COMPANION & LONG HORIZON AI
Know whether an AI relationship is helping or harming users — over time.
Derived from language. Independent of engagement metrics.
Products built for ongoing relationships need to know whether those relationships are beneficial. Receptiviti measures the psychological trajectory of the relationship — session by session, across time — from the language itself.
Production API · Containerized on-prem deployment available.
THE CORE TENSION
Engagement and wellbeing are not the same signal.
Engagement metrics — session length, return rate, messages sent — tell you whether users keep coming back. They do not tell you whether coming back is good for them. These signals can move in opposite directions, and without measurement, you cannot know which way they are going.
A strong, trusting relationship between a patient and human provider — the therapeutic alliance — is one of the most reliable predictors of successful treatment outcomes. Relationships with AI systems are one-sided, even if the user perceives otherwise.
APA Health Advisory on the Use of Generative AI Chatbots and Wellness Applications for Mental Health, November 2025
WHAT RECEPTIVITI MEASURES
The signals that determine whether an AI relationship is beneficial over time.
Scored from language — session by session and longitudinally — giving you a structured, auditable view of how the relationship is actually evolving.
WELLBEING TRAJECTORY
Is the user better or worse over time?
Emotions, distress signals, anxiety, cognitive load, and negative affect tracked longitudinally across sessions. Identifies whether psychological state is improving, stable, or declining — the signal engagement metrics cannot provide.
DEPENDENCY & ATTACHMENT
When does engagement become over-reliance?
Dependency appears in language before behavior. As cognition is outsourced to AI, confidence and analytical thinking decline while inward focus rises. These shifts precede entrenched dependency.
THERAPEUTIC ALLIANCE
Is the relationship genuinely supportive?
In validated research, the implicit coordination of function words between two parties predicts therapeutic alliance, relationship stability, and rupture in psychotherapy research better than self-report.
DISTRESS ESCALATION & CRISIS
Early warning, grounded in clinical science.
Psycholinguistic distress signals validated in peer-reviewed research as predictors of crisis trajectories weeks in advance. Not heuristic triggers — measured signals with a published scientific basis.
Receptiviti measures psychological signals from language. It does not diagnose, classify individuals, or replace clinical judgment. Scores are structured variables for research and evaluation purposes.
INTEGRATION
Into your session layer, safety infrastructure, and product analytics.
Pass conversation text to the API. Receive structured psychological variables. Append to your existing session logs. No changes to your data infrastructure.
REAL-TIME SCORING
Score each conversation turn as it happens. Distress and escalation signals available within 65ms — fast enough to inform in-session response logic or trigger safety protocols.
LONGITUDINAL MEASUREMENT
Session-level and cross-session measurement of wellbeing trajectory and therapeutic alliance, patterns that only become visible over time — not in a single conversation
SAFETY TEAM ACCESS
Structured psychological variables accessible to clinical, safety, and product teams — not just raw conversation logs. Scored, documented, and auditable evidence of how the relationship is evolving
ON-PREM DEPLOYMENT
For products with sensitive user data, Receptiviti is available as a containerized on-prem deployment. Conversation text never leaves your infrastructure.
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 and companion AI teams are actively working on.
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.
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 partner to Receptiviti.
PUBLISHED: Clinical Psychological Science, 2026
Replicability and validity of a new AI assessment of PTSD from patient language
Kjell, Ganesan, Boyd et al., 2026. AI-based psychological assessment from language, when grounded in validated measurement, produces replicable, clinically meaningful results across sequential evaluation with preregistered models.
Co-authored by Ryan Boyd (UT Dallas), academic advisor to Receptiviti.
SCOPED
Interaction 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.
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.
34,000+
Peer-reviewed research citations