AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

microsoft-foundry

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent, managed harness agent, Copilot harness, voice agent, create/update/invoke/evaluate agent, add tool to agent, agent insights, batch/continuous eval, continuous monitoring, agent CI/CD, optimize/improve prompt, optimize agent instructions, Agent Optimizer, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

Original source
microsoft
License
MIT
Pinned revision
3f5b461b2314e01c400564051e92469114c5b68f

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

This skill also requires local files or dependencies. Remote reading alone may not be enough.

Ask your assistant

Use Agentic Memory skills to read microsoft--microsoft-foundry at revision 3f5b461b2314e01c400564051e92469114c5b68f, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 151

foundry-agent/create/references/guardrails/guardrail-api-create.md

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