Production client system (In real use)

WhatsApp Appointment Booking Automation

Bookings were coming in on WhatsApp, which is where the customers already are. The problem was that every booking was a conversation somebody had to hold manually, from “are you free Thursday?” all the way to the confirmation.

Status
Production client system
Area
Lead Qualification & Appointment Booking
Workflow
7 steps · 4 failure paths
Stack

01 · Why it mattered

What the manual way was costing

  • Replies depended on whoever was holding the phone, so response time was all over the place.
  • Calendar and chat could disagree, which is how you get double bookings.
  • Reschedules and cancellations were easy to miss in a busy chat.

02 · System concept

What I set out to build

I wanted the customer to just chat like normal, and the system to work out what they want, check real availability, book it and confirm it. Changes should update the same booking, not create a mess.

03 · Before / after

From manual steps to a system

Toggle between the manual process and the system. Click any step to see what it does, what tools it touches, and what happens if it goes wrong.

How it ran manually · depends on whoever is free

  1. 01Customer sends a message on WhatsApp asking to bookby hand
  2. 02Someone reads it whenever they get a chanceby hand
  3. 03They open the calendar and check what is freeby hand
  4. 04Back and forth with the customer until a time worksby hand
  5. 05Booking is entered by hand, confirmation typed by handby hand
  6. 06Reschedules and cancellations start the whole thing againby hand

04 · Decision log

Why I built it this way

D-01WhatsApp first, not a booking page

The customers were already on WhatsApp. Sending them to a separate booking link is one more step where people drop off, so I kept the whole thing inside the chat.

D-02Calendar is the source of truth

I made Cal.com the thing that decides what is free. The bot never promises a slot the calendar hasn’t confirmed, because a wrong confirmation is worse than a slow one.

D-03Reschedule and cancel are first-class

Booking is the easy part. Most of the mess in a manual process comes from changes, so I treated reschedule and cancel as proper paths, not afterthoughts.

05 · Reliability layer

What can go wrong, and who steps in

Where it happens
Step 02 Understand intent
What goes wrong
Message is unclear or not about booking
What the system does
The bot asks a clarifying question instead of guessing, and if it still can’t tell, the chat is flagged for a staff member.
Who handles it
A person: staff

Human-in-the-loop points

  • Human in the loopMessage is unclear or not about booking → staff
  • Human in the loopCalendar API fails while booking → me / staff
  • Human in the loopReschedule request but no matching booking → staff

06 · Evidence

What exists today

  • Running in production for a client.
  • Handles booking, confirmation, reschedule and cancellation in the same conversation.

07 · What this demonstrates

What this demonstrates

Taking a conversation that used to need a person on every step and turning it into a system that holds up in real use, with the unclear cases still going to a human.

08 · Stack / integrations

What it’s built with

  • n8nOrchestrates the conversation logic and integrations
  • WhatsApp Cloud APICustomer channel, inbound and outbound messages
  • Cal.comAvailability, bookings, reschedules and cancellations

Architecture · static view · 7 steps · 4 failure paths

    • → staffMessage is unclear or not about booking
    • → system handlesNo availability for the requested time
    • → me / staffCalendar API fails while booking
    • → staffReschedule request but no matching booking

More systems

Keep reading

Proof of concept

AI Customer Support Assistant

Classifies incoming customer messages, answers from the knowledge base, escalates when needed and keeps the ticket updated.

  1. Customer message
  2. Intent
  3. Retrieval
  4. Response
  5. Resolve or escalate
  6. +2 more
2 failure paths · 2 human handoffs
Workflow build / implementation

E-commerce Order-to-Delivery Automation

Every order gets one record that follows it from fulfilment to rider to doorstep, and the customer hears what is happening without having to ask.

  1. New order
  2. Order record created
  3. Fulfilment
  4. Rider assigned
  5. Delivery update
  6. +1 more
3 failure paths · 3 human handoffs

Similar workflow?

Got a process that looks something like this?

Tell me how it runs today and where it hurts. If it’s a good fit for automation I’ll tell you how I’d approach it. If it isn’t, I’ll tell you that too.

Tell me what you’re trying to automate