> 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/release-notes/readme/oct-16-2026-ai-call-to-dos.md). # Oct 16, 2026: AI Call To Dos Your AI assistant can now make calls for you: collections, confirmations, reminders, and follow-ups, on a schedule or from your own systems. To Dos already let you reach people by call, text, and email. Now your AI assistant can make the call. Set up an AI Call To Do, and the assistant phones your customer, has the conversation, and lets you know how it went. ### What you can do * **Hand routine calls to your assistant.** The calls that follow a known script: collections, confirmations, reminders, and follow-ups. * **Make every call personal.** Add details such as the customer's name, an amount due, or an appointment time, and the assistant uses them in the conversation. * **Skip the voicemail mix-ups.** Machine detection tells a person from a voicemail, so the assistant never talks over a greeting. It hangs up or leaves a short message based on your preference, and AMD Premium gets through iPhone call screening. * **Hear about every call.** If a voicemail answers and the assistant doesn't speak, you get a message saying so, delivered like any other message. * **Run it your way.** Call once, on a recurring schedule, or from your own software through the To Dos API. ### Ways to use it * **Collections and past-due reminders.** Call with the customer's balance and due date filled in. Pair it with [Payment AI](/docs/ai/ai-features/payments.md) and the assistant can text a secure payment link so the customer pays before the call ends. * **Appointment confirmations and reminders.** Confirm tomorrow's visits, collect reschedule requests, and cut no-shows. * **Renewals and payment reminders.** Reach customers before a policy, contract, or subscription lapses. * **Lead and quote follow-up.** Call new inquiries back within minutes. Create the To Do from your website form or CRM through the [To Dos API](broken://spaces/HYs4Yy4CzlfUTSGjj9O1/pages/XDnLsgOtWTcegCY86TS9) or Zapier. * **Check-ins and satisfaction calls.** Follow up after a service visit, delivery, or support case. * **Calls in your customer's language.** With [Multilingual AI](/docs/ai/ai-features/multilingual.md), the assistant can hold the conversation in more than 80 languages. ### Works with your other AI features * [**Payment AI**](/docs/release-notes/readme/sep-29-2026-payment-ai.md): take a payment on the call with a secure link by text. * [**Multilingual AI in 80+ languages**](/docs/release-notes/readme/sep-6-2026-multilingual-ai.md): talk with customers in their own language. * [**AI Dispatcher**](/docs/release-notes/readme/oct-8-2026-ai-dispatcher.md): for urgent messages to your on-call team, the AI Dispatcher calls them and records that they got it. ### Why it matters Our agents are here for the calls that need a person, around the clock. Many outbound calls simply need to happen on time, every time. AI Call To Dos give you a quick, cost-effective way to make those, so your team can focus on the conversations that need them. ### Get started AI Call To Dos are available on accounts with AI answering. To set one up, contact your account manager or . For details, see [To Dos](/docs/features/to-dos.md) and [Create a To Do](broken://spaces/HYs4Yy4CzlfUTSGjj9O1/pages/XDnLsgOtWTcegCY86TS9) in the API reference. --- # 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/release-notes/readme/oct-16-2026-ai-call-to-dos.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.