> For the complete documentation index, see [llms.txt](https://lazylyrics.gitbook.io/carter-js/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://lazylyrics.gitbook.io/carter-js/conversation/downvoting.md).

# Downvoting

Downvoting is explained in the [CarterAPI Docs](https://carterapi.gitbook.io/carter-docs/api/downvote-agent-responses). carter-js allows you to easily downvote a response by calling `downvote()` and passing in a number of possibilities.

```javascript
// assuming you have already created a Carter object called carter

const interaction = await carter.say("Hi Carter, say something that doesn't make sense please.")
const downvoted = await carter.downvote(interaction)
```

`downvote()` returns a Boolean signifying success. The above examples passes an Interaction object to `downvote()`, but it can take one of three things:

* **An Interaction object**
* **A ConversationEntry object** (obtained through carter-js' [history](/carter-js/conversation/history.md) tool)
* **A tid string**

When passed either of the first two, downvote will try to extract the tid from its data. If this is not possible - likely because you passed an Interaction Object where the `data` property was undefined, `downvote()` will return false.


---

# 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:

```
GET https://lazylyrics.gitbook.io/carter-js/conversation/downvoting.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.