The science of what happens between humans and AI.
Validated measurement of psychological state, computed from language, independent of the model.
200+ dimensions — cognitive load, rapport, distress, wellbeing trajectory — traceable to 34,000 peer-reviewed citations. Deterministic scores in under 65ms, deployable on-prem.
34,000+
Peer-reviewed research citations
200+
Validated psychological dimensions
30+
Years of foundational research
<65ms
API response in production
AI systems continuously form judgments about the people they're talking to. Those judgments inform every response, and those responses influence how users think, feel, and behave.
The judgments are invisible. No one can check what was inferred, or catch it when it’s wrong. And asking the model what it inferred returns another output from the same process being examined, which is why the measurement has to come from somewhere else.
Receptiviti Labs is building the measurement layer for the human side of AI.
THE GAP
AI can tell you what the model did, but not how it impacts the user.
AI observability stacks are comprehensive on the model side. The interaction itself has none of that instrumentation — whether it's building the user's understanding or eroding it, fostering independence or dependence, all of it is left to inference.
Current tooling
What Receptiviti measures
THE ARCHITECTURE
One measured representation. Three consumers.
IN THE REQUEST PATH
The same representation, supplied back to the model.
Once psychological state exists as a measured variable, it can be supplied back as structured context, shaping the response without retraining. Because the score is measured rather than inferred, the value that influenced a response can be logged, reviewed, and reproduced.
+4%
Improvement in educational effectiveness
In a controlled test, GPT Study Mode was supplied with a validated 12-signal psychological vector as context. No retraining, no style prompts, only a measured read of the student's state was provided, derived from their prompt language. Across 25 blinded evaluations by five LLM raters, overall educational effectiveness improved 4%, with the largest gains in reasoning and scaffolding (+6.3%) and cognitive-load management (+5.9%).
WHERE IT FITS
The same representation, everywhere AI meets people.
Five applications across evaluation, inference, and governance:
EVALUATION & OBSERVABILITY
Eval stacks measure the model completely — traces, drift, faithfulness, hallucination rate. Receptiviti adds the psychological-state signal alongside existing model quality metrics.
ALIGNMENT & SAFETY
Foundation model teams need validated, external evidence of how interactions affect users over time — cognitive load, emotional trajectory, over-reliance. The measurement layer for socioaffective alignment: not inferred by the model being evaluated, but measured independently from language. The same signal can catch distress or overload that the model's own inference misses, and trigger escalation or handoff.
COMPANION & LONG-HORIZON AI
Products built for ongoing relationships need to know whether those relationships are helping or harming — therapeutic alliance, dependency signals, distress escalation, wellbeing trajectory.
ENTERPRISE AI DEPLOYMENT
Resolution rates and CSAT tell you what happened after the fact. Fed back into the model, psychological-state measurement changes what happens next — tone, pacing, and support calibrated to the person in the moment, not just scored once the conversation is over.
GOVERNANCE & RESPONSIBLE AI
Impact assessments require measurement that is validated, traceable, and independent of the model being assessed — grounded in peer-reviewed science, structured for documentation.
OUR POSITION
Four things we think are true.
01
Human agency is the variable AI systems are least equipped to protect. ​​
​
Delegating reasoning, judgment, and decision-making to AI can erode those capabilities over time. A system can only introduce protective friction if it can measure how its interactions are affecting the user's cognition in the moment, and over time.
03
What AI infers about you is invisible to the systems meant to check it.
​​​
AI systems continuously infer psychological signals from the people using them. That inference happens between input and output, exactly where standard evals don't look, yet it influences every response. Measuring it from the outside turns the model's hidden read of the user into something you can inspect. It's one of the most tractable ways of understanding what these systems are inferring.
02
The signals that matter most are the ones no one is measuring.
​​
Every conversation carries linguistic signals of cognitive load, emotional state, and distress. Models already respond to these signals through inference — but that inference stays inside the model, where no one can see what it concluded or check whether it was right
04
True alignment and safety require measuring what's happening to each user, across time.
​​
A system optimized for the average user is misaligned with almost every actual user. Alignment needs to become user-specific. A system that can't see the impact it's having on a user doesn't have the safeguards needed to keep users safe, and probably shouldn't be operating autonomously.
