Skip to main content

​
Engine Catalog

Omni provides AI-powered MCP engines that carry out verification steps. Which engines run is decided automatically from your policy, and the Identity Agent (DAG Planner) also orchestrates their execution order.
Engines are not something you pick in the workflow creation wizard. Step 3 selects an AI model; to see which engines a workflow ended up with, read engines from GET /workflows/:workflowId.

​
Available Engines

Additional engines will be added as Omni expands its capabilities. The engine catalog will grow to cover more verification use cases including identity document parsing, facial recognition, business registry validation, and more.

​
AML Search - Person

The AML Search engine screens individuals against global AML/sanctions watchlists via MCP tool call (search_individual). This is the only engine that performs external database lookups.

​
Input

The AI agent extracts the following fields from submitted documents and passes them to the AML Search engine:

​
Matching Score

The final matching score is calculated as the average of individual field scores:

​
Output — Risk Icons

Screening results are classified by risk level using the following risk icons:

​
Output — Result Status

​
Analysis Response Fields

When this engine runs, results appear in:
  • agentAuditLog.steps[].mcpcalls[] — tool, engine (engine display name), input, result (raw per-engine response), purpose, duration_ms
  • findings[] — Summarized result with category, result (passed/warning/failed), and details
  • rawActionResults — Action result text with verification status
For the complete AML database source documentation, risk icon details, and search algorithm specifications, see the AML Database Sources and Codes reference.

​
Text Verifier - Glove

The Text Verifier engine validates document text for consistency, accuracy, and completeness using AI-powered analysis via RAG (Retrieval-Augmented Generation). This engine does not perform external database lookups — it works entirely with the documents uploaded to the profile.

​
Input

The AI agent provides the engine with:

​
Capabilities

  • Data Extraction — Extract structured values from documents (names, numbers, dates, addresses, etc.)
  • Cross-field Validation — Check consistency between fields within and across documents
  • Completeness Check — Verify all required fields are present and populated
  • Document Validity — Assess whether a document appears valid and unaltered
  • Policy Compliance — Evaluate documents against the natural language policy rules

​
Output

The Text Verifier produces the primary content of the analysis response:
The field names and structure inside extractedData follow the output schema you defined, entirely. Omni does not impose a common field set.

​
Analysis Response Fields

When this engine runs, results appear in:
  • agentAuditLog.steps[] — Per-step execution log (rule, status, reasoning, tokens, executed_at)
  • findings[] — Summarized result per verification step
  • extractedData — Full structured output following your output schema
  • rawActionResults — Per-action result text and verification status
The fields inside extractedData are determined entirely by your workflow’s output schema. A different workflow means different key names and nesting. Omni does not impose a common field set.

​
How Engines Are Decided

When you save a policy, Omni interprets it, derives the verification steps it needs, and attaches an engine to each step. The Identity Agent (DAG Planner) also sets the execution order, so there are no dependencies to configure by hand. You can see the outcome in the GET /workflows/:workflowId response: workflowActions for the step definitions and engines for the engine catalog, including isSelected.

​
Workflow Templates

Pre-configured engine combinations are available as workflow templates. These provide recommended starting points for common use cases.