> For the complete documentation index, see [llms.txt](https://cc.docs.landis.cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://cc.docs.landis.cloud/setup/set-up-chat-channel/set-up-ai-chat-agent.md).

# Set Up AI Chat Agent

AI chat agents are able to answer customer questions through a chat channel. They use a Microsoft Copilot agent within a Chat IVR.

Below are the steps to setup an AI Chat Agent:

1. Create a Copilot agent. See [Copilot Agents](https://cc.docs.landis.cloud/administration/copilot-agents.md).
2. Create a Chat IVR and add a **Copilot Agent** block. Select the configured agent in that block. See [Set Up Chat IVR](https://cc.docs.landis.cloud/setup/set-up-chat-channel/setup-ivr.md#example-copilot-agent).
3. Create a chat link for the IVR. This connects the chosen channel to the flow. See [Set Up Chat Link](https://cc.docs.landis.cloud/setup/set-up-chat-channel/set-up-chat-link.md).

When a customer starts a chat, the IVR sends it to the Copilot agent. The agent handles the conversation in the existing chat interface. When it escalates the conversation, the IVR continues at the block configured after the Copilot Agent block.

For example, an AI agent can answer product questions. Configure its escalation topic to transfer unanswered billing requests. The next IVR block transfers to a chat queue. A live agent then receives the escalated chat.


---

# 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://cc.docs.landis.cloud/setup/set-up-chat-channel/set-up-ai-chat-agent.md?ask=<question>&goal=<user_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.
