Thousands of AI-agent shoppers, calibrated against real sales — not surveys. We simulate what people buy, not what they say, so you can test any price, product, or promotion before you commit.
A calibrated digital twin of your category — believable agents, anchored to real data.
Your category sales — products, prices, units. Or public/syndicated data. Even a few weeks is enough to start.
LLM-agent shoppers weigh brand, attributes and price and choose — the way real buyers do, one decision at a time.
Individual choices aggregate into shares, elasticities and substitution — the structure of your market, simulated.
We tune the model to your real sales, then you run any what-if: price, assortment, promo, AI-channel — decision-grade.
We tested the engine against real market data with a held-out design, so it can't be curve-fitting.
| Dataset | Elasticity sim vs real | Raw sim | + calibration (held-out) |
|---|---|---|---|
| Nevo cereal (IO textbook) | −2.5 vs −3.9 | r = −0.35 | r = +0.44 |
| dunnhumby real supermarket (pizza) | −2.51 vs −2.51 | r = +0.05 | r = +0.64 |
The simulation supplies the price mechanism (worth the most where you have no data); calibration supplies the brand levels from your data. Together: decision-grade.
One engine, three answers your team makes decisions on.
Own- and cross-price elasticity, promo lift, and exactly who you steal share from — or lose it to.
Add, drop, or launch a SKU — with cannibalization, including products that have no sales history yet.
Are you found when shoppers and agents ask AI what to buy — and what agentic commerce does to your demand.
The synthetic-consumer field asks agents what they'd say in a survey. We calibrate agents to what people actually bought — the difference between believable and accurate.
| Others (Simile · Aaru) | Avanti | |
|---|---|---|
| Anchored to | stated preference — surveys, interviews | revealed preference — real sales |
| Validated by | reproducing survey answers (self-retest) | recovering real market shares it never saw (r 0.64) |
| Founder DNA | CS / HCI / ML | agents + microeconomics (demand estimation) |
| Output | opinion distributions | decision-grade price & share counterfactuals |
The field's own critique — "individually believable, collectively wrong" — is only answered by calibrating to what people actually bought.
Drag a price. Watch thousands of agents re-decide. See who wins.
Open the live simulator →