Practical insights on SE skills and best practices, plus technical deep dives into agentic AI.
Skills are great for unbounded coding agents. For the scoped, event-triggered agents sitting inside a business process, the headline features — many skills, runtime discovery, progressive disclosure — are often solving a problem those agents don't have.
Coding agents are designed to be coupled with an oracle. AI agents that automate knowledge work in business processes often cannot replicate this pattern. That is the fundamental gap that explains why coding is the flagship agent use-case, while agents for knowledge work are often still in experimentation.
Your eval harness is an instrument, and the instrument has more moving parts than the thing it's measuring. A single judge can't measure a modern agent. You need a portfolio.
Good SEs know how to present. Great SEs know their product because they've built with it. The unscripted moments are where trust is won.