EVE for Lending

For lenders using AI agents or models in origination and servicing workflows that need deterministic policy decisions and independently verifiable records of each decision.

The problem

Lending decisions and the actions around them face close scrutiny: which policy applied, what inputs were considered, what was decided, and where is the durable record? A model output on its own is neither deterministic nor tamper-evident.

How EVE helps

  • Deterministic decision at the boundary. EVE CoreGuard makes a deterministic ALLOW / BLOCK / MODIFY decision before a governed action executes, with no LLM in the decision path. Policy packs (for example, a lending policy set) express the rules deterministically.
  • Signed, bound evidence. Each governed decision can produce a signed evidence record bound to the decision (Ed25519 in the production configuration, HMAC-SHA256 fallback), supporting evidence collection for a review file.
  • Independent verification. A reviewer verifies signed evidence independently and offline in Python, Node, or the browser without trusting the EVE server.
  • Candidate-policy replay. Authenticated customers can replay historical decisions against a candidate policy and receive signed divergence reports with modeled-effect estimates — a way to study a policy change before it becomes authoritative.
  • Control mapping. EVE can map controls to frameworks descriptively and produces records useful for review.

Framing that stays accurate

EVE supports evidence collection and helps enforce policy for lending workflows. It does not determine fair-lending outcomes and does not certify a lending program; those determinations remain with your compliance and legal functions.

Readiness

  • EVE SDK core is a RELEASE CANDIDATE WITH EXCLUSIONS.
  • The core governance architecture is pilot-validated; signed evidence and offline verification are SUPPORTED.
  • The Shadow subsystem is authenticated pilot-ready.
  • Framework adapters other than the generic adapter are experimental.

Limitations

  • EVE supports evidence collection and helps enforce policy; it does not determine fair-lending outcomes, guarantee compliance, or issue certification.
  • Divergence estimates from shadow replay are modeled effects, explicitly not observed production outcomes; shadow evaluation cannot alter the active verdict and promotion is dry-run only.
  • 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.
  • Verification attests that evidence is authentic and unaltered — not that the underlying decision was correct.
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.