Trade AI Playbook

62-tech HVAC contractor lifts after-hours capture from 23% to 96% with a voice agent

"Northbridge HVAC" (name anonymized by the vendor) · Greater Boston, MA, US ·

What they did

After 5 p.m., calls used to hit a voicemail box cleared the next morning. A voice agent now qualifies each call (no heat, no cool, maintenance, estimate), writes a structured job into ServiceTitan, pages the on-call tech for true no-heat emergencies below 50 F, and queues a human callback by 9:15 a.m.

Reported results

  • After-hours capture 23% to 96% in the first 30 days
  • Booked jobs +41% versus the same period the prior year
  • About 14 dispatch-supervisor hours a week reclaimed
  • $1.4M 'recovered pipeline' in 90 days (vendor's calculation)

Tools

Visiologic voice agent, ServiceTitan, Twilio, HubSpot

Cost

Not disclosed

Source

Visiologic: https://www.visiologic.ai/case-studies/regional-hvac

Vendor case study (results reported by the vendor). The vendor says the company name is anonymized at the client's request. Source checked 2026-10-20. Results are as reported by the source, not independently audited.

Try it yourself: starter prompt

Our suggested prompt for an AI assistant (ChatGPT, Claude, Grok or your phone-agent tool). It is not from the source.

You answer calls for an HVAC company between 6 PM and 8 AM. Ask what's happening, decide if it's an emergency using these rules: [list your emergency rules]. If it is, page the on-call tech with the address and issue. If not, offer the next two open morning slots and confirm by text.

Related use cases