The Model Changed. My Skill Didn't. The Score Still Dropped.
What agent evals taught me about moving model floors, noisy LLM judges, and treating the evaluator as part of the instrument
Oct 5, 20269 min read8

Search for a command to run...
Articles tagged with #keepthewhy
What agent evals taught me about moving model floors, noisy LLM judges, and treating the evaluator as part of the instrument

Rationale, structured knowledge, or codebase intelligence for coding agents?

Decisions that cite each other across repositories — no graph database, no central index, no account. Just Markdown and Git.

Four tools that get called project memory. Three questions sort them. One table, as of September 2026.

Install it, initialize the project, keep coding.

How a small structural change reduced unnecessary Git conflicts in a shared Markdown index — and made it easier for coding agents to navigate.
