Skip to content
Workflow demo · appointments

Let a customer find and request the right appointment after hours

A customer choosing at 9 PM should not have to wait for tomorrow's callback.

A Business MCP workflow for salons, med spas, dental offices, clinics, and other appointment businesses. It answers approved questions, finds a real slot, and routes anything sensitive to a person.

ChatGPT, Claude, or GrokBooking calendarCRM / intake formStaff review queue
The scenario

A prospective client asks ChatGPT for a consultation next week. The front desk is offline and the customer is comparing several providers.

Four-step walkthrough

The AI moves the request. Your rules decide how far.

01 · Trigger

The customer asks for a service and time

The connection identifies the requested service, location, new-or-returning status, and timing preference.

02 · AI action

Approved answers and real availability come back

The AI uses the current service menu, policies, provider rules, and calendar. It does not answer clinical questions or improvise eligibility.

03 · Existing system

The appointment or consult request lands where staff already work

Simple services can book directly. Complex services create a review-ready intake with the requested time held when policy allows.

04 · Human boundary

Clinical, custom, and exception cases stay human

Medical advice, contraindications, discounts, package exceptions, and sensitive cancellations route to staff.

Example conversation
Customer

Do you have a consultation after 5 next Thursday?

Business AI

I can check the live calendar. Is this your first visit, and which service are you considering?

Customer

First visit. I want to discuss laser treatment.

Business AI

There is a 5:30 PM consultation. I can hold it and send the intake form. Treatment eligibility and pricing are confirmed by the provider at the consult.

Approval boundary

What the AI cannot decide

The AI may book approved appointment types and send intake. It cannot provide medical advice, guarantee results, override eligibility rules, or negotiate price.

Expected outcome

A better handoff, not a magic claim

The customer leaves with a real next step and the business receives structured intake instead of an after-hours message.

Acceptance test

The build is accepted against observable behavior.

Delivery is not based on a revenue promise. Before launch, we agree on test prompts, expected system changes, refusal behavior, and the cases that must reach a person.

Test 01
Request a standard appointment in an open window.
Pass: The booking is created with the correct service, duration, customer details, and confirmation.
Test 02
Ask a clinical or contraindication question.
Pass: The AI states the boundary and routes the question to an authorized person.
Test 03
Ask for a discount or an unavailable provider.
Pass: It does not override the approved menu or calendar and offers the allowed next step.
Do not deploy yet if
  • ×A business whose appointments already book cleanly online with no response-time gap
  • ×A practice unwilling to define which questions and services require human review
Make this specific

Get the exact map, boundary, and test for your business.

Start free if you are still choosing the first workflow. Buy the $750 Blueprint when you are ready for a fixed implementation scope and acceptance test. The Blueprint is credited in full toward a build started within 30 days.