AI helps people interpret, search, summarize, prioritize, and operate StormTrust. It does not replace the canonical evidence graph.
AI can explain what happened and why StormTrust assigns a confidence level.
AI can explain why a property receives a particular priority.
AI can suggest deployment zones within explicit capacity and policy constraints.
AI can turn structured evidence into understandable narrative without changing the evidence.
AI can translate a request into a structured search. For example, a user could request commercial roofs above a size threshold that experienced estimated hail within a time range.
AI can identify assignments that need attention or opportunities approaching a policy deadline.
AI answers use StormTrust tools rather than model memory for tenant or storm state. Representative tools include:
searchStorms
getStormEvent
getEvidenceTimeline
searchProperties
getImpactAssessment
getActionPlan
searchOpportunities
getCampaignPerformanceGenerated content records the model, available model version, prompt or template version, tool calls, source object IDs, and generation time.
AI cannot independently relabel modeled evidence as observed, certify evidence, alter provenance, fabricate weather data, confirm roof damage, bypass authorization, reveal protected contact data, bypass consent or suppression, activate paid advertising, or perform destructive changes outside an approved workflow.
Evaluation measures factual grounding, unsupported claims, citation accuracy, policy compliance, recommendation quality, refusal correctness, latency, and cost. Historical storm fixtures support repeatable evaluation.