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).
- 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.
foundry-agent/agent-optimizer/references/azd-setup.md
azd Setup
Use this before running Agent Optimizer operations. This skill targets agent code repos that use azd and hosted agents.
Verify prerequisites
Run from the selected agent repo:
azd version
az login
azd ai agent --help
azd ai agent optimize --help
If azd ai agent is unavailable, install or update the azure.ai.agents azd extension using the official extension source. If the needed version is private preview only, ask the user for their approved extension source; do not embed private registry commands.
Resolve hosted-agent context
Use Common Project Context Resolution. Prefer azd context from azure.yaml and azd env get-values.
Confirm:
- selected service uses
host: azure.ai.agent
- selected root contains Python agent code
- agent kind is
hosted
- project endpoint/project ID and deployed agent name/version are known
If the agent's azure.yaml service block is missing, ask before initializing:
azd ai agent init --project-id <project-id>
Use the project ID from azd context when available; otherwise ask the user. After init, stop for review of the generated azure.yaml service block.