> For the complete documentation index, see [llms.txt](https://docs.ai.insly.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ai.insly.com/nora/skills/chat-agent-integration.md).

# Chat agent integration

FormFlow can meet your users wherever they already are. Our chat agent can be embedded directly into other SaaS platforms, giving brokers or clients a conversational way to submit information without ever leaving the environment they're working in.

The chat agent understands natural language, asks clarifying questions when needed, and processes submissions in real time using FormFlow's extraction engine. The data flows seamlessly into your underwriting pipeline, structured and ready to action.

This makes FormFlow invisible to the end user — they just have a conversation, and the submission gets handled automatically on your side.

#### **Special integration with Insly Ledger**

For users of Insly Ledger, we've built a deeper level of integration. Once a submission is processed and a quote is generated, the agent can navigate the user directly to the quote within the Ledger UI.

The agent can review quote fields in-browser and suggest edits where needed. It can also work with the user to add any additional information to the quote, all through natural conversation.

The result is a completely unified experience — brokers submit, review, and refine quotes without switching tools or waiting for back-and-forth emails.

{% hint style="info" %}
For a demo or information on how to set this up, please [reach out to us](/readme.md). Agentic experiences are available on L and Enterprise plans, and require an Insurance Copilot licence.
{% endhint %}


---

# 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.ai.insly.com/nora/skills/chat-agent-integration.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.