Innovation Matters
Essays on AI, developer tools, and thoughtful software.
Does every agent skill need an eval?
A skill can make an agent better and still be a bad trade. How much evidence should you expect before trusting someone else's skill?
What's volatile about your technology?
A model's knowledge cutoff doesn't tell you how old its knowledge of your SDK is. Technology providers know something more useful.
Your agent should start with a hypothesis, not a plan
Agents can turn a plausible first answer into a plan before current documentation gets a say. By then, correcting an outdated assumption is already expensive.
DRY might be wrong for agent documentation
DRY documentation saves maintainers from repeating themselves. What if it makes every agent pay for that convenience?
I was wrong: there are bad prompts
A prompt that produces undesirable results is easy to call bad. But there's another kind that's harder to spot.