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 int...
92
Quality
88%
Does it follow best practices?
Impact
100%
100.00xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Function tools with parameter annotations
AzureAIAgentsProvider import
0%
100%
Credential import source
0%
100%
Functions passed directly to tools
0%
100%
Annotated parameter syntax
0%
100%
Annotated from typing
0%
100%
Field from pydantic
0%
100%
Credential context manager
0%
100%
Provider context manager
0%
100%
Without context: $0.6038 · 5m 53s · 32 turns · 39 in / 6,821 out tokens
With context: $0.2654 · 3m 46s · 17 turns · 437 in / 2,897 out tokens
Hosted tools and streaming responses
HostedCodeInterpreterTool import
0%
100%
HostedWebSearchTool import
0%
100%
WebSearchTool name param
0%
100%
run_stream usage
0%
100%
async for streaming loop
0%
100%
chunk.text check
0%
100%
AzureAIAgentsProvider context manager
0%
100%
AzureAIAgentsProvider import source
0%
100%
Without context: $0.1570 · 1m 49s · 10 turns · 14 in / 3,197 out tokens
With context: $0.3752 · 3m 35s · 21 turns · 285 in / 3,220 out tokens
Multi-turn threads and structured output
get_new_thread usage
0%
100%
thread passed to run
0%
100%
conversation_id accessed
40%
100%
Pydantic BaseModel for output
0%
100%
ConfigDict extra=forbid
0%
100%
response_format on run()
0%
100%
model_validate_json parsing
0%
100%
ConfigDict import
0%
100%
Without context: $0.6146 · 5m 53s · 31 turns · 30 in / 9,489 out tokens
With context: $0.2425 · 2m 29s · 14 turns · 279 in / 2,986 out tokens
5c5ae21
Table of Contents
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.