You cant unit-test a paragraph. So how do you know an AI feature works and that your last change didnt quietly break it? A clear, no-hype intro to evals, and how we run them on a live .NET product with Microsoft.Extensions.AI.Evaluation.
What crash-resumable budget enforcement looks like when the enforcement state lives in a ledger, not in memory. A walkthrough of the kill-9 -> resume demo.
Our MCP tool passed every server-side test, then Claude refused to call it. A debugging story about outputSchema and what E2E testing MCP actually means.
A couple of weeks ago I published a walkthrough of my agentic coding setup, the plan-first...