Back to AqtaBio Pandemic Risk Agent
Card snapshot
qjtqgvpd9s.eu-west-1.awsapprunner.com
·
2026-05-19 00:50:47 UTC
·
6358d21b6fadb7afd0bc9e7b01578a86f67f19c81eb7d7d60a7f8e8afcc57fc4
This is a frozen copy of the agent's agent-card.json as we observed it at the timestamp above. We capture a new snapshot every time the card's content hash changes. Useful for: forensic drift analysis, verifying downstream callers see the right version, reproducing routing decisions made historically.
{
"name": "AqtaBio Pandemic Risk Agent",
"description": "Pre-etiologic zoonotic spillover risk forecasting at 25 km tile resolution. Backtest validation on the v0.1.0 historical cohort: AUROC up to 0.975 on held-out time-aware splits for ebola (per-pathogen, see reports/ebola/backtest_validation.json in the closed source). Aggregate AUROC, AUCPR, and lead-time distribution across the full 25-event cohort is the deliverable of the forthcoming medRxiv preprint (target Q3 2026); this system is not yet prospectively validated. Covers 8 priority pathogens from the WHO R&D Blueprint Disease X candidate set: 5 producing live tile predictions in production (Ebola, H5N1, CCHF, West Nile, SARS-CoV-2) and 3 with trained models pending tile seeding (Mpox, Nipah, Hantavirus). Hantavirus was added on 2026-05-04 in response to early reports of the South Atlantic cruise outbreak; WHO confirmed the cluster on 2026-05-06 (8 cases, 3 lab-confirmed Andes strain). Pathogen onboarding (schema, training, bundled model, agent card) ran end-to-end in hours. Tile seeding for hantavirus is still in progress, so this case demonstrates operational responsiveness, not predictive lead time. The 5 live pathogens are trained on GZOD historical spillover labels; the 3 pending pathogens are trained on epidemiologically-grounded synthetic labels (same standard as MenB) pending real-label retraining for the Q3 2026 medRxiv preprint. See `prediction_status` and the training-script citations on each entry. Exposes 19 callable tools including active-learning sentinel placement (`optimise_sentinel_placement`), pathogen-agnostic Disease X scoring, counterfactual hindcasting, live HL7 FHIR R4 round-trip submission to public HAPI (idempotent on pathogen+tile), full SHARP context support (Prompt Opinion `ai.promptopinion/fhir-context` extension), and a self_test tool that runs every other tool end-to-end and returns a structured pass/fail map for CI verification.",
"version": "0.1.0",
"url": "https://qjtqgvpd9s.eu-west-1.awsapprunner.com/mcp",
"protocol_version": "1.0",
"protocolVersion": "1.0",
"provider": {
"organization": "Aqta Technologies Limited",
"url": "https://aqtabio.org"
},
"model_info": {
"primary": "claude-haiku-4-5-20251001",
"scoring": "XGBoost + SHAP v0.1.0",
"training_cutoff": "2025-10-01"
},
"service_endpoint": "https://qjtqgvpd9s.eu-west-1.awsapprunner.com/mcp",
"supported_protocols": [
"mcp-streamable-http",
"http+json/rest"
],
"authentication": {
"type": "none",
"description": "Public read-only tooling. Rate limits enforced upstream."
},
"capabilities": {
"streaming": true,
"fhir_r4": true,
"prediction_status_taxonomy": "pathogens_covered entries carry a `prediction_status` field: 'live' = tile_predictions rows exist in production; 'pending_tile_seeding' = XGBoost model bundled but atlas tiles not yet seeded, so the prediction pipeline has not run.",
"extensions": [
"ai.promptopinion/fhir-context"
],
"sharp_context": {
"supported": true,
"fields_consumed": [
"patient_id",
"encounter_id",
"fhir_server",
"access_token"
],
"tools_using_sharp": [
"get_patient_local_risk",
"emit_riskassessment_to_ehr"
],
"phi_minimisation": "Only address.country is retained from the FHIR Patient resource. Risk is population-level (25 km tile). No patient identifier, name, DOB, or condition is stored or returned."
