Just logging for posterity that AI models and specifically coding agent harnesses have gotten really good at discovering and using tools lately.

Some of my recentish posts are already dated and seem obvious now:

I’ve been having this feeling on and off since 2022, but I need to check most impulses to build any significant low-level (close to the model) customization on top of what’s offered. It’s invariably only a matter of (short) time until the foundation models overcome the next crop of limitations and the harnesses fill more ergonomic gaps. It feels like Skills are getting to a good place, but there’s still quite a lot of thrash around security best practices, MCP vs direct CLI/SDK/cURL, orchestration, and agent to agent communication.