200k calls/month · 67% booking rate vs 77% human
24/7 AI Agent Call Center: 200k Calls a Month Across 60 US HVAC Brands
Voice agents orchestrating 200,000 calls a month across 60 US HVAC brands for a 5,000-person enterprise, booking 67% of calls against 77% for human agents — within 10 points of a trained team, around the clock. Built as a product, an AI front desk that answers, books and routes, not a pilot.
The problem
For an HVAC brand the front desk is the business: a missed call is a missed booking, and after-hours and peak-hour calls went to voicemail that most callers never leave. Across 60 brands under one 5,000-employee US enterprise, staffing every shift for that volume was hard to justify, and leaving it unanswered cost real business.
What we built
An AI front desk that runs the call centre 24/7: real telephony with barge-in handling so callers can interrupt naturally, booking, rescheduling and cancelling against live availability, answers only from what each brand has approved, and tool-calling into live systems so the agent can look things up and write back rather than just talk.
Before
- Night and weekend calls unanswered
- Staffing every shift hard to justify
- A demo bot is not a call centre
How it works
Answer on real telephony. Callers reach the agent on the phone line and can interrupt it mid-sentence, as they would a person.
Book against real availability. It checks the live calendar, then books, reschedules or cancels directly in the scheduling system instead of taking messages.
Say only what is approved. Questions are answered from what each brand has approved, never improvised.
Hand over with context. When confidence drops, the call moves to a person with the context already written down.
Test on real transcripts. Every release is regression-tested against real call transcripts before it ships.
Trace every call. Each call is traced end to end, so a 3am failure is findable the next morning.
After
200k calls/month · 67% booking rate vs 77% human
Stack
Voice AIAI AgentAI ReceptionistSchedulingTelephonyEnterpriseWhy it holds up
Production is a different problem from a demo. This one ships with defined handoff to a human when confidence drops, regression tests over real transcripts before every release, and tracing on every call so a 3am failure is findable the next morning. It is live inside the business, not piloted in a sandbox: 200,000 calls a month across 60 HVAC brands, with a 67% booking rate against 77% for the human team.
Related service: Forward-deployed AI engineers
More case studies
Big 4 client · fully on-premise
Enterprise RAG Chatbot for a Big 4 Accounting Firm
Multimodal retrieval over a Big 4 firm’s full compliance library, tuned for citation instead of summary — every answer arrives with its source paragraph attached.
- Juniors reading thousands of pages per question
- Seniors acting as search engines
US$1M collected in the first 3 months
AI Payment Collection and Reminders
The companion product to the AI front desk: it chases unpaid invoices with polite, timed reminders and a payment link, and stops the moment the customer pays or replies. It collected over US$1 million for the client in its first three months.
- Chasing payment is awkward and late
- Billable time lost to collections
Ask the EDI in plain English
Natural-Language EDI for a US EDI Solutions Vendor
Business users ask questions of raw X12 — “what are the net terms on invoice 4471?” — and get answers in plain English, from a Llama 3 model fine-tuned on EDI and grounded in the parsed transactions.
- Business and EDI teams speak different languages
- Rejected transactions decoded by hand
Get started
Talk to the engineer who will build it.
You will speak with me directly. Bring the use case, the data and the constraints, and I will give you a straight view on feasibility, effort and the first thing to ship.
