Skip to main content
Your policy is the most important part of an Omni workflow. It tells your Review Ops Agent exactly what to check, how to evaluate documents, and when to approve or reject. A well-written policy produces accurate, consistent results. A vague one produces unreliable output. This guide covers the principles of effective policy writing, provides templates for common use cases, and explains how your policy language influences engine selection.

What Makes a Good Policy

Good policies share four characteristics:
Omni’s NLP Workflow Generator parses your policy to determine which engines to activate and how to orchestrate them. The more precise your language, the more accurate the engine selection and execution.

Policy Structure Template

Every policy should follow this four-part structure:
You do not need to use these exact section headers. What matters is that your policy covers all four areas: objective, inputs, steps, and decisions. Omni parses the meaning, not the formatting.

Examples by Use Case

Engines activated: Text Verifier, AML Search - Person
Engines activated: Text Verifier
Engines activated: Text Verifier
Engines activated: Text Verifier (for name extraction), AML Search - Person (for screening)

Common Mistakes

Avoid these pitfalls when writing policies:
Problem: Omni does not know what to verify. “Verify the document” gives no information about which fields to check or what constitutes a pass.Fix: Be explicit about what to check.
Problem: Without clear approve/reject rules, the AI agent has to guess what constitutes a passing result.Fix: Always end your policy with explicit decision criteria.
Problem: Omni performs better when it knows what type of document to expect. Without this context, extraction accuracy can suffer.Fix: Specify expected document types at the beginning of your policy.
Problem: Putting too many unrelated verification tasks into one policy makes it hard for the AI agent to execute cleanly. Results become less reliable.Fix: If your process involves fundamentally different types of checks (e.g., invoice validation AND employee background screening), split them into separate workflows.

Your wording decides the engines

Which engines get assigned depends on the wording of your policy. When you need a particular check, state that action explicitly in the policy. External lookup engines cost credits per call. Do not reach for an external lookup for something you can settle by comparing within the documents. Engine capabilities, prices, and supported countries are in AI model and engines.
One policy can call several engines. To see which engine actually landed on which action, check the playbook action list on the completion screen; if it is not what you wanted, change it in the step engine editor in editing a workflow.

What’s Next?

Creating a Workflow

Put your policy into action by creating a workflow.

Workflow Templates

Start with a pre-built template and customize it.