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-manage.md

Guardrails (RAI Content-Filter Policies)

Guardrails are Responsible AI (RAI) content-filter policies that control what content is allowed through model deployments and agents in Microsoft Foundry.

When to Use

  • Create or manage a guardrail (content-filter policy) for a Foundry project
  • Attach a guardrail to a hosted agent, model deployment, or toolbox → guardrail-attach.md
  • Create a guardrail via REST API → guardrail-api-create.md

Default Path: Portal

By default, guide the user to the Foundry portal to create guardrails interactively.

Construct and show this URL to the user:

https://ai.azure.com/nextgen/r/{encodedSubId},{resourceGroup},,{accountName},{projectName}/build/guardrails

Where:

  • {encodedSubId} — subscription GUID as URL-safe base64 (no = padding):
    python -c "import base64,uuid;print(base64.urlsafe_b64encode(uuid.UUID('<SUBSCRIPTION_ID>').bytes).rstrip(b'=').decode())"
    
  • {resourceGroup} — resource group name
  • {accountName} — AI Services account name
  • {projectName} — Foundry project name

If resource details are unknown, use the generic URL and instruct the user to navigate manually:

https://ai.azure.com

Then navigate: select your project → Build → Guardrails → Create Guardrail.

Use the API path (guardrail-api-create.md) only when the user explicitly asks for programmatic/CLI/CI/CD creation.

Intervention Points

| Intervention Point | Models | Agents (Preview) | Toolbox | |---|---|---|---| | User input | Yes | Yes | No | | Tool call | No | Yes | Yes | | Tool response | No | Yes | Yes | | Output | Yes | Yes | No |

Tool call and tool response are agent-only (and toolbox). An agent's guardrail fully overrides its model deployment's guardrail at all intervention points.

Default Guardrails

| Policy Name | Description | Editable | |-------------|-------------|----------| | Microsoft.Default | Base default policy (4 categories) | No | | Microsoft.DefaultV2 | Updated default with jailbreak + protected material | No | | Custom policies | User-created policies | Yes |