What are synthetic audiences?
Synthetic audiences are large-scale simulations of real people. We build them from your customer data or high-quality real-world data. The simulations are grounded in social science research and validated against real-world benchmarks. Query them directly through our platform and get answers to unanswered questions in seconds.
How accurate are they?
As accurate as traditional research methods. Our synthetic audiences match what real people say 96% of the time and have been independently validated by Professor Michael Muthukrishna at LSE. We measure this through hold-out testing: we generate synthetic responses, then compare them against real survey data the model has never seen. We have run tens of thousands of these evaluations. Every new audience is benchmarked this way before it goes live, and we communicate these benchmarks directly so you know exactly where the model is strong and where it has limits.
How do synthetic audiences work?
Human behaviour is shaped by a combination of individual circumstances, cultural background, and environment. Traditional research accounts for this by weighting survey samples by age, gender, and region - these are proxies for the factors that actually drive how people think and act. LLMs are trained on an enormous volume of human-generated text. That makes them, in effect, a model of human beliefs and behaviours across billions of people - the most comprehensive representation of collective human thought ever assembled. The problem is that this representation is averaged and opaque. When ChatGPT answers a question, it draws on everything, everywhere, all at once. It has no specific audience in mind and builds generic personas without real-world grounding. Electric Twin solves that problem. We use your real customer data - surveys, focus groups, and customer interviews - combined with machine learning to constrain and direct that broad human representation toward your specific audience. The result is a synthetic population that thinks, responds, and behaves like your actual customers.
How do you build a reliable model from limited data?
This is one of the first questions we work through with every client, and the answer is usually straightforward: if you have data on your audience, we can almost always build a reliable model from it. Your data anchors who the audience is — how they behave, what they think, who they are. The wider context comes from the models underneath, which carry a vast body of human knowledge, and the processes by which we build personas. Together they produce responses that hold up against real-world testing. The first conversation with our team is about what data you have, what shape it’s in and what we can build from it. We'll tell you upfront where the model will be reliable and where its limits are, so you know exactly what you're working with from day one.
How does Electric Twin integrate into my workflows?
Electric Twin is designed to slot into the way insight teams already work, not to replace it. The platform works as your always-on audience. You log in via the browser, ask questions, and get answers in seconds, the same way you'd structure a survey or a focus group. Outputs are designed to land in the formats your team already uses, with one-click export so findings can move straight into reports and stakeholder updates.
Is my data secure?
Electric Twin is ISO 27001:2022 certified, GDPR compliant and we are in the process of gaining our SOC2 accreditation. We have designed the system so it can operate in classified environments for government clients. Your data stays yours. It’s never used to train general models - or shared externally.
What can I use Electric Twin for?
Anything you'd ask real consumers. The most common uses are: - Concept and proposition testing. Reaction to new products, services, or features before you commit to development. - Messaging and creative testing. Run multiple messaging and copy variations past your target audience and see which version performs best. - Pricing exploration. Test how different price points land and where the value perception sits. - Strategic decision support. Understand motivations, trade-offs, and what would make people switch opinions. - Audience deep-dives. Explore segments, personas, and the drivers behind their behaviour. - Survey hard-to-reach audiences. With appropriate seed data, the platform allows you to engage deeply with niche segments, international markets, or emerging demographics that traditional research struggles to recruit. This enables businesses to extract more value from research into such populations.
What does it cost?
Electric Twin works on a simple licensing fee agreement that gives you unlimited queries. Once your audience is built, you can ask as many questions as you want without paying per query, per study, or per response. Pricing depends on the audience or audiences you need built and the number of seats across your team. We'll scope this with you in the first conversation. For context, clients running 1,500+ queries in six months have saved in the region of £300,000 compared to running that volume of work through traditional methods. The economics shift quickly when speed and iteration are no longer constraints as by per-study costs. More than one of our clients report that Electric Twin has enabled a 10x increase in their research capacity.
How is this different from ChatGPT or other AI tools?
ChatGPT, Claude and other AI tools generate plausible-sounding answers based on general training data. You get a bland composite of consumer opinion, which holds no context on your specific audience, no grounding in your actual demographics or behaviours, and isn’t validated against real-world research outcomes.