Fixed quote after a free call

An AI receptionist for HVAC, plumbing and electrical companies

We build an AI receptionist for your phone line, website chat or text number that answers when the office is busy or closed. It says it is automated, answers questions about service areas, hours, pricing policies and maintenance plans from your approved wording, collects job details and books requests into your field service software, and hands any danger, emergency or complaint to a person at once. Projects typically cost $2,500 to $7,500 and take five to eight weeks.

The problem

What an AI answering service for trades should and should not do

Answering services and receptionists cost money, and calls still go unanswered at lunch, in the evening and during the first cold or hot week of the season. Many calls are routine: do you cover my area, what does a service call cost, can someone come tomorrow, do you service my brand.

An AI answering service for plumbers or HVAC companies is only safe if it is narrow. It must answer from your own rules, never diagnose or give repair instructions, and treat any mention of gas, carbon monoxide, sparks or flooding as an emergency for a person.

What we build

What our AI receptionist for HVAC and plumbing includes

Approved answer library

Service areas, hours, call-out and diagnostic fee policies, maintenance plans and brands serviced, written and approved by you.

Phone, chat and text

An AI voice line for overflow and out-of-hours calls, plus the same assistant on website chat or a text number.

Job intake and booking

Collects name, address, equipment and problem, then books a request or slot in the field service software.

Emergency hand-off

Danger words trigger your safety instructions and a live transfer or alert to the on-call technician.

Clear AI disclosure

It says it is an automated assistant and offers a person at any time.

Call review

Recordings or transcripts with summaries, and a weekly list of questions it could not answer.

Who does what

Automation does the chasing, people make the calls.

Every step is marked: what runs on its own, what a member of staff reviews and what stays with a person who decides.
  1. 01 Automated

    Call or chat

    A customer calls or chats and is told they are talking to an automated assistant.

  2. 02 Automated

    Answer from your rules

    Routine questions are answered from your approved library.

  3. 03 Automated

    Job captured

    Job details are collected and a request or slot is booked.

  4. 04 Office or dispatcher review

    Office confirms

    The office confirms bookings and calls back anything unresolved.

  5. 05 Technician or owner decides

    Emergencies and diagnosis

    Emergencies go to the on-call technician; diagnosis is done by a qualified tech on site.

How it behaves

How the AI receptionist behaves

What each person sees and what runs in the background, including what happens when something goes wrong.

What the customer sees

  • An instant answer with a clear note that it is automated
  • Short answers from your approved wording
  • A booked request or slot and a confirmation text
  • A person straight away for emergencies

What the office sees

  • New booking requests with job details
  • Emergency transfers and alerts logged
  • A weekly list of unanswered questions

What the automation does

  • Answers only from the approved library
  • Refuses diagnosis and repair advice
  • Logs and summarises every conversation

Edge cases and fallbacks

Caller reports carbon monoxide alarm
Safety instructions and a live transfer or alert to on-call; no booking flow.
Question not in the library
It says it does not know and books a call-back.
Angry or complaining caller
Offered a person straight away and flagged to the owner.
AI or telephony outage
Calls fall through to voicemail and the owner is alerted.

Architecture

An AI receptionist for a trades business at a glance.

The setup we usually start from. We adapt it to the phone system and practice software you already use.
Customer Call, chat, text Assistant service Voice and chat Language model Claude, Gemini, GPT Approved answers Areas, fees, plans Job request Into FSM On-call tech Emergencies Call log Weekly review
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 A customer calls or chats and is told they are speaking with an automated assistant.
  2. 2 The service retrieves your approved answers and passes them, with fixed rules, to the model.
  3. 3 Routine questions are answered and job details are booked as a request in the field service software.
  4. 4 Emergencies go to the on-call technician at once, and every conversation is logged for review.

Project planner

How the project runs, phase by phase.

Typical durations for a first version. Your proposal lists the exact phases, dates and what you sign off at each step.

AI receptionist & answering service project plan

Typical time to launch: about 6 weeks, then support

  1. 01

    Discovery

    About 1 week

    Real calls and questions, emergency policy, booking rules and what the assistant may say.

