Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creating persistent agents with AzureAIAgentsProvider, using hosted tools (code interpreter, file search, web search), integrating MCP servers, managing conversation threads, or implementing streaming responses. Covers function tools, structured outputs, and multi-tool agents.
95
93%
Does it follow best practices?
Impact
100%
7.14xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Function tools with typed parameters
Correct provider import
0%
100%
Correct credential import
0%
100%
Async context manager for provider
0%
100%
Async context manager for credential
0%
100%
Functions passed directly to tools
0%
100%
Annotated parameter typing
0%
100%
Field from pydantic
0%
100%
result.text usage
0%
100%
create_agent usage
0%
100%
asyncio.run entrypoint
0%
100%
Package installation comment
0%
100%
Streaming responses and conversation threads
run_stream usage
16%
100%
chunk.text guard
41%
100%
async for iteration
0%
100%
get_new_thread usage
0%
100%
thread passed to run
80%
100%
conversation_id saved
30%
100%
Async context manager
0%
100%
Correct provider import
0%
100%
Credential from azure.identity.aio
0%
100%
Multi-turn sequence
100%
100%
Structured output with Pydantic models
Pydantic BaseModel used
100%
100%
ConfigDict extra=forbid
0%
100%
ConfigDict import
0%
100%
response_format passed
0%
100%
model_validate_json parsing
0%
100%
result.text access
0%
100%
Correct provider import
0%
100%
Async context manager
0%
100%
Credential from azure.identity.aio
0%
100%
Structured fields accessed
100%
100%
Package install comment
0%
100%
ae2cadd
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.