> For the complete documentation index, see [llms.txt](https://docs.deepconverse.com/product-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.deepconverse.com/product-docs/chatbots/deploy/custom-initialization-and-passing-metadata.md).
# Custom Initialization and Passing Metadata
By default the chatbot script is configured to show the chatbot on load. In cases you need customization on which pages does the chatbot show on or pass specific metadata you can override the trigger function and initialize the chatbot on your webpage.
You can find the **Trigger Function** under **Features**
### Initializing the chatbot
The chatbot works based on events passed through the script. You can fire the following event to show the chatbot on a page. You can customize when the event is sent based on the origin, button click or any other action on the page to show the chatbot.
```javascript
document.dispatchEvent(new CustomEvent("botWidgetInit", {"detail": {"origin": "support"}}));
```
### Passing Metadata
To make decisions in the flow you can pass metadata to the chatbot. This metadata live in the conversation context and is available to use in routing/api and other actions.
```javascript
let metadata = {
"origin": "support",
"tags": ["ios", "vip"]
}
document.dispatchEvent(new CustomEvent("botWidgetInit", {"detail": metadata}));
```
---
# 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.deepconverse.com/product-docs/chatbots/deploy/custom-initialization-and-passing-metadata.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.