}
},
"skills": [
{
"name": "list_pathogens",
"description": "List all monitored pathogens with SNOMED CT codes and geographic scope.",
"tags": [
"discovery"
]
},
{
"name": "get_risk_score",
"description": "Current spillover risk score for a geographic tile with SHAP feature drivers. FHIR RiskAssessment optional.",
"tags": [
"query",
"fhir"
]
},
{
"name": "get_hotspots",
"description": "Hotspot counts by severity tier (critical \u22650.9, high \u22650.7, moderate \u22650.5) for a pathogen. FHIR DetectedIssue optional.",
"tags": [
"query",
"fhir",
"aggregate"
]
},
{
"name": "get_risk_trend",
"description": "24-month risk trajectory for a tile. FHIR Observation Bundle optional.",
"tags": [
"query",
"timeseries",
"fhir"
]
},
{
"name": "get_top_risk_tiles",
"description": "Highest-risk tiles ranked by score for a pathogen.",
"tags": [
"query",
"ranking"
]
},
{
"name": "get_top_risk_countries",
"description": "Returns the top countries by spillover risk. When a trained CountryClassifierModel sidecar is available for the requested pathogen + month, serves rankings from that model with a `scoring_method: 'trained_classifier'` flag. Otherwise falls back to a heuristic aggregation of tile-level scores (mean / max / upper bound of a bootstrap CI on the country mean), with saturation share flagged so callers can see when a country's rank is driven by clipped scores. Use for country-of-concern guidance (eg pre-positioning by WHO Africa).",
"tags": [
"query",
"ranking",
"aggregate",
"country",
"trained-classifier"
]
},
{
"name": "get_system_status",
"description": "System health, data freshness, live vs demo mode.",
"tags": [
"ops"
]
},
{
"name": "generate_outbreak_briefing",
"description": "Claude generates a PHO situational brief synthesising hotspots, top tiles, and SHAP drivers into an actionable narrative with 3 recommended actions.",
"tags": [
"genai",
"narrative"
]
},
{
"name": "explain_risk_drivers",
"description": "Claude translates SHAP values into plain-English causal narrative for a tile, with 2-3 specific recommended actions.",
"tags": [
"genai",
"explainability"
]
},
{
"name": "retrospective_validation",
"description": "Returns the recorded retrospective attestation for a historical spillover event paired with the publicly verifiable WHO / ECDC / national notification date. Backtest provenance, AUROC and AUCPR are surfaced in the `cross_check` field. Not a live model recomputation.",
"tags": [
"validation",
"evidence"
]
},
{
"name": "get_multi_pathogen_hotspots",
"description": "Detects syndemic convergence: regions and time windows where multiple pathogens simultaneously cross HIGH+ severity, flagging response infrastructure saturation risk.",
"tags": [
"syndemic",
"aggregate"
]
},
{
"name": "generate_fhir_bundle_for_pho",
"description": "Complete HL7 FHIR R4 transaction Bundle (RiskAssessment + DetectedIssue + 12\u00d7Observation) with per-entry POST requests, ready to submit to any FHIR server.",
"tags": [
"fhir",
"integration"
]
},
{
"name": "get_disease_x_risk",
"description": "Pathogen-agnostic pre-spillover risk score addressing the WHO R&D Blueprint's Disease X priority. Aggregates per-pathogen risks into a single 'any zoonotic emergence' signal for the unknown pathogen of the next pandemic.",
"tags": [
"disease-x",
"blueprint",
"novel"
]
},
{
"name": "get_hindcast",
"description": "Counterfactual timeline analysis. Given a recorded retrospective attestation, returns the actual outbreak timeline alongside an illustrative counterfactual: what intervention window would have been available if a public-health responder had acted N days after the threshold-crossing signal. Honest about caveats; no claim of cases averted.",
"tags": [
"counterfactual",
"validation",
"novel"
]
},
{
"name": "submit_to_hapi_fhir",
