Behavioural Signal InfrastructureSignal, not decision

Behavioural infrastructure
for emotionally intelligent
AI systems.

SOHMA develops behavioural signal infrastructure that helps AI systems respond in more context-aware and human-controlled ways.

Scroll
01The Core Insight

AI systems read what is typed.
Humans communicate far more than that.

Today's systems operate on explicit inputs — text, commands, structured data. The interaction itself carries another layer: timing, intent, attention, repair. SOHMA studies how that layer can be measured, interpreted, and made available to AI under human oversight.

Hesitation
Pacing
Retries
Disengagement
Recovery
Interaction stability
signal
02 — Sohma Lab

A set of research environments
for studying behavioural signals.

The Lab is not a product line. Each environment is an instrumented context — chosen for the kinds of interactions it reliably produces — used to validate what behavioural signals can and cannot tell us.

  1. E.01Gaming environmentsAdaptive challenge, frustration & flow signals under sustained interaction.
  2. E.02Conversational interactionRepair, turn-taking, attentional drift in dialogue with AI agents.
  3. E.03Learning environmentsHesitation, retries, recovery as proxies for comprehension state.
  4. E.04Communication simulationsMulti-party exchange dynamics across structured roleplay tasks.
  5. E.05Wellbeing environmentsLow-stakes contexts for studying disengagement and self-regulation.
Status — Active researchOn-deviceNo camera · No microphone
03 — Signal Layer

A new input layer
between interaction and intelligence.

01
Human Interaction

Natural input across environments.

02
Behavioural Signals

Timing · pacing · repair · attention.

03
SOHMA Layer

Interpretation under governance.

04
Adaptive AI Systems

Context-aware, human-controlled response.

We treat behavioural context as a first-class input — probabilistic, interpretable, and routed through human-controlled governance before reaching any downstream system.

04 — Validation & Research

Early. Serious.
Carefully bounded.

Our current focus is establishing what the behavioural signal layer can responsibly provide. We are deliberate about what is claimed and what remains open. Validation is conducted through the SOHMA Lab environments — controlled contexts designed to test signal consistency across interaction settings and to generate behavioural datasets.

Focus 01
Behavioural signal validation

What signals are real, repeatable, meaningful.

Focus 02
Cross-environment testing

Generalisation across distinct interaction contexts.

Focus 03
Interaction research

How users repair, recover, disengage with AI.

Focus 04
Probabilistic signals

Confidence-aware interpretation over hard labels.

Focus 05
Data generation environments

Consented, controlled, reproducible contexts.

Focus 06
Governance-first system design

Constraints encoded before capability.

Internal · 04.A
Signal Dashboard

An internal view into the development of SOHMA's behavioural intelligence layer — including signal validation, cross-environment consistency, and progress toward API readiness.

Password protected · Invited collaborators, investors, advisors & strategic partners

05 — Governance

Constraints written into
the architecture.

Governance is not a layer added at the end. It defines what is measurable, what is interpretable, and what is ever allowed to leave the system.

Auditable end to end

  • No diagnosis

    We do not produce clinical or medical inferences.

  • No personality scoring

    We do not generate trait, type, or character profiles.

  • No hidden profiling

    Signals are contextual and bounded to the session.

  • No autonomous intervention

    Outputs inform systems; they do not act alone.

  • Human oversight

    Interpretation paths are reviewable and overrideable.

  • Transparent outputs

    Signals are documented, scoped, and surfaced honestly.

06Long-term Vision

Foundational behavioural
infrastructure for the next
generation of adaptive systems.

H.01Onboarding systems
H.02Learning systems
H.03Conversational AI
H.04Adaptive environments
H.05Agentic systems
H.06Human-facing AI infrastructure

We are building patiently. The work compounds as the signal layer becomes legible — and as the systems that depend on it learn to ask for context, not merely commands.