Designing an AI Service Layer
How to place model access, prompts, retrieval, tools, and application policy behind a maintainable use-case boundary in a .NET application.
Posts
Practical articles about .NET, Azure, AI engineering, architecture, evaluation, observability, retrieval, and reliable delivery.
Trust Boundaries Around AI Features
How to keep model proposals separate from trusted application behavior with authorization, approval policy, current-state checks, and least privilege.
Why Retrieval Exists
Why application knowledge does not belong in model weights, what retrieval contributes, and when a prompt, database query, or deterministic tool is simpler.
The Model Is Only One Dependency. Map the Rest.
How to map the execution, prerequisite, and operational dependencies around an AI feature and give each interaction a usable failure contract.
Stop Letting Provider SDKs Define Your .NET AI Architecture
How Microsoft.Extensions.AI keeps provider SDKs at the edge of .NET applications through shared abstractions, dependency injection, and middleware.
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.
Microsoft Foundry: When Agent Framework Agents Become Managed Resources
Series
Deep Dive: Microsoft Agent Framework
Part 19 of 19
How to host a Microsoft Agent Framework agent in Foundry while keeping authorization, conversation ownership, identity, and governance boundaries explicit.
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.
Testing Microsoft Agent Framework Applications
Series
Deep Dive: Microsoft Agent Framework
Part 18 of 19
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.
Generate Useful Test Data in .NET with Bogus
How to use the Bogus library to generate realistic, repeatable, and domain-shaped test data in .NET, including faker rules, related objects, seeds, and practical boundaries.