  2. 02

    Answer library

    About 1 week

    Approved answers, safety instructions and hand-off wording.

  3. 03

    Build

    About 2 weeks

    Voice line, chat or text, retrieval, FSM booking, transfers and call log.

  4. 04

    Test

    1 to 2 weeks

    Real, tricky and emergency test calls; the owner signs off before launch.

  5. 05

    Launch

    2 to 3 days

    Start with out-of-hours calls only, then add overflow during the day.

  6. 06

    Support

    Ongoing

    Weekly call review at first, then monthly answer updates.

What it runs on

Real products only, connected through the access each vendor provides. See all integrations

Claude, Gemini or OpenAI models Twilio Voice or a voice AI platform n8n AI Agent node or Laravel ServiceTitan, Housecall Pro or Jobber API Website chat widget SMS or Slack for on-call alerts

Cost estimate

What it costs, line by line.

Estimates to plan with. Your fixed quote follows a free call, once we have seen your systems and volumes.
  • Discovery and answer library

    Real calls collected, answers written and approved.

    $500 – $1,200

  • Build

    Voice line, chat or text, retrieval, booking and transfers.

    $1,200 – $4,000

  • Integrations

    Field service platform, telephony and alerts.

    $300 – $1,000

  • Testing and evaluation set

    Real, tricky and emergency test calls.

    $300 – $900

  • Launch and training

    Out-of-hours soft launch and team walkthrough.

    $200 – $400

  • Total project estimate

    $2,500 – $7,500

Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. A voice line costs more to build and run than chat. Model usage and telephony are billed to your accounts directly.

Monthly running costs you pay directly

Estimates from the vendors' published pricing, checked November 2026. Billed to you by each vendor, never marked up.

  • AI model and voice usage: Billed by the providers per minute or per use; voice costs more than chat.
  • Telephony: Twilio at its published rates for numbers and call minutes.
  • Hosting: n8n Cloud from about €20 a month, or your own server.

What pushes cost up

  • Systems without an API, or with integration access that must be requested from the vendor
  • Writing data back into your core system rather than only reading from it
  • Several locations, brands or very different processes to support
  • Custom apps, dashboards or a voice line on top of the workflows

What keeps cost down

  • One location and one clear process to start with
  • Cloud software with a documented API
  • Using tools you already pay for instead of adding new ones
  • Approved wording and sample data ready at the start
Get a fixed quote

Privacy and consent

Rules we design for, with the sources.

General information to plan with, not legal advice. Your counsel or data protection adviser confirms what applies to your practice.

EU: tell people they are talking to AI

Article 50 of the EU AI Act requires AI systems that interact with people to inform them they are interacting with AI, from 2 August 2026. We add the disclosure everywhere.

Source: artificialintelligenceact.eu

US: artificial voice calls

The TCPA rules cover calls using an artificial or prerecorded voice, so the assistant answers inbound calls and any outbound calls need the right consent.

Source: www.law.cornell.edu

UK: gas safety stays with registered engineers

Work on gas fittings must be done by a Gas Safe registered engineer, so the assistant never gives repair instructions and routes gas concerns to a person.

Source: www.hse.gov.uk

How we deliver

Agile delivery, in 1 to 2 week sprints.

We deliver in short Agile sprints using Scrum, so you see working software every one or two weeks instead of waiting for a big reveal at the end.

Every sprint

  1. 1 Sprint planning. At the start of each sprint we agree which backlog items we will finish, each with written acceptance criteria you can check.
  2. 2 Daily stand-up. A short internal check-in on progress and blockers. You get a written update in your Slack or Teams channel, not another meeting.
  3. 3 Sprint review and demo. At the end of each sprint we demo what was built on test data or in a shadow run, and you accept it or ask for changes.
  4. 4 Retrospective. The team looks at what went well and what to change in the next sprint, and we share anything that affects you.

How scope stays under control

Product backlog
Every feature, fix and question in one prioritised list you can see at any time.
Acceptance criteria
Plain-language conditions for "done" on each item, agreed before work starts.
Change requests
New ideas go into the backlog with an estimate. Nothing changes scope or price without your written approval.
User acceptance testing (UAT)
Before launch your team tests the real workflow against the acceptance criteria and signs off.

