~/topics/ai

Topic: ai

3 entries

skill·Jun 18, 2026

Remove trivial tests before they harden

An agent skill for replacing shallow AI-written coverage with tests that can catch real regressions.

4 min read0

llm·Mar 4, 2026

LLMs in production: tools, retrieval, evals

Where each pattern earns its place, where it does not, and how I keep cost, latency, and trust honest.

3 min read0

llm·Feb 25, 2026

Keep tool-calling agents on a short leash

The tool surface, eval loop, and refusal rules I want before an agent can touch a real repo.

4 min read0