Scientific foundations

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.

Whether AI supports how people think and decide

Most AI evaluation measures technical performance: accuracy, robustness, reasoning, policy compliance. A 2026 preprint co-authored by our founder argues that this misses something a human-facing system does every time it speaks. It shapes how a person understands their situation and what they decide to do next.

The paper names that missing dimension psychological competence:

“The capacity of a human-facing AI system to support user cognition, emotional interpretation, and behavioural decision-making in ways that are appropriate to the user, context, and purpose.”

It sets out the properties this depends on, including framing, tone, perceived authority, and how a system communicates uncertainty, and proposes a conceptual framework and assessment methods rather than a single benchmark. It comes from the same programme of work behind PromptSafe: deciding what good conversational AI behaviour looks like before trying to measure it.

This work is at preprint stage and has not been peer reviewed. We publish it openly so the approach can be examined and challenged while it is still taking shape.

We measure evaluators. We do not assume they are correct.

An evaluator is a measurement instrument. Small changes in its wording can produce very different results, so we treat evaluator design as an engineering problem that can be measured rather than guessed.

PromptSafe applies the same evidence-based methodology when developing evaluator templates and when working with enterprise customers to develop evaluators for their own AI systems.

In practice, that means treating evaluator development as a disciplined process:

1. 1Define the behaviour
   We start by defining the behaviour we want an evaluator to measure.
2. 2Build multiple evaluators
   We create alternative evaluator designs rather than assuming the first version is correct.
3. 3Compare against reference examples
   Where appropriate, we compare candidate evaluators against expert-rated examples to understand which performs most reliably.
4. 4Improve using evidence
   Evaluators are version controlled and refined over time as more evidence becomes available.

When evidence is insufficient, we record it as insufficient rather than assuming an evaluator is correct. Evidence accumulates over time as evaluators are used, tested and improved.

The same methodology underpins our Enterprise Evaluator Engineering.

Grounded in academic collaboration

Our founder is an honorary senior lecturer in the Faculty of Medicine at Imperial College London 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.