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/voice-agent-common.md

Voice Agent Common Invariants

Rules shared by Prompt Voice and Hosted Voice services in azure.yaml.

Classification

  • Author and maintain Voice Agent services with canonical kind: voice.
  • Silently recognize existing kind: prompt-voice manifests as Voice Agents for compatibility, and normalize them to kind: voice when editing.
  • Prompt Voice declares model with modelType: managed or self_deployed.
  • Hosted Voice uses a managed Voice wrapper whose conversationEngine names a distinct hosted target.
  • A standalone kind: hosted service using raw invocations_ws is not a managed Voice Agent.

Required Rules

  1. Place Voice fields directly under services.<service-key>; never use a nested config: block.
  2. Declare exactly one engine:
    • Prompt Voice: modelType plus model.id.
    • Voice wrapper: conversationEngine.
  3. Stop when both engines or neither engine are declared.
  4. Never use obsolete modelType: hosted_agent or targetAgent.
  5. Keep hosted target and Voice wrapper service keys and name values distinct.
  6. Preserve existing optional settings and omit optional fields the user did not request.

Lifecycle Boundaries

  • Deploy Voice services with azd.
  • Do not invoke a Voice service with azd ai agent invoke.
  • Prompt Voice has no local container.
  • Hosted target testing validates only its Voice Live Bridge handler; the Voice wrapper still requires end-to-end testing over the managed voice WebSocket.

Load only the selected subtype reference: