11. Agentic Autonomy Levels In most conversations about agentic engineering, the action has changed from prompting to operating . Here’s a frontier looking into the fog: software factories, goals, loops 07/03 22:30 ♡
12. Agentic Code Review Coding agents are extraordinarily good now and getting better fast. The interesting consequence is that the hard part of engineering moved from writing code to deciding whether to 06/16 22:31 ♡
13. Loop Engineering Loop engineering is replacing yourself as the person who prompts the agent. You design the system that does it instead. A loop here can be thought of a recursive goal where you def 06/08 22:31 ♡
14. Long-running Agents A long-running AI agent can keep making progress over hours, days, or weeks. It can do this across many context windows and sandboxes, recover from failure, leave structured artifa 04/30 22:30 ♡
15. The Agent Stack Bet Peek under the hood of most “production agents” shipping today and you won’t find intelligence. You’ll find custom plumbing, fragile session logic, shared s 04/19 01:16 ♡
16. Is the IDE dead? The center of developer work is moving. Not disappearing - moving. Away from continuous, line-by-line editing inside a single window, and toward supervising agents that can plan, r 03/20 22:31 ♡
17. 14 More lessons from 14 years at Google A while back, I wrote down 21 lessons from my time at Google . The response caught me off guard because of which ones stuck. It wasn’t tech-specific advice. It was the stuff 02/12 23:30 ♡
18. The 80% Problem in Agentic Coding said something this week that made me pause: “I rapidly went from about 80% manual+autocomplete coding and 20% agents to 80% agent coding and 20% edits+touchups. I really am 01/29 01:20 ♡
19. How to write a good spec for AI agents TL;DR: Aim for a clear spec covering just enough nuance (this may include structure, style, testing, boundaries) to guide the AI without overwhelming it. Break large tasks into sma 01/19 23:31 ♡
20. Code Review in the Age of AI AI did not kill code review. It made the burden of proof explicit. Ship changes with evidence like manual verification and automated tests, then use review for risk, intent, and ac 01/05 23:30 ♡
