prevention.school is the platform story for schools and education systems: Teenology for families (as part of the school ecosystem), Prevention Terminal for psychologists, and aggregate dashboards for leadership. Live today: Teenology PWA; specialist web workspace preview is paused until the school desk is ready for demo. Grant cloud credits would fund engineering completion, production Gemini inference, and a bounded school pilot—not a claim of national deployment.
Commercial psychology centers and the IDA product line live on ida-ai.chat. This grant ask covers the school prevention architecture only: educator entry point, psychologist workspace, family support via Teenology, and privacy-safe aggregate telemetry for administrators.
Credits map to concrete cost lines in a solo-founder build. We apply as an AI-first startup under the Google for Startups Cloud Program (Gemini on Vertex, BigQuery, optional Ads pilot).
Program credits cover Google models (Gemini, Gemma) on Vertex; Antigravity usage is a separate engineering line (Google AI credits / Pro tier)—budgeted explicitly so reviewers see inference vs build tooling.
Teenology and the specialist desk are built around long-context, safety-bounded generative AI—not a wrapper on third-party chat. Vertex Gemini is the natural production path for family sessions and protocol-bound specialist assistance.
Bounded cohort: families + school psychologists + leadership sandbox. KPIs are process and architecture metrics (engagement, time-to-draft, crisis-route counts)—not clinical efficacy claims.
BigQuery research contour, Model Garden optionality, and agentic development (Antigravity) match Google’s AI-first startup track—up to $350k in cloud credits for qualified Scale-tier applicants.
Figures below are planning targets for fund reviewers; final numbers follow the application form.
| Phase | Focus | Exit criteria |
|---|---|---|
| 0–3 | L1↔L2 consent bridge, safety audit, specialist web polish | Documented crisis-routing tests; demo path for reviewers |
| 4–6 | Bounded family + school pilot (fund-demo cohort) | ≥50 active families with check-up + 2+ sessions; Pulse/Battery telemetry |
| 7–9 | Specialist workspace beta (school psychologists) | ≥15 specialists generating .docx drafts with PIE tags |
| 10–12 | Aggregate dashboard prototype (synthetic + pilot aggregates) | One regional-style sandbox dashboard; privacy review memo |
Percentages are illustrative for credit allocation, not a cash budget. Cash cofunding, if any, is listed in the formal application.
The architecture separates personal identifiable information (PII) from the LLM processing layer. Consumer diaries can stay local-first; specialist case data stays local-first in the terminal. The design targets GDPR- and COPPA-aligned deployment for school contexts—final compliance depends on jurisdiction, DPIAs, and institutional contracts.
Teenology prevention signals flow to the school psychologist workspace only with explicit consent—showable to ministries and school leadership.
Secure web terminal with Consultant / Expert / Architect modes and exportable prevention documents for school psychologists.
Regional-style analytics UI fed by anonymized pilot data—not a live national registry.