Innovation Matters
Essays on AI, developer tools, and thoughtful software.
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.
Your agents should learn for the organization
Your agents discover stale guidance and hidden constraints every day. When the conversation ends, who gets to keep what they learned?
When organizations can build faster than they can agree
When building becomes cheaper than another alignment meeting, every team has a rational reason to ship its own solution. Who pays when all of them do?
Every team needs a knowledge interface
Organizations have spent years improving how people find knowledge. Agents don't just find it. They make decisions with it.
"Coding is solved" misses the point
Every few weeks, someone declares that coding is solved. If they mean turning a well-specified problem into runnable code, they're increasingly right. But was writing runnable code ever the whole problem?