Scientific foundations
An ongoing research programme in conversational AI evaluation.
PromptSafe is built on an evolving programme of behavioural science, evaluation methodology, and empirical research designed to improve how conversational AI is evaluated.
As conversational AI becomes part of healthcare, finance, education, and customer support, organisations need evaluation methods that are transparent, reproducible, and grounded in evidence rather than subjective judgement.
Why behavioural science
AI that talks to people does more than return information. It influences behaviour, sometimes in ways that are harmful or misleading even when the system is technically accurate. These effects are rarely measured by standard testing.
Our founder, Dr Paul Sacher, set out the case for this in a 2026 open letter, co-authored with leading behavioural scientists:
“Even when technically accurate, AI systems can influence behaviour in ways that are harmful, misleading, or misaligned with people’s interests.”
The letter was published on behalf of the Behavioral AI Institute, where Dr Sacher is a co-founder and research director.
PromptSafe was created to translate behavioural science into practical, scalable methods for evaluating conversational AI.
The missing discipline in AI: a call for behavioural science. Wellcome Open Research, 2026.
Read the paperMeasuring conversation quality
FAST, a framework co-authored by our founder and published in Frontiers in Digital Health, evaluates conversations across four dimensions:
- FidelityDoes the agent follow evidence-based behaviour-change practice, not just hand over information?
- AccuracyIs what it says correct, current, and within scope?
- SafetyDoes it recognise risk and signpost to a professional when it should?
- ToneIs it empathic, non-judgemental, and pitched at the right level?
PromptSafe draws on published evaluation research, including the FAST Framework, alongside behavioural science, software testing principles, and ongoing methodological research.
Think FAST: a framework to evaluate fidelity, accuracy, safety, and tone in conversational AI health coach dialogues. Frontiers in Digital Health, 2025.
Read the frameworkHow much confidence should a score carry?
A quality score only means something if there is sufficient evidence behind it. We are developing the Evaluation Evidence Framework (EEF), a transparent methodology for quantifying confidence in AI evaluation results. Rather than asking only “How well did the AI perform?”, EEF also asks “How much evidence supports that conclusion?” This work is currently in development and will be published as it matures.
An ongoing research programme
PromptSafe improves continuously through the PromptSafe Research Programme, drawing on anonymised and aggregated evaluation data held in the PromptSafe Research Dataset, under the PromptSafe Research & Data Governance Framework. Data is processed using appropriate deidentification and governance safeguards, and is never published in a way that identifies individual customers or users.
Over time, this programme will support benchmark reports, validation studies, peer reviewed publications, and improvements to PromptSafe’s evaluation methodologies.
Our aim is not only to apply published research, but to contribute new methodologies and evidence that advance the evaluation of conversational AI.
Grounded in academic collaboration
PromptSafe is used in research grant applications led by academics at Imperial College London. Our founder is an honorary senior lecturer in its Faculty of Medicine and a collaborator at the Health Impact Lab there.
The Health Impact Lab works to close the gap between health research and real-world adoption, applying implementation science to move evidence-based innovations beyond academia and into patient care. Turning research into impact is the same goal PromptSafe is built to serve: turning behavioural science into evaluation that teams actually use.
Where this is heading
- PublishedFAST framework
- TodayPromptSafe platform
- In developmentEvaluation Evidence Framework
- NextValidation studies
- FutureIndustry benchmarking
Planned parts of the programme
These components will expand the PromptSafe Scientific Foundations programme over time.
- Coming soonValidation studiesIndependent and internal studies testing the reliability of our evaluation methodologies.
- Coming soonBenchmark reportsAggregated, anonymised findings on how conversational agents perform across behavioural dimensions.
PromptSafe is helping advance the science of conversational AI evaluation.
Our research programme is ongoing. The published research described on this page has been peer reviewed. Other methodologies, including the Evaluation Evidence Framework (EEF), are under active development. We are explicit about the status of each.