)


---

# 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://replai-1.gitbook.io/replai-docs/use-cases/internal-knowledge-base.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.