What an Agent Harness Needs Before Production: Eleven Failures and the Part That Stops Each

An agent harness is the code around the model. A bare twenty-line loop meets eleven bad days: a runaway model, bad arguments, a slow tool, a hidden instruction, generated code that reads secrets, a crash after a refund. Then the eight parts that stop them, built with JSON Schema, SQLite, OpenTelemetry, process limits and a container.

AI/ML14 min read

High Performance C#: Span and Memory

`Span<T>` allows you to work with contiguous memory regions (Arrays, Stack, Native Heap) without allocating new objects. It’s the secret sauce behind Kestrel’s speed. Slicing without Allocation Stackalloc Allocate memory on the…