For healthcare & clinics
More appointments, and the proof it was Avarto.
Patients ask hours, insurance, and "do you treat…" — then leave. Avarto answers and routes them to real booking.
What the assistant does on a healthcare & clinics site
Answers hours, location & accepted-cover questions
Routes to your real booking flow
Captures enquiries after hours
Guardrailed: never gives medical advice — answers logistics, routes to a clinician.
See which experiments moved appointments
Each experiment runs against a randomized holdout. The bar is the 95% confidence interval — never a bare point estimate. Green helped, red hurt, slate isn’t yet significant, and a sample too small to trust is labelled “not enough data” instead of a confident wrong number.
Appointments lift vs holdout, by experiment
The bar is the 95% confidence interval; the dot is the point estimate; the line at zero is the holdout baseline. A “✓” marks a statistically significant result.
Illustrative — based on the demo store, not a real customer result.
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 appointments would have done with no experiments at all; the gap is the illustrative lift Avarto adds.
Appointments vs holdout, across two campaigns
The shaded area is appointments 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.
What moved
Illustrative — based on the demo store, not a real customer result.
Grounded answers, measured causally
Answers are grounded in your own content, and a holdout group never sees the assistant — so you measure the appointments it actually added, not the ones it happened to sit near.
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.