How it Works

Global AI Orchestration

The Autonomy orchestrator coordinates end-to-end check reviews across a case. It:

• Retrieves all case data and identifies checks or controls requiring review.
• Loads the relevant AI policies configured for each check type.
• Delegates each check to the appropriate specialized review agent.
• Aggregates all outcomes and generates a decision report for every automated approval or rejection.

This ensures consistent, policy-aligned decisions across all cases—at scale.

Specialized check review agents

Each check type is processed by a dedicated AI agent.

AML Check Review

• Uses LLM-based reasoning to instantly classify potential match hits.
• Automatically discards false positives or validates true positives.
• Applies policy-based routing to ensure compliant decisions.
• Produces contextual, line-by-line reasoning explaining the disposition of every hit.

Document Check Review

• Reviews submitted documents and automatically approves or rejects them.
• Compares extracted data with case data to flag discrepancies.
• Highlights potential issues and provides structured explanations for each decision.

ID Document Check Review

• Verifies personal identity documents and cross-checks data points.
• Detects mismatches, formatting anomalies and authenticity concerns.
• Generates a detailed reasoning report for approval or rejection.

ID Verification Review

• Confirms identity by comparing declared information to document data.
• Evaluates inconsistencies, potential fraud indicators and authenticity signals.
• Produces a clear justification for all outcomes.

Every decision made by an agent includes a full reasoning report accessible within the case.

AI policies

Each review agent within Autonomy operates under customizable, check-specific AI policies that let you define your own rules and decision logic.

Access to AI policies via the Advanced features settings menu.