Artificial intelligence is fundamentally transforming how pollsters gather public opinion, with a French start-up called Naratis spearheading efforts into what promises to be a faster, cheaper alternative to conventional polling approaches. The company, founded in 2025 by 28-year-old engineer Pierre Fontaine, deploys conversational AI agents to perform detailed conversations with respondents, eliminating the time-consuming work that has long characterised qualitative research. Rather than asking people to tick boxes, Naratis’s AI engages citizens in genuine dialogue designed to explore not just what they think, but how they think. The technology purports to provide results significantly quicker and at a tenth of the cost of conventional polling, whilst maintaining 90 per cent accuracy—a significant breakthrough as the polling industry contends with declining participation levels and growing public distrust.
The Growth of Interactive Polling
At the heart of Naratis’s innovation lies a seemingly straightforward concept: substituting the transactional character of traditional surveys with genuine conversation. When a participant answers the phone, they meet a youthful, energetic AI voice asking open-ended questions about politics, society and their personal views. Rather than mechanically recording answers, the system engages in genuine conversation. Three separate AI agents work simultaneously behind the scenes—one making sure the participant stays on topic, another probing for deeper insights when answers seem superficial, and a third confirming the person is genuine and not a bot gaming the system. This layered approach converts polling from a box-ticking exercise into something considerably sophisticated and insightful.
The efficiency improvements are remarkable. Traditionally, qualitative research required weeks of meticulous work: recruiting small panels of respondents, carrying out one-to-one interviews, documenting spoken exchanges, and then reviewing data for patterns and meaning. Naratis collapses this timeline using what Fontaine describes as “parallelisation”—multiple AI agents performing interviews at the same time rather than interviewers operating in sequence. A study that once took weeks and many thousands of euros can now be accomplished in one or two days. Responses often arrive within 24 hours, permitting campaigns, government bodies and groups to react to breaking news and shifting public sentiment almost in real time, radically transforming the speed of polling work.
- AI agents perform concurrent interviews across numerous participants
- Live analysis flags shallow answers needing deeper exploration
- Fraud screening prevents bot activity and dishonest responses from skewing data
- Results delivered within hours as opposed to multiple weeks of traditional research
Pace and Effectiveness Reshape Research Surveys
The survey sector confronts an fundamental threat. Response rates have plummeted from over 30% in the 1990s to below 5% today, according to AI consultant Stéphane Le Brun. This sharp fall has created a vicious cycle: fewer respondents mean increased expenses per finished questionnaire, which in turn renders studies less reflective of the broader population. Confidence in polling has diminished accordingly, with many viewing surveys as unreliable or intrusive. Against this backdrop, conversational polling powered by AI provides a lifeline, possibly reversing years of declining engagement by rendering the research process itself more appealing and interactive.
Naratis contends its AI-driven approach achieves outcomes that are “10 times quicker, 10 times cheaper and 90% as precise as human polling.” These figures, if validated independently, would represent a seismic shift in the way organisations grasp public opinion. The financial savings by themselves are transformative: a thorough qualitative investigation that once required tens of thousands of euros and several weeks of labour can now be conducted for a fraction of the price in days. This democratisation of access could enable smaller entities, grassroots campaigns and community organisations to conduct rigorous opinion research formerly available only to well-funded institutions.
Parallelisation: A Revolutionary Approach
The innovation enabling these gains is remarkably uncomplicated: parallel processing. Rather than human interviewers performing interviews in sequence—one conversation after another—AI agents work simultaneously across numerous respondents. This scaling of capacity without equivalent expense growth fundamentally alters the economics of polling. Where standard qualitative approaches required patience and significant investment, AI-driven approaches compress timescales whilst lowering expenses, permitting businesses to obtain rich, detailed understanding on demand.
