As of 13 August 2026, AI can only partly send automatic appointment reminders.

What to actually do

1. Hand it to a person

   The route this page recommends

   A person who owns the outcome does this end to end, worth it when the failure is dear.

2. Use a tool built for this

   Second choice

3. Do it yourself

   The distant third

   A chat interface, power-user skill, and roughly 1 hour until you can act on the result.

   How to actually do it

   1. Open the booking or calendar system and the email or messaging service you intend to use, then record their exact names, available integrations, appointment fields and account permissions.
   2. Gather the reminder timings, time zone, cancellation and rescheduling rules, contact details to use, and the wording customers should receive, including an opt-out or contact route where appropriate.
   3. Paste those details into the prompt and ask the chatbot to produce the workflow, field mappings, configuration steps and test plan without inventing unsupported platform features.
   4. Create the workflow in a test environment or with test accounts, using sample customer records and the minimum permissions needed rather than live customer data.
   5. Create test appointments for a new booking, changed booking, cancellation, missing contact detail, duplicate trigger, time-zone edge case, failed delivery and opt-out, then compare each result with the expected behaviour.
   6. Check the message recipient, appointment details, timing, sender identity, delivery log and duplicate prevention for every test before enabling the workflow for real bookings.
   7. Enable the workflow for a small controlled set of appointments, monitor its logs and failed deliveries, and send the final reminder wording and operating instructions to the colleague responsible for the booking system.

   Prompt

   Design an automatic appointment-reminder workflow for a UK business.
   
   Appointment system: [name and available integration or API]
   Reminder channel: [email, SMS, WhatsApp or other]
   Trigger: [when an appointment is created, changed or approaching]
   Reminder timings: [for example, the chosen intervals before the appointment]
   Required appointment fields: [date, time, time zone, customer name, contact details, service and location]
   Business rules: [cancellation, rescheduling, no-contact, duplicate-booking and opt-out rules]
   
   Produce:
   1. A plain-English description of the workflow.
   2. The exact steps to configure it in the named systems.
   3. Any code, API requests, field mappings or expressions required.
   4. Reminder templates with clear placeholders and an opt-out or contact route where appropriate.
   5. A test plan covering a new booking, changed booking, cancellation, missing contact detail, duplicate trigger, time-zone edge case, failed delivery and opt-out.
   6. A list of permissions, secrets and customer data the workflow needs.
   
   Do not invent API names, field names, permissions or platform features. Mark anything that must be confirmed in the platform documentation. Do not send anything or claim the workflow is live. Keep customer data out of the example and use test records only. Put the steps that prevent duplicate or wrongly addressed reminders first.

   Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.