"description": "Live HL7 FHIR R4 round-trip: builds a RiskAssessment for a tile/pathogen/month, POSTs to the public HAPI FHIR test server, and returns the assigned resource URL plus HAPI's HTTP status. Makes the 'FHIR round-trip tested' claim a callable proof; anyone can fetch the resource back to verify conformance. Population-level risk only, no PHI.",
"tags": [
"fhir",
"interop",
"verifiable"
]
},
{
"name": "get_patient_local_risk",
"description": "SHARP-aware patient-local risk. Reads the Prompt Opinion `ai.promptopinion/fhir-context` block (patient_id, fhir_server, access_token), fetches the Patient resource via SMART-on-FHIR, derives the home tile from address.country, and returns AqtaBio's population-level spillover risk for that area. PHI minimisation: only country is retained. Designed to be invoked from a clinician's Prompt Opinion workspace.",
"tags": [
"sharp",
"fhir",
"patient-context",
"smart-on-fhir"
]
},
{
"name": "emit_riskassessment_to_ehr",
"description": "SHARP-aware EHR write-back. Takes the SHARP-propagated bearer token from the clinician's EHR session and POSTs an AqtaBio FHIR RiskAssessment resource to the same FHIR server, attached to the patient reference. Demonstrates round-trip context propagation: the platform's promise of bridging EHR credentials without bespoke token handling is verifiable end-to-end.",
"tags": [
"sharp",
"fhir",
"writeback",
"smart-on-fhir"
]
},
{
"name": "handoff_to_triage",
"description": "A2A v1.0 handoff. Takes a FHIR RiskAssessment from the surveillance side of AqtaBio and returns a FHIR Task that hands the matter to a clinical triage specialist agent. The Task carries a deterministic risk-band action (notify / surveil / routine) plus a disclaimer in note that the mapping is not clinical decision support; a public health officer must approve before any operational step. The triage specialist agent card is exposed at /.well-known/triage-agent.json.",
"tags": [
"a2a",
"handoff",
"fhir",
"task",
"triage"
]
},
{
"name": "self_test",
"description": "Runs every other tool with sane default arguments and returns a structured pass/fail map. Lets CI / pre-deploy / post-deploy check that all 18 working tools execute without exception. Catches dangling references and missing pathogen branches that would otherwise only surface in a clinician's workspace.",
"tags": [
"self-test",
"ci",
"ops"
]
}
],
"pathogens_covered": [
{
"id": "ebola",
"display": "Ebola Virus Disease",
"snomed": "37109004",
"status": "operational",
"model_status": "trained",
"prediction_status": "live"
},
{
"id": "h5n1",
"display": "Avian Influenza H5N1",
"snomed": "396425006",
"status": "operational",
"model_status": "trained",
"prediction_status": "live"
},
{
"id": "cchfv",
"display": "Crimean-Congo Haemorrhagic Fever",
"snomed": "19065005",
"status": "operational",
"model_status": "trained",
"prediction_status": "live"
},
{
"id": "wnv",
"display": "West Nile Virus Disease",
"snomed": "417093003",
"status": "operational",
"model_status": "trained",
"prediction_status": "live"
},
{
"id": "sea-cov",
"display": "SARS-CoV-2",
"snomed": "840539006",
"status": "operational",
"model_status": "trained",
"prediction_status": "live"
},
{
"id": "mpox",
"display": "Mpox (Monkeypox)",
"snomed": "50811000",
"status": "operational",
"model_status": "trained",
"prediction_status": "pending_tile_seeding"
},
{
"id": "nipah",
"display": "Nipah Virus",
"snomed": "27332006",
"status": "operational",
"model_status": "trained",
"prediction_status": "pending_tile_seeding"
},
{
"id": "hantavirus",
"display": "Hantavirus",
"snomed": "16541001",
"status": "operational",
"model_status": "trained",
"prediction_status": "pending_tile_seeding"
}
],
"validation_claim": {
"event": "COVID-19 Wuhan",
"model_prediction_date": "2019-11-08",
"risk_score": 0.82,
"who_notification_date": "2019-12-31",
"lead_time_days": 53,
"tile_id": "AS-025-45678",
"verifiable_via": "retrospective_validation(event_id='2019_wuhan_sars_cov_2')"
},
"documentation_url": "https://aqtabio.org/proof-of-concept"
}