> 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/manage-unrecognized-communication.md).

# Manage Unrecognized Communication

## Overview

Unrecognized communications are inbound messages (SMS, email, or calls) received by your Welkin system from phone numbers or addresses that do not match any existing patient record. Welkin surfaces these in a dedicated queue so care teams can resolve them appropriately.

## Accessing Unrecognized Communications

1. Navigate to **Communication Center** (or **Messages**)
2. Look for the **Unrecognized** or **Unmatched** tab/section
3. All inbound messages without a matched patient record are listed here

> **Note:** The unrecognized voice calls queue includes all unrecognized calls, including any that were previously deleted or archived. This ensures no inbound contact attempt is permanently hidden from the queue.

## AI Autolink

If your organization has AI Autolink enabled, Welkin may automatically match an incoming communication to a patient contact based on the message content. When this happens:

* An **AI Suggested** badge appears in the communication list and on individual messages in the thread.
* When you open the **Link** panel, the suggested patient is pre-selected and a notice explains that AI matched the message based on its context.
* You can accept the suggestion, choose a different patient, or search all patients.

See [AI Autolink](/care/communication/ai-autolink.md) for full details.

## Resolving an Unrecognized Communication

For each unrecognized message, you have several options:

### Match to an Existing Patient

1. Click **Match to Patient**
2. Search for the patient by name, date of birth, or other identifiers
3. Confirm the match
4. The communication is linked to that patient's record and moved out of the unrecognized queue

### Create a New Patient Record

1. Click **Create New Patient**
2. Pre-fill the patient details using the information from the message
3. Complete the required fields and save
4. The communication is linked to the new patient record

### Archive / Ignore

If the message is spam or otherwise irrelevant:

1. Click **Archive** or **Dismiss**
2. The message is removed from the active queue and stored for audit purposes

## Reassigning a Linked Communication

If a communication is already linked to a patient (by AI or manually) but needs to be moved to a different patient:

1. Open the communication and click **Link** in the context panel
2. The panel opens with the current patient pre-selected and the action button labeled **Reassign**
3. Search for and select the correct patient
4. Click **Reassign** to update the link

## Preventing Unrecognized Communications

To reduce unrecognized messages:

* Ensure patients have current, verified phone numbers and email addresses in their records
* Configure duplicate detection settings in the Admin portal
* Remind patients to communicate from their registered contact information


---

# 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/manage-unrecognized-communication.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.