TWO-STAGE REMINDERS & RESCHEDULE REQUESTS
Two reminders. A clear handover.
AI for appointment reminders sends two messages built from the booking itself: one roughly 48 hours before, and a shorter one around 2 hours before, pulled straight from your calendar or booking system. Replies can be classified and a suitable alternative slot proposed where the booking system supports it. The team confirms changes; unclear replies go to a person.
Updated
What you’ll find here.
Shows the exact two-stage trigger logic, 48 hours and 2 hours before a booking, as an actual flow you could rebuild in n8n or Make, rather than describing reminders in general terms.
- The 48h plus 2h staging and the reschedule-on-reply logic are laid out step by step, not just claimed
- The service-message versus marketing line is cited to ICO guidance and used to decide what a reminder may say
- Built on the documented Google Calendar API, which represents every booking as an event with a start time and attendees
The job, broken down.
- Reminding customers 48 hours before their booking
- Sending a shorter reminder around 2 hours before
- Reading replies and sorting confirmed, wants to move or cancelling
- Offering the next available slot when someone can't make it
- Updating the diary when a booking changes
The same job, handled.
| The task today | With AI doing the legwork |
|---|---|
| Someone phones or texts each customer the day before | Two reminders go out automatically, 48 hours and 2 hours before |
| A 'can't make it' reply is only seen once someone checks the phone | A reply can propose a suitable alternative, with the team confirming any change |
| A no-show is discovered when the slot is already lost | Unconfirmed bookings are flagged early enough for the team to call |
Built in steps.
Connect
We check the supported API or connector, licensing and update delivery. Before each send, the workflow rechecks booking status; cancellations, changed times and duplicate sends are tested before use.
Schedule two reminders
The illustrative timings are 48 hours and 2 hours before the current start time. The practice agrees appropriate timings and rules for bookings made after a reminder window has passed.
Read and offer
A reply such as 'can't make it' is read in plain English. Where the calendar has a slot that fits the same rules as the original booking, it is offered back to the customer; anything unclear is passed to a person.
Hand over
Your team can review the sending log and received replies. In this proposed scope, a person confirms a change before the diary is updated.
Do the maths.
A small clinic's reception phones or texts every next-day appointment by hand.
| Input or step | Value |
|---|---|
| Times a week | 60 |
| Minutes each time | 3 |
| People doing it | 1 |
| Cost per hour | £14 |
| Hours a year | 156 (about 21 working days) |
| Cost a year | £2,184 |
Illustrative inputs, not a client's figures: sixty reminders a week at three minutes each, handled by one person. Change the inputs to your own with the calculator. See how we calculate this.
These are illustrative workflow scopes. The audit checks the actual software, supported access, licences, permissions and human review rules before a build is agreed.
Why a reminder is a service message, until it is not
The ICO’s guidance on identifying direct marketing explains that data protection law and the electronic marketing rules do not stop a business telling customers what they need to know as part of their relationship with it, calling these service messages and naming appointment reminders as an example. The same guidance is equally clear that a service message becomes direct marketing the moment it also promotes something, even as a secondary purpose, so the two-stage sequence below stays deliberately neutral: it confirms, it reminds, and it never adds an offer.
The two-stage reminder, as an actual flow
The logic is simple enough to sketch out in full. The trigger is a booking’s own start time in the calendar or booking system.
- 48 hours before: a reminder goes out confirming the date, time and what to expect, with an easy way to reply if the customer needs to move it.
- 2 hours before: a shorter, same-day nudge goes out, mainly to catch the booking that has simply been forgotten in a busy day.
- On a “can’t make it” reply, at either stage: the reply is read, and if the calendar has an open slot that fits the same rules as the original booking (same service, same duration, same staff member if that matters), it can be proposed to the customer for reception to confirm. If nothing fits, or the reply is anything other than a straightforward reschedule request, it is flagged for a person.
Built in a platform such as n8n or Make, this is a scheduled trigger plus a webhook for replies, not a single “send a reminder” step, which is why timing both stages off the booking’s own start time matters: a reminder that ignores a last-minute change is worse than no reminder at all.
Where it sits in your booking process
Google’s own documentation on the Calendar API describes each booking as an event carrying a title, start and end times and a list of attendees, exposed through the same REST interface the Google Calendar interface itself uses. That is what lets both reminder stages, and the reschedule check, read the booking’s current details rather than a snapshot taken when it was first made. Many booking platforms expose the same information through their own API or through a connector platform, which is what the AI Opportunity Audit checks before anything is scoped.
The worked calculation on this page shows why this is usually one of the first jobs worth automating: the minutes per reminder are small, but they repeat every working day and fall on the busiest person in the building.
On the tools you already use.
- Google Calendar
- Microsoft Outlook calendar
- Calendly and similar booking platforms
- n8n
- Make
- Email and SMS sending services
Who needs it most.
What it costs.
Every price is published and fixed in writing before any work starts.
AI Opportunity Audit
In person across Leeds and West Yorkshire, or by video call. A written report of your top 5 automations, yours to keep.
AI Lead & Ops Sprint
Enquiry capture through to booking, follow-up and CRM logging, plus one ops automation. The monthly fee covers monitoring, tuning, a monthly review and up to 2 hours of changes.
Fractional AI Team
Ongoing AI builds, staff training and a monthly review.
Prices exclude VAT where applicable.
The build guarantee. We agree written acceptance criteria before any work starts. If the build doesn’t meet them, we fix it at no extra cost, and if we can’t, you don’t pay for it.
Where the facts come from.
- Identify direct marketingInformation Commissioner's Office
- Google Calendar API overviewGoogle for Developers
Questions, answered straight.
Why two reminders instead of one?
A reminder roughly 48 hours out gives someone time to rearrange without wasting the slot, and a shorter one around 2 hours out catches same-day forgetfulness. The workflow checks current booking status before each send. Update delays or failed checks require a defined pause and human review; the timings do not guarantee fewer missed appointments.
Do appointment reminders need marketing consent?
Under ICO guidance, messages that confirm or remind people about a booking are service messages, not direct marketing. That changes the moment a reminder also promotes an offer, at which point the marketing rules apply, so reminders built by Neura North are kept neutral.
What happens if someone replies 'can't make it'?
The reply can be classified and a suitable alternative proposed where the supported booking connection allows it. Reception confirms the change; unclear requests go to the team.
What does an appointment reminder automation cost?
A workflow like this is usually a fixed-price package agreed in writing before any work starts (most clients begin with the AI Opportunity Audit at £495, credited against a build). The Fractional AI Team at £1,500 a month covers ongoing work if you want it looked after. Prices exclude VAT where applicable.
Will it work with my booking system?
It works with calendars and booking systems that can share bookings, usually through an API or a connector platform such as n8n or Make. The AI Opportunity Audit checks your system before anything is quoted.
Where to go next.
The best reminder is one nobody had to remember.
Start with a 20-minute call.
Tell us the job that keeps coming back. We’ll tell you honestly what’s worth automating and what isn’t, and put a number on each one.