What problem does it solve? A single agent reviewing its own output shares the same biases and blind spots that produced the errors, so hallucinations, compliance violations, and factual mistakes slip into shipped content and production code. ## Core Features & Use Cases - Dual Independent Review: Two context-isolated reviewer agents evaluate output against an identical structured rubric, and both must pass before anything ships. - Convergence Fix Loop: Flagged issues are merged, fixed, and re-reviewed by fresh agents each round, with a max-iteration cap and human escalation on exhaustion. - Batch Sampling Mode: Verifies a 10-15% stratified sample of large batches, classifies failure patterns, and applies targeted fixes across the whole batch. - Use Case: Before publishing AI-generated technical documentation at scale, run each document through two independent reviewers checking factual accuracy, hallucination-free claims, and completeness, then auto-fix and re-verify until both pass. ## Quick Start Review this generated output using the Santa Method with two independent reviewers against a rubric covering factual accuracy, completeness, and compliance, then fix and re-verify until both pass.
