Lead Scoring Validation with Fraud Prevention

The problem

Lead scores produced by AI models are validated by Corules before routing to sales. Email domain reputation, phone number validity, IP geolocation consistency, and submission velocity checks filter out fraudulent leads. Suspicious leads are flagged for manual review instead of auto-routing to sales, preserving pipeline quality.

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: ESCALATE — IP geolocation (Nigeria) does not match stated country (United States). Flagged for manual review.

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.

// Lead validation policy (CEL)
context.email_domain_reputation >= params.min_domain_reputation
  && context.phone_valid == true
  && context.ip_geo_matches_country == true
  && context.submission_velocity_score < params.max_velocity_score

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