EVE for Insurance

For carriers and insurtechs using AI agents in underwriting, claims, and servicing that need deterministic control decisions and independently verifiable evidence of each one.

The problem

An AI agent acting in underwriting or claims can trigger consequential actions and data flows. The control environment expects deterministic policy enforcement and a durable, checkable record — not a probabilistic model narrative.

How EVE helps

  • Deterministic pre-execution decision. EVE CoreGuard returns a deterministic ALLOW / BLOCK / MODIFY decision before a governed action executes, computed by deterministic policy code with no LLM in the decision path.
  • Evidence for review. Each governed decision can produce a signed evidence record bound to the decision (Ed25519 in the production configuration, HMAC-SHA256 fallback), supporting evidence collection.
  • Independent verification. Signed evidence verifies independently and offline in Python, Node, or the browser without trusting the EVE server.
  • Document-input protection. For file inputs such as claim documents, EVE detects the real media type from content, applies bounded safe-parsing limits, runs deterministic scanners, and blocks/quarantines/requires-approval before ingestion — emitting signed scan evidence. Scan evidence binds the artifact digest to the decision, so a substituted document after approval is detected at verification.
  • Sequence and budget controls. EVE can block individually-permitted actions that combine into a prohibited sequence, and enforce deterministic budget/resource limits.

Framing that stays accurate

EVE supports evidence collection, helps enforce policy, and can map controls to frameworks for review. It does not determine regulatory outcomes or certify an insurance program.

Readiness

  • EVE SDK core is a RELEASE CANDIDATE WITH EXCLUSIONS.
  • The core governance architecture is pilot-validated; signed evidence and offline verification are SUPPORTED.
  • Artifact governance is customer-pilot ready at supported boundaries (PILOT_READY).
  • Framework adapters other than the generic adapter are experimental.

Limitations

  • EVE supports evidence collection and helps enforce policy; it does not guarantee compliance, issue certification, or determine regulatory outcomes.
  • Deterministic scanners are pattern/structure-based; OCR/vision/QR-barcode extraction is probabilistic, disabled by default, and reported as unavailable — incomplete extraction is reported as partial and cannot masquerade as complete.
  • Artifact-digest binding is detected at verification time; enforcing re-scan-before-use is a wiring responsibility at the ingestion boundary.
  • Independent verification requires the Ed25519 public key; the HMAC fallback is symmetric and not independently verifiable.
  • The pip client governs via hosted mode (requires a reachable endpoint); embedded evaluation is the EVE service.
Part of the EVE AI Core control plane Deterministic AI Governance Control Plane → Policy decisions that return the same result for the same input every time, before execution.