Fair Lending-Compliant AI Credit Decisions

The problem

When an AI model scores a credit application, Corules validates the decision against underwriting policy before it is rendered. Approved applications proceed. Denied applications automatically generate specific adverse action reasons citing the exact factors that failed (debt-to-income ratio, credit score threshold, employment verification). Every decision is replayable for regulatory examination.

Without deterministic enforcement, AI agents either block every edge case (adding manual overhead) or silently approve decisions that violate policy — with no audit trail to show auditors or regulators.

How Corules solves it

Corules sits between your AI agent and the action it wants to take. When the agent proposes a decision, Corules evaluates the full context against your compiled policy set in a single deterministic pass — no LLM, no ambiguity.

The result is a structured outcome: BLOCK — DTI ratio 52% exceeds max_dti = 43%. Adverse action reason: debt-to-income ratio.

Policy example

Corules policies are written in CEL (Common Expression Language). They are compiled once at publish time and evaluated deterministically at request time — no LLM, no variability.

// Credit decision policy (CEL)
context.credit_score >= params.min_credit_score
  && context.dti_ratio <= params.max_dti
  && context.employment_verified == true
  && context.loan_amount <= params.max_loan_by_tier[context.applicant_tier]

This expression is evaluated against the structured context your agent sends in the /v1/validate request.

Integration options

Corules integrates with the tools your teams already use. All integrations call the same REST API or MCP server — your policy logic stays in one place.

Frequently Asked Questions