Calling a Model Is Easy. Running an AI System Is Not
Why a successful model call says little about whether an AI feature is reliable, secure, observable, affordable, and ready to operate in production.
Ai-Engineering
Measure retrieval misses separately from model failures
Give retrieval its own outcome and telemetry so missing or irrelevant context is not diagnosed as a model problem.
Describe tool parameters like API contracts
Give AI tools precise parameter names, units, formats, and side-effect expectations so the model receives an unambiguous contract.
Microsoft Foundry: When Agent Framework Agents Become Managed Resources
How to host a Microsoft Agent Framework agent in Foundry while keeping authorization, conversation ownership, identity, and governance boundaries explicit.
Choose rate-limiting policies by endpoint cost
Apply different ASP.NET Core rate limits to cheap reads and expensive AI or data-processing endpoints.
When an AI Request Should Become a Background Job
How to decide when a .NET AI request should stay synchronous, stream its response, or move to a durable background job with HTTP 202 and a status resource.
Validate structured model output before using it
Treat deserialized model output as untrusted data and apply normal business validation before it drives application behavior.
Testing Microsoft Agent Framework Applications
How to test Microsoft Agent Framework applications with fake model clients, tool contract tests, structured output tests, routing tests, workflow tests, and eval-style regression checks.
Use HybridCache for expensive AI work in .NET
Use HybridCache to avoid duplicate AI model calls, with a cached summarization example and deliberate cache-key design.
Keep agent tools narrow and boring
Expose only the small, specific capabilities the agent needs for the current workflow.