Model governance

modelPolicy:
  allowedProviders:
    - openai
    - azure-openai
    - ollama
  allowedModels:
    - gpt-5
    - qwen3
  forbiddenModels:
    - unapproved-model
  requirements:
    approvalStatus: approved
    encryption: true
    region: EU

• Every agent model is validated against modelPolicy before the execution starts.
• Substituted (fallback) models must satisfy the policy as well and the substitution is audited.
• A model can carry approval, evaluation and region metadata; expired approvals do not satisfy a requirement.

Normative text: Model governance.

Compliance

AWP provides machine-readable governance primitives that can help organizations implement and enforce their own compliance requirements. Compliance depends on the implementation, organizational controls and applicable regulatory requirements.