Tools we use

Jira, ClickUp or Trello for the backlogSlack or Microsoft Teams for updatesGitHub for code and version historyLoom or a live call for demos

Project manager / Scrum master

Runs the sprints, keeps the backlog and timeline honest, and is your single point of contact.

Business analyst

Maps how the work runs today, writes the workflow specification and acceptance criteria with your team.

Automation engineer

Builds the n8n workflows, integrations, AI steps and error handling.

Backend developer

Writes custom code where a no-code step is not enough: APIs, data sync, secure storage.

Frontend / mobile developer

Builds forms, booking pages, dashboards, web apps or Android apps when the project needs them.

QA engineer

Tests every workflow against the acceptance criteria, including edge cases and failure paths.

DevOps engineer

Sets up hosting, access, backups, monitoring and alerts, and the deployment pipeline.

Who does what at each phase

Free call
Project manager, business analyst
Understand the problem, check it is worth automating and outline a rough range.
Discovery
Business analyst, automation engineer
Map the current process, systems and data, and agree success measures.
Design
Business analyst, automation engineer, backend developer
Write the workflow specification, data flows, compliance notes and backlog with acceptance criteria.
Sprints
Automation engineer, developers, QA
Build, test and demo in 1 to 2 week sprints; you accept or adjust after each demo.
UAT and launch
QA, DevOps, project manager
Your team tests and signs off, we switch on, monitor closely and train the team.
Support
Automation engineer, DevOps
Stabilisation window, then optional monthly care with monitoring and changes.

A point of contact

One person who can answer questions and approve decisions, with about an hour a week during the project.

Access

Admin or API access to the systems involved, created as separate accounts with the least access needed.

Sample data

Real but non-sensitive records (or de-identified ones) so we can design and test against reality.

Approved wording

Message templates, policies and consent wording (for SMS, your opt-in and opt-out text) reviewed by you.

Vendor agreements

Signed agreements with the software vendors that will handle personal data, such as a BAA or processor contract.

Time for testing

A few hours from the people who will use the system, for the demos and user acceptance testing.

Working system

Workflows, integrations and any apps running in your accounts, under your keys.

Documentation

Workflow specification, data-flow map, run book and exported workflow files.

Training

A walkthrough for the team and a short recorded video for new starters.

Handover

All access, credentials and code handed over; you can keep us or take it in-house.

Stabilisation window

Fixes for anything that does not meet the agreed acceptance criteria after launch.

Support options after launch

  • No plan

    You run it yourselves after the stabilisation window and contact us when you need a change.

  • Monthly care

    Monitoring, error alerts, small changes and updates each month, with an agreed response time.

  • Priority care

    Faster response times for business-critical workflows and a monthly review call.

How a project moves through our team

Free call PM and analyst Discovery Process and data Design Spec and backlog Sprints Build, test, demo Your review Accept or adjust UAT and launch Sign-off, go live Support Monitor and improve
  • Input
  • Logic and services
  • People
  • Output
  • Data

How it flows

  1. 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
  2. 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
  3. 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
  4. 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.

FAQ

AI receptionist for HVAC and plumbing questions questions, answered.

It is an automated assistant that answers your phone or chat when the office cannot, using your own approved answers. It books service requests into your field service software and sends emergencies to a person.

It answers instantly, follows your rules exactly and books straight into your system, and it costs less per call. A call centre handles complex conversations better. Many firms use AI for overflow and out of hours and keep people for the rest.

No. It collects the symptoms in the customer's words for the technician. It never diagnoses or suggests repairs, and danger words go straight to a person.

Yes, through their APIs where your plan includes API access. We usually start with booking requests the office confirms, then allow direct booking once the team trusts it.

Yes. It says so at the start and offers a person at any time. In the EU that is required under the AI Act from 2 August 2026.

Measure calls answered, jobs booked, emergencies transferred and how long they waited, and questions it could not answer. We review calls weekly at first.

Free 20-minute call

Want this for your heating, plumbing & electrical?

Book a free 20-minute call. We will look at how the work runs today, tell you honestly whether it is worth building and give you a fixed quote if it is.

Book a free 20-minute call