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
Command Palette
Search for a command to run...
Series
AI-Assisted Development
Real-world experiences with AI-assisted software development — what works, what breaks, where the limits are, and how AI changes development workflows in practice.
Keep the Why vs. OKF Agent Memory vs. RepoWise: Three Approaches to Git-Native Project Memory
Rationale, structured knowledge, or codebase intelligence for coding agents?
Oct 5, 202616 min read29
The Globe: Following Your Reasoning Into Other People's Repositories
Keep the Why records why a codebase is the way it is. Decisions can cite decisions in other repositories. The Globe follows those citations outward, one wave at a time, without turning project memory into a centralized service.
Oct 1, 202613 min read94
The reasoning behind a codebase, as a web you can walk
Decisions that cite each other across repositories — no graph database, no central index, no account. Just Markdown and Git.
Sep 29, 20269 min read125
Session memory is not project memory. It fixes the same complaint.
"My coding agent forgets everything between sessions." Two different things answer that, and they are not competing.
Sep 23, 20266 min read79
Keep the Why vs. Claude Code Auto Memory vs. MemoryCustodian vs. AgentsRoom
Four tools that get called project memory. Three questions sort them. One table, as of September 2026.
Sep 22, 202613 min read206