WHY EXPLICIT MEASUREMENT
What explicit psychological state measurement gives you that inference cannot.
The problem with inference
Implicit and unauditable
When a model infers psychological state, that state never becomes an observable variable. It influences behavior without being visible, citable, or challengeable.
Prompt-sensitive and unstable
LLM-based inference shifts unpredictably across model versions and phrasings — the same conversation yields different inferences on a different day.
Circular — the model grading itself
Asking the model being evaluated to assess its own impact on the user is not independent measurement. It's the model grading itself.
What Receptiviti provides
Structured, observable variables
200+ dimensions derived from language — explicitly computed, consistent across runs, independent of model behavior. Observable, auditable, citable.
Version-stable
Derived from validated psycholinguistic frameworks built over 30 years, not from prompt-dependent inference. The same input yields the same score.
34,000 citations
Every dimension traceable to peer-reviewed science. The kind of evidence that holds up in research, in product decisions, and in accountability conversations.
Trapped inside the model
Whatever the model infers stays in its own computation. It influences its response but never becomes something anything downstream can use or inspect.
Actionable
A clean signal the system can act on — logged for review, or fed back into the model as context to shape the next response.
WHY IT WORKS
Stable representations require stable measurement.
A representation that changes every time the underlying model changes cannot serve as an independent reference for evaluation, longitudinal measurement, or governance.
Receptiviti computes psychological state from a validated psycholinguistic framework developed over three decades of research, producing reproducible measurements that remain comparable across models, deployments, and time.
BUILT ON THREE DECADES OF VALIDATED PSYCHOLINGUISTIC SCIENCE
Dr. James W. Pennebaker — Co-founder and Chief Science Officer
​
Regents Centennial Professor, University of Texas at Austin. Creator of LIWC — the foundational psycholinguistic framework at the core of Receptiviti's measurement science. The three decades of research that made this possible.
ACTIVE RESEARCH
We publish. We contribute.
Receptiviti's team and academic advisors publish peer-reviewed research on the psychological dimensions of language and human behavior. Receptiviti also conducts its own research and experiments, contributing to the questions AI safety, alignment, and evaluation teams are actively working on.
PUBLISHED: PNAS Nexus, 2024
Large language models display human-like social desirability biases in personality surveys
Salecha, Ireland et al.,2024. Large language models display human-like response biases when they infer they are being evaluated, with effects up to 1.20 human SD across GPT-4, Claude 3, Llama 3, and PaLM-2. Co-authored by Molly Ireland, Receptiviti.
​
PUBLISHED: Perspectives on Psychological Science, 2026
Artificial intelligence and the psychology of human connection
Boyd & Markowitz, 2026. Introduces the MIRA model - a theoretical framework for when and how AI functions as a relational entity in human ecosystems. Language is the primary modality through which that relationship operates. Co-authored by Ryan Boyd (UT Dallas), academic advisor to Receptiviti.
​
SCOPED
Providing measured user state as context to customer support AI
This study asks whether customer service agents provided with real-time measured psychological state produce better resolution outcomes and lower escalation than agents working from inference alone.
PUBLISHED: npj Mental Health Research, 2025
Psychosocial dynamics of suicidality and nonsuicidal self-injury: a digital linguistic perspective
Entwistle, Hoemann, Nightingale & Boyd, 2025. Large-scale naturalistic study of the language dynamics surrounding suicidality and self-injury in 992 individuals with borderline personality disorder (66,786 posts). Co-authored by Ryan Boyd (UT Dallas), academic advisor to Receptiviti.
​
INTERNAL STUDY
Providing measured psychological state as context to educational AI
GPT Study Mode: Providing psycholinguistic signals produced a +4% improvement in overall educational effectiveness across 25 blinded evaluations. Largest gains in reasoning & scaffolding (+6.3%) and cognitive-load management (+5.9%).
SCOPED
Psychological state as a missing dimension in AI evaluation
The case for human-state signals as a first-class eval criterion alongside accuracy, helpfulness, and harmlessness.
​