Accuracy Claims and Industry Scepticism
Naratis’s claim that its AI methodology delivers 90% accuracy matching human polling has understandably attracted scrutiny from established researchers. The polling industry, developed through decades of procedural improvement, remains cautious about claims that machine learning can replicate the subtle discernment of experienced human interviewers. Critics doubt that conversational AI can genuinely identify the delicate interpersonal signals, hesitations and unspoken cues that experienced practitioners use to explore more thoroughly respondent motivations. The company has failed to produce peer-reviewed studies validating its accuracy claims, with independent verification still outstanding.
Beyond concerns about accuracy, industry observers are concerned about potential biases built into AI systems themselves. If the algorithms powering Naratis’s conversational agents are trained on skewed datasets or programmed with untested presumptions, those flaws could consistently skew results across thousands of interviews. Additionally, respondents may change their conduct when interacting with machines rather than humans, either growing more forthright or more guarded based on their comfort with technology. These technical and psychological variables are largely unexamined ground, and their effect on polling reliability stays unclear.
- Independent verification of precision assertions is still pending from established research institutions
- Potential algorithmic biases could consistently skew results across large-scale AI polling operations
- AI-human engagement dynamics may influence the way respondents articulate authentic views and beliefs
The Synthetic Data Challenge
As AI polling scales up, a troubling question arises: how will regulators and the public differentiate between genuine human responses and synthetic data generated by the very systems running the polls? The speed and efficiency that makes AI polling attractive also creates opportunities for distortion. If an dishonest actor were to augment genuine responses with computer-generated data, the final dataset could appear statistically robust whilst bearing little resemblance to actual voter sentiment. The technology’s opacity exacerbates the problem—most voters would struggle to understand how algorithms aggregate and authenticate responses, making it hard for them to trust the findings shaping political discourse.
Naratis claims its systems feature fraud prevention systems, with one AI agent specifically assigned with identifying whether respondents are real people or automated systems. However, this security feature itself relies on AI evaluating AI, producing a self-referential flaw. As interactive AI develop greater complexity, differentiating genuine human conversation from synthetic responses may be technically unachievable. The polling industry has historically possessed public trust partly because its processes are fundamentally transparent—people provide responses, results are tallied. AI polling threatens to undermine that openness, displacing transparent procedures with algorithmic black boxes that scarcely anyone can properly evaluate.
Confidence and Compliance Concerns
Regulators in Europe are only now come to terms with AI’s role in opinion research and political polling. Currently, few explicit safeguards govern how AI systems gather, analyse and present polling data. Lacking strong governance structures, the industry confronts a crisis of credibility if artificial information contaminates published results or if systematic biases systematically skew findings. French data protection regulators and the European Union’s AI Act regulatory bodies must immediately create standards ensuring transparency, auditability and accountability in algorithmic polling processes before the technology becomes entrenched in political processes.
The Hybrid Evolution of Consumer Insights
Despite the efficiency improvements AI polling offers, industry experts suggest that human and machine-driven studies will likely coexist rather than one replacing the other entirely. Traditional polling methods have weathered decades of scrutiny and remain integral to political institutions, regulatory frameworks and public understanding. Companies such as Naratis recognise that AI excels at speed and cost efficiency, yet human interviewers bring irreplaceable nuance—the capacity to detect fine emotional signals, adjust questions instinctively and build rapport that promotes candid responses. A measured strategy combining both methodologies could yield richer insights whilst preserving the openness voters increasingly expect from research shaping electoral discourse.
The shift to hybrid models, however, necessitates precise adjustment. Pollsters must establish clear protocols for the circumstances under which AI data should be given weight alongside conventional methods, and the way conclusions should be shared to make clear to the public which methods generated which conclusions. Preparing emerging researchers to operate proficiently alongside AI systems creates further difficulties, as does setting industry benchmarks that oversee the technology’s implementation. If managed thoughtfully, this evolution could breathe new life into survey methodology by enhancing efficiency and reach whilst maintaining the human judgment and ethical oversight that uphold democratic discourse.