Create a Guardrail via the REST API (`az rest`)

Use this path only when the user explicitly asks for programmatic/CLI/CI/CD creation. Otherwise, guide them to the portal.

Prerequisites

Azure CLI installed and logged in (az login)
Foundry Account Owner role (or higher) on the Azure AI resource
The Azure AI Services account name, resource group, and subscription ID

Step 1: Set Variables

SUBSCRIPTION_ID=$(az account show --query id -o tsv)
RESOURCE_GROUP="<your-resource-group>"
ACCOUNT_NAME="<your-ai-services-account>"
POLICY_NAME="my-custom-guardrail"

Step 2: List Existing Guardrails

az rest --method GET \
  --url "https://management.azure.com/subscriptions/${SUBSCRIPTION_ID}/resourceGroups/${RESOURCE_GROUP}/providers/Microsoft.CognitiveServices/accounts/${ACCOUNT_NAME}/raiPolicies?api-version=2024-10-01"

Step 3: Create a Guardrail

Minimal example — guardrail-policy.json:

{
  "properties": {
    "basePolicyName": "Microsoft.Default",
    "mode": "Asynchronous_filter",
    "contentFilters": [
      { "name": "Hate", "enabled": true, "blocking": true, "severityThreshold": "Medium", "source": "Prompt" },
      { "name": "Hate", "enabled": true, "blocking": true, "severityThreshold": "Medium", "source": "Completion" },
      { "name": "Violence", "enabled": true, "blocking": true, "severityThreshold": "Low", "source": "Prompt" },
      { "name": "Violence", "enabled": true, "blocking": true, "severityThreshold": "Low", "source": "Completion" },
      { "name": "Jailbreak", "enabled": true, "blocking": true, "source": "Prompt" }
    ]
  }
}

az rest --method PUT \
  --url "https://management.azure.com/subscriptions/${SUBSCRIPTION_ID}/resourceGroups/${RESOURCE_GROUP}/providers/Microsoft.CognitiveServices/accounts/${ACCOUNT_NAME}/raiPolicies/${POLICY_NAME}?api-version=2024-10-01" \
  --body @guardrail-policy.json

200 OK — policy updated
201 Created — policy created for the first time

For the full request body schema (contentFilters[], basePolicyName, mode, customBlocklists), see the RAI Policies - Create Or Update API reference.

Step 4: Verify via CLI

az rest --method GET \
  --url "https://management.azure.com/subscriptions/${SUBSCRIPTION_ID}/resourceGroups/${RESOURCE_GROUP}/providers/Microsoft.CognitiveServices/accounts/${ACCOUNT_NAME}/raiPolicies/${POLICY_NAME}?api-version=2024-10-01"

Confirm contentFilters[] matches your intended configuration.

Step 5: Assign to Targets

After creating a guardrail, assign it to a hosted agent, model deployment, or toolbox → guardrail-attach.md

Delete a Guardrail

Remove all model/agent assignments before deleting (portal: edit guardrail → deselect all targets → save).

az rest --method DELETE \
  --url "https://management.azure.com/subscriptions/${SUBSCRIPTION_ID}/resourceGroups/${RESOURCE_GROUP}/providers/Microsoft.CognitiveServices/accounts/${ACCOUNT_NAME}/raiPolicies/${POLICY_NAME}?api-version=2024-10-01"

References

RAI Policies - Create Or Update (REST API) — full schema, parameters, response codes
RAI Policies - List — list all policies on an account
Blocklists API — custom blocklists (created separately)
How to configure guardrails (Microsoft Learn) — portal walkthrough

Third-party checks

2 warnings3d4 checks · Risk SAFE

Gen Agent Trust Hub3d
This skill provides a comprehensive environment for managing the end-to-end lifecycle of AI agents, models, and infrastructure on Microsoft Foundry. It includes sub-skills for deployment, evaluation, fine-tuning, and troubleshooting. The skill utilizes dynamic code execution and shell command wrappers, which are used within the context of local development and cloud orchestration. All external resources and dependencies originate from trusted organizations and well-known services.
Socket3d
2 alerts: gptSecurity, gptAnomaly
Snyk3d
Risk: LOW · No issues
Runlayer7mo
36/36 files flagged

/microsoft-foundry

foundry-agentcreatereferencesguardrailsguardrail-api-create.md

Create a Guardrail via the REST API (`az rest`)

Prerequisites

Step 1: Set Variables

Step 2: List Existing Guardrails

Step 3: Create a Guardrail

Step 4: Verify via CLI

Step 5: Assign to Targets

Delete a Guardrail

References

Third-party checks

Provenance

Capability

/microsoft-foundry

microsoft-foundryfoundry-agentcreatereferencesguardrailsguardrail-api-create.md

Create a Guardrail via the REST API (az rest)

Prerequisites

Step 1: Set Variables

Step 2: List Existing Guardrails

Step 3: Create a Guardrail

Step 4: Verify via CLI

Step 5: Assign to Targets

Delete a Guardrail

References

Third-party checks

Provenance

Capability

README badge

Related skills

foundry-agentcreatereferencesguardrailsguardrail-api-create.md

Create a Guardrail via the REST API (`az rest`)