> For the complete documentation index, see [llms.txt](https://ed.sunbird.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ed.sunbird.org/release-6.0.0/learn/functional-capabilities/multi-channel-chatbot.md).

# Multi-Channel Chatbot

A chatbot is a type of software that can help users by automating conversations and interacting with them through messaging platforms.

Users can interact with the chatbot using two ways -

1. Structured pre-defined steps - In this, the creator can define the steps, flows, UI, and actions that a user can access. The user has to choose specific paths to reach what they are looking for.
2. Free-flowing conversation - In this, the creator can define an answer to a list of probable questions. Using machine learning, the system will further make more such combinations of questions to which a particular answer can be applied. This is more like a real conversation with users but here also the boundary is what answers have been already defined by the creator.

Chatbots can be utilized for -

1. Discovery - Creator can enable the discovery of content, programs, apps, etc. for its users.
2. Query resolution - User's queries can be resolved related to anything for which a help section is required.
3. Updates and Announcements - Creator can put personalize updates and announcements for its users to consume
4. Contexual engagement - Creator can allow users to engage with the platform better with contexual popup of chatbot in scenarios such as while user leaving the page, to explain content better on a page, etc.

The above capabilities of Multi-Channel Chatbot are derived from components of Sunbird UCI. You can find details by clicking on the link [here](/release-6.0.0/learn/functional-capabilities/product-and-developers-guide/multi-channel-chatbot.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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://ed.sunbird.org/release-6.0.0/learn/functional-capabilities/multi-channel-chatbot.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.