> For the complete documentation index, see [llms.txt](https://help.recart.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.recart.com/latest-news/introducing-ai-powered-unsubscribe-intent-detection.md).

# Introducing AI-Powered Unsubscribe Intent Detection

Announces AI detection of unsubscribe intent in free-text replies, processed the same as a standard STOP.

Subscribers Who Say "Stop Texting Me" Are Now Automatically Unsubscribed

SMS compliance is evolving — and Recart is going beyond STOP and UNSUBSCRIBE keywords. We now use AI to detect unsubscribe intent in free-text replies, so messages like *"please stop texting me"* or *"I don't want these anymore"* are processed automatically, just like a standard STOP.

The system also catches stop-related emojis (🛑, ✋, 🚫) and common misspellings, while correctly ignoring short conversational replies ("Yes," "Ok," "Thanks"), 2FA codes, and automated carrier responses.

You'll see three updates in your account:

* **AI opt-out counts** on your Subscribers chart
* **Detection method and message** displayed on each subscriber profile
* **A toggle** to turn the feature on or off in Settings → SMS

Regulators increasingly expect brands to honor opt-out requests regardless of how they're worded. This feature ensures subscribers who express intent to opt out are always unsubscribed — reducing your compliance exposure from missed or ambiguous requests.

No setup required — it's live for all accounts automatically.


---

# 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://help.recart.com/latest-news/introducing-ai-powered-unsubscribe-intent-detection.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.
