Prevention taxonomy
A shared, deterministic language for risk factors, protective factors, and outcomes across family, specialist, and administrative layers. It bounds AI within validated behavioral standards.
Methodological Framework
The Science of Prevention: PIE Architecture
The platform operates as a continuous, empirical research loop. It transforms raw field signals into standardized, structured data, combining a three-axis prevention taxonomy and an evidence-informed knowledge base with an active analytical contour designed to programmatically validate and engineer future standards for AI-assisted care.
Powered by the Prevention Intelligence Engine (PIE)—a deterministic ontology that bounds generative AI within validated prevention science, not open-ended clinical advice.
Statistical feedback loop
Evidence production
Three-axis taxonomy
Non-clinical boundaries
Operational triad
Taxonomy, knowledge, and evidence production
Three coupled layers turn everyday prevention work into standards the industry can audit—not a static expert system relocated onto an LLM.
Knowledge base
Evidence-informed guidance attached to concrete prevention situations in real time—the matrix is injected into the AI runtime, not left as disconnected literature.
Evidence production engine
The third layer closes the design: anonymized field signals are intended to refine what the platform deploys next—evidence-informed protocol updates rather than one-off guidelines (subject to pilot evaluation).
How the closed loop is designed to run
The engine above is not a separate product—it is the target pipeline connecting taxonomy coordinates to measurable protocol updates as pilots mature.
1. Edge categorization
Teenology logs and specialist intake summaries are tokenized and mapped to taxonomy coordinates at the PWA layer, with PII stripped at the edge.
2. Aggregated evaluation
Anonymized telemetry is designed to enter an isolated BigQuery research contour for risk clustering and aggregate public-health trend analysis (when enabled in pilots).
3. Protocol optimization
Verified statistical deltas adjust prompt boundaries, RAG injection, and routing—codifying benchmarks for AI-assisted psychological support.
Runtime factory
The evidence factory: classifier → protocols → sprints → outcome
Above the macro research contour, Teenology Companion already runs a closed operational loop on every paid session. Raw chat is never stored as evidence; the factory emits structured keys, protocol IDs, sprint metadata, and user-rated outcomes that can be aggregated for protocol effectiveness.
Step 1 · Classify
Automatic problem classifier
Each user turn is mapped to taxonomy coordinates: problem_key, category_key, severity (Y-axis), modality hints (M-axis), and prevention direction (prevention_link). Unmatched topics stage review candidates without persisting message text.
Step 2 · Protocolize
Executable protocol selection
The engine selects bounded micro-interventions from the approved public.protocols catalog for the current process stage (X1–X5). Guidance is injected into the AI runtime; applied protocol IDs are logged on every assistant turn.
Step 3 · Sprint
Case sprint loop
Dialogue is organized as short case sprints: discover friction → work the focus problem → contain escalation → evaluate → decide next. Each sprint carries sprint_id, focus node, and x_stage so the same taxonomy language spans turns and sessions.
Step 4 · Evaluate
User outcome card
When a sprint closes, the user rates the cycle: helped / partly / did not help / felt worse, plus optional science scales (clarity, relief, next-step confidence, alliance, micro-action status). Outcomes bind to applied_protocol_ids and focus taxonomy—measuring what worked, not storing narratives.
Factory → evidence: chat_turn, problem_tree_snapshot, and sprint_outcome events feed anonymized analytics (BigQuery when enabled in pilots). Statistical deltas on protocol × problem × outcome combinations are the input to the protocol-optimization step above—not a separate product, but the same loop at aggregate scale.
Operational Limits
Strict Non-Clinical Bounds: Prevention vs. Therapy
Generic LLMs fail in volatile social environments because they drift into unvalidated psychotherapeutic advice. The PIE framework enforces strict topological boundaries, operating exclusively within the domain of Primary and Secondary Public Health Prevention Science.
We do not diagnose. We de-escalate.
The system is architected to explicitly reject the clinical/psychotherapeutic paradigm. It does not treat clinical pathologies, handle deep trauma, or issue medical assessments. Instead, it acts as an immediate structural stabilizer for communication, reinforcing systemic buffers before vulnerabilities manifest as medical or behavioral crises.
Automated Crisis Routing
If natural language tokens breach deterministic thresholds (detecting clear indicators of self-harm, systemic violence, or criminal patterns), the LLM layer is bypassed entirely. The platform locks the session and triggers a hot-route handoff to geo-targeted human crisis infrastructure.
The Core Mapping Engine
The Multidimensional Prevention Matrix
The PIE engine does not allow open-ended semantic drifting. Every incoming natural language token is programmatically ingested, vectorized, and forced to map onto a strict, 5D state matrix compiled directly from our production codebase (derived from WHO prevention standards).
X-Axis: Process Stages
Defines the exact operational phase of the intervention loop:
X1_Problem— Acute identification of frictionX2_Diag— Non-clinical prevention screening / structured check-upX3_Goal— Setting bounded de-escalation milestonesX4_Action— Deploying micro-action protocolsX5_Eval— Automated reflection and outcome tracking
Y-Axis: Severity Levels
Enforces the safety perimeter and determines routing thresholds:
Y1_Normal— Standard age-appropriate crisisY2_Risk— Sub-clinical risk factors accumulationY3_Problem— Manifested behavioral or communication crisisY4_Crisis_Clinical— Hard boundary for human hot-routing
M-Axis: Systemic Modalities
Categorizes the physiological or ecological origin of the stress vector:
M1_Biology— Age-related and neurodevelopmental shiftsM2_Psychophysiology— Somatic and stress-response markersM3_Cognition— Internal behavioral loops, beliefs, and scriptsM4_Social— Micro-system dynamics (family and peer environments)M5_Environment— Macro spaces (institutional and digital contexts)
Executor Roles (Target Interface)
Dynamic context filtering depending on the certified user interface: Psychologist (methodological logs), Teacher (classroom dynamics), or Administrator (macro reports).
Organizational Scale (Target Radius)
Defines the target sociological system size for the data loop: Individual → Family → Group → Community → Society.
Unified Taxonomy Passport Metadata
To ensure total semantic continuity between Level 1 consumer apps and Level 2 specialist spaces, every operational session generates an isolated, non-PII cryptographic passport. This passport tracks the BEHAVIOR_DELTA (movement from baseline anomaly to target de-escalation) and evaluates context continuity across long-term logs without exposing the underlying personal narratives.
Macro Analytics
Anonymized aggregate analytics (design)
Local client-side logging (IndexedDB) and PII stripping at the edge are design choices so individual interactions can become structured research signals—not passive charts alone, but inputs to the evidence loop described above.
The target architecture routes behavioral typologies and risk-vector matrices to analytics warehouses (e.g., BigQuery) so institutions could monitor regional stress patterns at aggregate level. That governance layer is not live nationally yet; grant funding aims to prove the pipeline end-to-end.
Vector Ontological Search
We use high-throughput vector databases (Azure AI Search / Vertex AI Vector Search) to perform deterministic matching between natural language input and our fixed prevention ontologies, forcing the model to stay on-script.
Decoupled Edge Isolation
The processing architecture utilizes stateless cloud worker nodes to ensure raw text analysis remains ephemeral and completely separated from the storage layers that feed the macro research databases.
"The ultimate goal of the Prevention AI Platform is not to automate human empathy, but to construct a resilient, scalable digital infrastructure where empirical science, frontline prevention practice, and regional governance finally operate in a single, real-time data feedback loop. By turning day-to-day field activity into a structured, verifiable source of evidence, we aren't just applying existing protocols—we are validating the future standards of AI-assisted psychological care."