> For the complete documentation index, see [llms.txt](https://docs.userlane.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.userlane.com/assistance/the-assistant/connections.md).
# Connections
Knowledge connectors, your own AI service, and support email routing.
{% columns %}
{% column %}
{% content-ref url="/pages/FxcQeBasWlRhc3HVdmJT" %}
[Knowledge connectors](/assistance/the-assistant/connections/knowledge-connectors.md)
{% endcontent-ref %}
{% content-ref url="/pages/7EPCKtnfdYXjGlW43dbR" %}
[Connect your own AI service](/assistance/the-assistant/connections/connect-your-own-ai-service.md)
{% endcontent-ref %}
{% endcolumn %}
{% column %}
{% content-ref url="/pages/MwzGnMwrF439WOeHklOX" %}
[Support email routing](/assistance/the-assistant/connections/support-email-routing.md)
{% endcontent-ref %}
{% endcolumn %}
{% endcolumns %}
The Assistant[^1] can search documentation an organization already keeps in other systems. Once a source is connected, the Assistant finds and links its content the same way it finds a guide.
## Why connect existing documentation
The answers to most common questions already exist somewhere in an organization, in an intranet, a service desk knowledge base, or a wiki. Connecting that material lets the Assistant use it as it stands, which saves rewriting it as Userlane content first.
Where an answer draws on a connected source, the Assistant links that source, so a reader can open the original and check it. Connecting material that someone already keeps current means the content behind those answers stays accurate.
## What the Assistant does with a connected source
Alongside guides and announcements, connected sources become material the Assistant can draw on when it answers, and it links the results it used.
Content from a connected source appears as a document result. Opening one shows a preview inside the Assistant, so the reader stays in the application.
## Setting up a connection
Knowledge connectors are set up in two steps. An administrator connects the source once for the organization, then switches it on for each application that needs it. Because the two steps are separate, one source can serve several applications. See [Knowledge connectors](/assistance/the-assistant/connections/knowledge-connectors.md).
An organization can also connect its own search or retrieval service, which verifies each user through Microsoft Entra ID. That connection is set up under **Agentic Assistance**. See [Connect your own AI service](/assistance/the-assistant/connections/connect-your-own-ai-service.md).
When no connected source answers a question, the Assistant points the user to the support link or email address set in [Support email routing](/assistance/the-assistant/connections/support-email-routing.md).
## Relevant articles
{% content-ref url="/pages/XDGntxUJimFOtJOihyow" %}
[The Assistant](/assistance/the-assistant.md)
{% endcontent-ref %}
{% content-ref url="/pages/jaGpQWjETS3dwv2yneLk" %}
[Configure the AI Assistant](/assistance/the-assistant/configure-the-ai-assistant.md)
{% endcontent-ref %}
{% content-ref url="/pages/14ViydxzHwBkmZMnQj6h" %}
[AI features: what data is processed and where](/security-and-privacy/ai-features-what-data-is-processed-and-where.md)
{% endcontent-ref %}
## FAQ
Does connecting a source replace writing Userlane content?
No. A connected source adds existing documentation to what the Assistant can draw on. Guides and announcements continue to work as before.
Where does a reader end up after opening a connected result?
In a preview inside the Assistant, in the application they were already working in.
[^1]: The AI Assistant is the conversational feature inside the Userlane Assistant panel that answers questions from published and connected content, and hands off to guides or support.
---
# 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.userlane.com/assistance/the-assistant/connections.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.