One agent or many? Start with the task, not the architecture. Use one agent for sequential, stateful work. Test several when the task splits cleanly or benefits from independent verification. Keep the complexity only if it materially improves the result.
Prompt engineering asks: how do I get a better response? Loop engineering asks: how does the system know the work is actually done? I just published an introduction to loop engineering, including how it builds on prompt, context, and harness engineering, and what reliable agent
Who still understands the code? Coding agents make you faster at producing code and, if you are not careful, slower at understanding it. AI pays down technical debt and quietly runs up cognitive debt. New post on that trade, and how I try to stay on the right side of it.
"I think the most valuable engineer over the next five years will not be the one who writes code fastest, but the one who orchestrates most effectively: someone who can point an agent at a problem, judge what comes back, steer the next attempt, and know when to stop and do the