> For the complete documentation index, see [llms.txt](https://docs.welkinhealth.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.welkinhealth.com/care/communication/ai-autolink.md).

# AI Autolink

## Overview

Welkin's AI Autolink feature automatically matches incoming unrecognized communications to the most likely patient contact based on the message content and context. When AI links a communication, care team members see clear visual indicators and can confirm, reassign, or override the suggestion.

***

## AI Suggested badge

When a communication has been linked to a patient by AI (rather than manually by a care team member), an **AI Suggested** badge appears:

* In the **communication list** — the chip is displayed beneath the message preview for that conversation.
* In the **message thread** — the badge appears next to the sender's name on each individual message (SMS, email, or call) that was AI-linked.

The badge is styled with a star icon and the label **"Suggested"**. Hovering over it shows the tooltip **"Linked by AI"**.

***

## Linking panel — AI-suggested patient

When you open the **Link** panel on an AI-linked communication, Welkin automatically pre-selects the patient contact that AI suggested. The contact card for the suggested patient displays a highlighted **"AI matched the message to the selected person based on its context."** notice.

If the communication already has a patient contact linked (manually or by a previous AI suggestion), the action button in the Link panel reads **Reassign** instead of **Link**, making it clear you are changing an existing link rather than creating a new one.

***

## Accepting or overriding the AI suggestion

| Action                         | What to do                                                                                           |
| ------------------------------ | ---------------------------------------------------------------------------------------------------- |
| **Accept the suggestion**      | Confirm the pre-selected patient is correct, then click **Link** (or **Reassign** if already linked) |
| **Choose a different patient** | Select a different contact from the list, then click **Link** / **Reassign**                         |
| **Search all patients**        | Enable **All Patients** mode to search beyond the suggested matches                                  |

Once you manually link or reassign a communication to a different patient, the AI suggestion for that specific AI turn is dismissed and will not be re-offered.

***

## Notes

* AI Autolink is a licensed feature that must be enabled for your environment. Contact your Welkin administrator or Customer Success Manager to enable it.
* AI suggestions are based on message context; they are not guaranteed to be correct. Always review the suggested patient before confirming.
* The **AI Suggested** badge is display-only — it does not affect communication delivery or patient record access.

***

## Related Topics

* [Manage Unrecognized Communication](/care/communication/manage-unrecognized-communication.md) — manually linking communications to patients
* [Communication Center](/care/communication/communication-center.md) — overview of all communication channels
* [Inbox](/care/communication/inbox.md) — inbox management and filtering
* [AI Assistant](/care/ai-assistant.md) — the interactive AI chat panel


---

# 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.welkinhealth.com/care/communication/ai-autolink.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.