Solutions · Teams building agents, digital twins and simulations
AI and simulation builders
A grounded population to sample agents from, from a synthetic population you can check first. Every answer comes with its interval, who said what, and why.
What you ask
A population to sample agents from that matches official statistics instead of a prompt, and a way to check how close a simulation is to real people.
What you get
A declared population to sample agents from, ninety attributes each with its source, and a calibration record to compare your own simulation against; a demo shows a run end to end.
Questions to start with
Each opens an answer from a representative sample of the population, with its interval, who said what, and why.
What would adults in New York do with an unexpected $1,000: save it, pay off debt, spend it, or invest it?Would adults in Arizona give up their car if public transport were free?How many close friends do adults in New York say they have?
Other solutions
Market and opinion researchTest survey items before the field workConsumer brands and product teamsWillingness to pay, choices, conceptsMedia and advertisingAudience size and response, by placePublic policy and governmentHow a policy lands, by region and groupAcademic and social researchPilot instruments, draw reproducible samplesHealth and public healthPopulations by condition and habit, by state