Field notes

Notes from where the docs run out.

AI systems, JavaScript, security, databases, and bug fixes worth remembering.

Auto-Tune Your LLM Judge

Measure the evaluator's variance, then rebuild its prompt from zero.

An open-source security workbench that keeps scope, approvals, tools, and evidence in one project.

Route to the best model with confidence.

Reduce local-dev risk with containers, canaries, and boring limits

The search tools already in your database, and when each one earns its keep.

Benchmarks measure benchmarks. Your system needs its own measures.

The full search landscape: exact, fuzzy, semantic, hybrid — and when to layer all of them.

Simplify Model & Provider Config with llm:// URLs