AI for Developers

Most Recent

AI for Developers

How to Use CI as Your Agent Loop

Strangely, designing a useful agent loop turns out to be eerily similar to designing feedback loops in "pre-AI" software engineering.

AI for Developers

I'm not all that convinced I'm all that much faster with AI. The code comes out faster, sure. But the code was never the whole job.

AI for Developers

I recently wrote about my client team's decision to make human code review optional. Enough time has passed to share some honest reflections.

AI for Developers

AI reads code better than humans can, and Grep is 10,000 times faster than human eyeballs! What do we find joy and pride in now?

AI for Developers

The insight isn't just about adding AI analysis to your tooling. It's about deliberating on what problem you're asking it to solve.

AI for Developers

In software's history, the limit on what you could ship was how fast you could type and build. Execution got cheap. Attention got expensive.

AI for Developers

While generating comparison concepts with a model, I had to change the team's approach; the AI couldn't have asked the question that mattered.

AI for Developers

Every permission prompt is supposed to be a checkpoint where a human looks at what the AI is about to do and decides whether it's safe.

AI for Developers

The size of the task you can hand to a coding agent is bound by the quality of its feedback loop and its ability to validate its work.

AI for Developers

Drowning in markdown specs? Here's how I used AI to build a lightweight, regenerable HTML spec dashboard for faster, cleaner reviews.

AI for Developers

Frontier models are powerful, but increasingly expensive. Are local models a good option for helping to carry some of the workload?

AI for Developers

If code can only be modified safely by the original developer with the original agent setup, then the delivery is weaker than it looked.