What Should You Actually Evaluate?
Choose AI evaluation criteria from the feature contract: answer quality, retrieval, tool effects, safety, reliability, latency, and cost.
Testing
Pin culture and time zone in tests that depend on them
Make culture and time zone explicit inputs when parsing, formatting, or local-time conversion depends on them.
What Happens When Your AI Feature Fails?
A practical way to identify failure modes, choose explicit application behavior, and test an AI feature before its successful path hides the hard decisions.
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 TimeProvider instead of DateTime.UtcNow in testable code
Inject TimeProvider when business logic depends on the current time, then control that time in tests.
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.