> For the complete documentation index, see [llms.txt](https://answeringservicecare.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://answeringservicecare.com/docs/ai/ai-features/ai-dispatcher.md). # AI Dispatcher Our agents still call your on-call team. The AI Dispatcher is one more way to do it: it phones your on-call person, reads them the message, and records that they got it. Our agents have always called your on-call team when a message can't wait, and they still do. The AI Dispatcher is one more way to make that call. It phones your on-call person as soon as a message is ready, reads them the message, and records that they got it. If they don't confirm, your escalation moves to the next step, the same way it does today. ### What your on-call person hears {% stepper %} {% step %} ### A call from a number they know The call comes from your answering service number. If they miss it and call back, they reach our agents on your line. {% endstep %} {% step %} ### A quick check that it's them The AI Dispatcher says who it is calling for and confirms it is speaking with the right person before it shares anything. {% endstep %} {% step %} ### Your message, read clearly It reads the details you chose for that person, such as the caller's name, callback number, reason for calling, and answers from your script. {% endstep %} {% step %} ### Answers to their questions They can ask what else came in over the last 24 hours and whether each item has been handled. {% endstep %} {% step %} ### Confirmation, or a person They press 1 or say they got it, and the message is marked acknowledged in your portal with a short excerpt of the call. If they would rather talk to someone, they can ask, and the call is transferred to our agents. {% endstep %} {% endstepper %} ### Set it up In the Client Portal, open **Oncall Calendar**, select the person, add a delivery method, and choose **AI Assistant**. Then fill in: * **Contact Name**, **Country**, and **Phone Number** * **Extension** (optional): digits to dial after the call is answered * **Message details sent to the AI Assistant**: which message and script fields to read. Your account information, notes, and FAQs are always included. * **Machine Detection**: choose **AMD Premium** * **When Voicemail Picks Up**: hang up, or leave a short message Then select the new delivery method on that person's on-call events, like any other delivery method. ### Voicemail and privacy * Your message is never read to a voicemail. If voicemail answers, the AI Dispatcher either hangs up or leaves a short message with only who is calling and the number to call back. * The AI Dispatcher uses AMD Premium machine detection. It tells a person from a voicemail before it speaks, and it gets through iPhone call screening. * A voicemail can't confirm a message, so your escalation keeps going. * Numbers with an extension skip machine detection, because a phone system's greeting can sound like a voicemail. * AI Dispatcher calls are not recorded. * If someone else on your team already confirmed the message, the AI Dispatcher doesn't call. ### Turn it on The AI Dispatcher is available on accounts with AI answering, and it uses AMD Premium machine detection. Contact your account manager or . ### Related * [How AI answers your calls](/docs/ai/how-ai-answering-works/how-ai-answers.md) * [Get started with AI](/docs/ai/ai-answering-overview/get-started.md) * [Oncall calendar](https://answeringservicecare.com/docs/app/client-portal/oncall-calendar) --- # 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://answeringservicecare.com/docs/ai/ai-features/ai-dispatcher.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.