For service businesses & trades
Turn visitors into quote requests and bookings.
Avarto answers questions about your services and guides visitors to the next step — but only to the real actions your site already offers. It grounds itself in your contact, quote, and booking forms, and never invents one.
It won’t invent a way to contact you
A generic chatbot might confidently tell a visitor to “use the online booking portal” you don’t have. Avarto can’t: it only guides visitors to the actions it discovered on your actual site. No phantom forms, no dead-end instructions.
How site-action grounding works
Avarto learns the real actions on your site and ties every “next step” it suggests back to one of them.
- 1
It discovers your real actions
When Avarto learns your site, it finds the actions you actually offer — your contact form, quote request, and booking page — and the fields each one needs.
- 2
It grounds answers in those actions
The assistant only ever points visitors to actions that exist on your site. If you don't offer online booking, it won't pretend you do.
- 3
It guides the visitor to the right one
When a visitor is ready, the assistant routes them to the matching action — "request a quote" for a job, "book a call" for a consult — and helps them fill it in.
- 4
It hands off cleanly
The visitor completes your real form, so the lead lands wherever your forms already go. No new inbox, no parallel system to check.
What a guided conversation looks like
The assistant answers the question, then offers the matching action on your site — and helps the visitor complete it.
Example conversation
Illustrative example — the assistant guides to the quote form this site actually offers, and never invents one.
The campaign loop: a ratchet, not a one-off test
Optimisation isn’t a single A/B test — it’s a programme that compounds. Inside each shaded experiment band the line wobbles as variants win and lose; when the experiment ends you apply the winners as normal site behaviour and the line settles and holds. Run a second experiment and the cycle repeats — even dipping while a losing idea is live — but its learnings push the metric to a new high, above where the first round left it. The holdout line shows what quote requests would have done with no experiments at all; the gap is the illustrative lift Avarto adds.
Quote requests vs holdout, across two campaigns
The shaded area is quote requests with Avarto; the dashed line is the holdout (no experiments), held flat at the baseline index of 100. The dashed-edge bands mark each live experiment period (“begin ┄ end”) — where the line wobbles; between them the winning learnings are applied and the line holds, then climbs.
Illustrative — based on the demo store, not a real customer result.
- 1
Hold-out
A randomized slice of visitors never sees an experiment. That flat line is your true baseline — the counterfactual every later gain is measured against.
- 2
Experiment period
Inside the shaded band the line wobbles week to week — some variants win, some lose. That noise is the programme working, not failing: you're learning what actually moves the metric.
- 3
Learnings applied
When the experiment ends, the proven winners become permanent site behaviour. The wobble stops and the line settles — and the lift holds instead of snapping back to baseline.
- 4
Repeat — and climb
The next experiment period wobbles again (sometimes it even dips while a losing idea is live), but once its learnings are applied the line steps up to a new high — above where the last round left it.
Grounded in your own content
Avarto answers from your site and the services you list, with citations — so it describes the work you actually do, not a generic version of it.
Avatar-optional, one script tag
Run text-only or add an animated avatar with voice. Install directly or via Google Tag Manager with no other site code change.