One API. Four integration patterns. Real scenarios, real endpoints.

Users of condition management apps — migraine trackers, asthma diaries, sleep apps — already log their symptoms. But they have no in-depth way to connect what happened environmentally to what they experienced. The app captures the outcome. It can have no or minimal visibility into the trigger and science behind it.

vasus.ai adds environmental context to every check-in. Each morning, the app calls POST /v1/insight with the user's home location and condition specifics like subtype, trigger and time to onset. The response includes a risk level, the three most relevant environmental signals, a synthesis paragraph grounded in peer-reviewed evidence, and cited recommendations — all in one structured JSON response that can merged with existing user attributes

Users see "Moderate migraine risk today — barometric pressure dropped 6.2 mb overnight" with two citations, not just a weather widget. The app becomes clinically meaningful, building trust and traction with users, without the product team building any environmental science. Users experience a more personalised app experience and app teams gain deeper insight into what information connects best with their users.

Insurers have extensive claims data but no forward-looking environmental signal. They know what happened — high claim volumes in summer in Delhi, elevated asthma hospitalisations in London during pollen season — but cannot systematically anticipate it or act proactively. The missing data layer is real-time environmental health intelligence at city level.

The EHSPI API provides daily composite and per-sensitivity environmental health scores for 22 global cities. Call GET /v1/ehspi nightly to pull the full city cohort. Build a dashboard that flags cities where EHSPI composite or a specific sensitivity score falls below a threshold — triggering proactive member outreach, preventative care programme activation, or underwriting alerts.

Environmental health risk becomes a structured data input to population health management — not an afterthought. Actuarial teams can correlate EHSPI trajectories with historical claim patterns. Member engagement teams can send targeted communications when environmental burden is elevated in a member's city.

Environmental health researchers often have excellent clinical outcome data but no structured, comparable environmental exposure data across multiple cities and time periods. Building that data infrastructure — ingesting from 7 API sources, computing features, normalising signals across cities — is a significant engineering investment that sits outside the core research competence.

vasus.ai's EHSPI history endpoint provides a clean, structured daily time series of environmental health scores across 20 cities for up to 5 sensitivities. All weight vectors are published transparently — any paper using EHSPI data can fully describe the scoring methodology. The Google Environmental API Spot Study (in progress) will provide validation data comparing API outputs against independent reference networks.

Research teams can access a structured, validated environmental exposure dataset without building the data infrastructure. The published weight vectors enable methodological transparency in any resulting publication. Collaboration on the formal EHSPI validation study is actively welcomed.

Employers running employee wellbeing programmes want to support employees with chronic conditions but face a fundamental constraint: they cannot collect health data. Any tool that requires employees to disclose their condition to their employer creates legal and trust risk. Existing environmental health tools are either too generic (weather apps) or require personal health profiling.

vasus.ai's architecture is privacy-first by design. Employees interact with the tool anonymously — no account, no health record, no PII of any kind. They choose their condition sensitivity privately. The API receives a condition key and a location string, returns an intelligence output, and stores nothing about the individual. The employer never sees who chose which condition.

Employees with migraines, asthma, cardiovascular conditions, or allergies get daily environmental context relevant to their condition — served through a white-labelled integration or the consumer SPA — without the employer ever knowing which conditions are being checked. The privacy architecture is a competitive differentiator for enterprise deployment.