How AI books real appointments while you sleep
A plain-English walkthrough of what happens during one AI-handled phone call — from the first ring to the SMS confirmation. No jargon, no magic, just the actual mechanics.
Most people who hear "AI receptionist" for the first time picture either a chatbot (text on a screen) or the menu-driven phone trees they remember from 2005 ("press 1 for hours…"). The actual thing is neither. It's a conversation, in real-time, indistinguishable from a person to most callers until they're told.
Here's what actually happens during one call — start to finish, no jargon.
The call, step by step
It's 8:47pm on a Tuesday. Sarah has a kitchen sink leaking and calls Mike's Plumbing. Mike is at his daughter's hockey game.
0 — 1 second: pickup
The phone rings once. Cedri answers in Mike's voice profile with the greeting Mike set up: "Hi, you've reached Mike's Plumbing — how can I help?"
1 — 8 seconds: understanding the request
Sarah says "my kitchen sink is leaking and I need someone out as soon as possible." Cedri parses that as three things in parallel: the service type (plumbing emergency, residential), the urgency (high), and an implicit appointment request.
8 — 18 seconds: checking the calendar
While still on the call, Cedri queries Mike's calendar (Google Calendar in this case — it works with Microsoft 365 too) and finds the earliest available slot that matches the service type. Mike has a 10am-12pm window tomorrow that's flagged for emergency calls. Cedri offers it: "I can have someone there tomorrow between 10 and noon — does that work for you?"
18 — 25 seconds: confirming details
Sarah agrees. Cedri asks for her address, her phone number for the confirmation SMS, and a one-line description of the problem to help Mike prepare. None of that is a form — it's just the rhythm of a normal phone conversation.
25 — 30 seconds: booking + confirmation
Cedri creates the calendar entry, marks it as confirmed, and triggers two SMS messages: one to Sarah ("Mike from Mike's Plumbing will be at 42 Elm St between 10am-12pm tomorrow. Reply STOP to cancel.") and one to Mike ("New booking: Sarah, 42 Elm St, kitchen sink leak. Tomorrow 10am-12pm.").
Sarah hangs up with a real appointment. Mike sees the booking notification at intermission, knows what to bring, and goes back to the game.
Total elapsed time on the call: 30 seconds. Total elapsed time for Mike: zero. He didn't even know it happened until the SMS arrived.
The pieces under the hood
There's no magic — just three well-understood technologies wired together:
- Speech-to-text + text-to-speech.Modern versions (the ones Cedri uses, like ElevenLabs and Cartesia) process audio in real time with sub-200ms latency. The voice is natural enough that 80% of first-time callers don't immediately notice they're talking to an AI.
- A language model.The model is given your business's context (services, hours, prices, FAQs) and told its job is to handle inbound calls. It doesn't improvise — it's constrained to your data and a small set of allowed actions (book, reschedule, answer FAQ, transfer urgent calls to your cell).
- Integrations. Google Calendar, Microsoft 365, and the popular booking platforms (HouseCallPro, ServiceTitan for trades) are read/written live during the call. SMS via Twilio, email via Resend.
What it doesn't do
Worth being honest about the boundaries. An AI receptionist is not:
- A general-purpose assistant.It does inbound calls. It doesn't do email triage, social media replies, or anything outside its trained scope.
- A replacement for human judgement on hard calls. When a call is genuinely complex (a hostile customer, a legitimate emergency, an edge case), it forwards to your cell. That's the right outcome — you'd rather handle five escalations a week than miss every call.
- A magic upsell engine.It books what people ask for. It doesn't aggressively sell add-ons. (If you want that, you want a sales team, not a receptionist.)
Why this works now and didn't two years ago
Two things changed. Voice models got fast enough (under 300ms round-trip latency) that conversations stopped feeling robotic. And language models got reliable enough at constrained tasks ("only book real slots from this calendar") that you could trust them with real customers. Before 2024 either of those would have wrecked the call quality.
Frequently asked
- Does an AI receptionist sound robotic on the phone?
- The current generation of voice models (ElevenLabs, Cartesia) produce speech indistinguishable from a human for most callers — under 200ms latency, natural intonation. About 80% of first-time callers do not immediately notice they are talking to an AI.
- What happens if the call is too complex for the AI?
- It transfers to your cell phone. The AI is configured to forward genuinely difficult calls (hostile customers, edge cases, real emergencies) to a human — that is the correct outcome, not a failure.
- How does the AI know my business?
- On setup, it reads your website to learn services, hours, and pricing. You can also feed it your FAQ document or have it learn from existing call recordings. It does not improvise — it answers from your data.
Cedri picks up. Books the job. Live, in one call.
Click the orb on the homepage and try a real demo call — works in 60 seconds.
See Cedri in actionKeep reading
How much do missed calls really cost a Canadian small business? (2026 data)
A 30-second math problem with a five-figure answer. We break down what one missed call actually costs across plumbing, dental, salon, and HVAC — with real Canadian numbers.
AI receptionist vs answering service vs voicemail: who actually books the job?
All three pick up the phone. Only one closes the loop. A side-by-side breakdown for Canadian SMBs — what each option does, what it costs, and the right pick for your business.