AI support desk for construction firms and tradespeople
Between two jobs, nobody answers the clients asking for an intervention date, a document or news about their snag list. The agent answers routine requests on its own by reading your schedule and files, and hands over the rest with context.
In your day-to-day
- 01
Answers to visit or intervention requests using the slots actually open in your schedule.
- 02
Sending requested documents — insurance certificates, handover reports, invoices — without tying up the office.
- 03
After-sales or snag-fixing request pre-qualified: photos, location, description, passed to the works supervisor.
A typical scenario
Ten employees, heating season starting: a plumbing-and-heating firm takes around forty calls and emails a day, and the owner returns calls in the evening from the van.
- 01
On a Friday at 7 PM, a boiler breakdown lands through the website form: the agent collects the model, the error code displayed and a photo of the rating plate.
- 02
A client asks about her annual service: the agent answers with the date set in the contract, and offers a slot if the due date is close.
- 03
A tenant writes on behalf of the landlord: the agent identifies the right file and requests the required approval before any billable call-out.
What changes
Requests arrive documented instead of as garbled voicemails, and the owner’s Saturday morning stops being a phone shift.
Order of magnitude
Working assumptions
- →35 requests a day in season
- →6 out of 10 are routine questions — slots, contracts, certificates
- →5 minutes of handling each
21 requests absorbed a day at 5 minutes apiece is about 1 h 45 of front-office time saved daily — close to 8 hours a week handed back to the office.
Indicative estimate built on average sector assumptions — it gets recalibrated on your actual volumes during scoping.
What eats your days
- →
Progress payments and final accounts settle months late, and retention money ends up forgotten.
- →
The office drowns in email — supplier invoices, tenders, after-sales requests — while everyone is on site.
- →
A project’s real margin only surfaces at the final account, when nothing can be fixed anymore.
How it works
- 1
The agent learns your business
It is fed your real sources: FAQ, documentation, ticket history, business rules. It only answers what it can source — no improvising.
- 2
Autonomous resolution, fenced
Recurring requests — tracking, invoices, procedures — are resolved end to end. Anything outside the fence goes to the human queue with a sourced draft reply already written.
- 3
Supervision and continuous improvement
Every conversation is reviewed by our engineers in the first weeks. The autonomous-resolution rate rises as the agent earns reliability — never the other way round.
Typical results
60%
of tickets resolved with no human involved, observed in production
3 min
first response, 24/7
×3
handling capacity for the same team
Orders of magnitude observed in production; your diagnostic sets your own baseline and targets.
Frequently asked questions
Can the agent promise a client an intervention date?+
It only offers slots that are open in your schedule, under rules you approve. Outside that frame, it takes the request and passes it on — it never promises a date you could not keep.
Our residential clients call more than they write — is it still useful?+
Yes: the agent covers email, the website form and WhatsApp, which absorbs a good share of requests — and the office, relieved of the repetitive, answers the phone better.
Is this the problem eating your team’s time?
Tell us how you work today — 30-minute call, then a free written diagnostic of what this agent would change for you, with numbers.
Get my free diagnosticFree resource
Get the self-assessment grid for your sector
Sales, admin, support, operations: the 20 tasks AI agents already handle in SMEs — with, for each one, the tell-tale sign that your team is concerned.