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/create/references/tools/managed-harness-agent/tool-a2a.md
Agent-to-Agent
Use a2a_preview to call another A2A-compatible Agent as a tool.
tools:
- type: a2a_preview
name: specialist
description: Handles specialist requests.
base_url: https://<peer-endpoint>
agent_card_path: /.well-known/agent-card.json
project_connection_id: <optional-connection>
Same-project or public peers may not need a connection. For an authenticated peer, use a connection supplied by the user or already referenced by the Agent.
Create a remote A2A connection only when explicitly requested:
azd ai connection create <connection-name> \
--kind remote-a2a \
--target "<peer-a2a-endpoint>" \
--auth-type <user-entra-token-or-agentic-identity> \
--audience "https://ai.azure.com" \
--metadata "ApiType=Azure" \
--metadata "type=custom_A2A" \
--metadata "AgentCardPath=/agentCard/v1.0" \
--project-endpoint "<project-endpoint>"
Grant the invoking user or Agent identity the Foundry Agent Consumer role on the peer project.
The target must already expose an A2A endpoint and Agent Card. For a Foundry peer that does not, follow Enable Incoming A2A.