10 posts
Not a tools list. The tools changed three times this year; what changed underneath is where the hours go: specs in the morning, batch review in the afternoon, and the judgment work that never left.
The code got cheap. The review did not. Here is the review workflow I actually use when AI agents write most of the diff: three passes, an adversarial second agent, and the discipline of reading what ships.
A practical, plain-spoken manual for building software with an AI agent: the setup, the loop, context management, and verified Claude Code and Copilot commands. Written like the old Linux HOWTOs, by someone who runs it daily.
The suit never replaced Tony Stark. It amplified him. That is the closest thing I have to a description of what it feels like to build software in agent mode, directing one or many agents and scaling your own thought and output.
This site was rebuilt from scratch by directing an AI agent, then migrated off cPanel onto AWS S3 and CloudFront. Here is what that actually looked like, the parts that worked, and the day a deploy script quietly deleted production.
Autonomous mode is when the agent runs the whole loop without you in it: plan, act, check, repeat, until the task is done or it gets stuck. Here is what that means, how it differs from agent mode, and where the real risk lives.
A practical, repeatable workflow for building software with an AI agent: specify, delegate, verify, record. The loop I actually run every day, with the parts that keep it from turning into slop.
I used GitHub Copilot in VS Code for a long time, always with Claude underneath. Then I moved most of my work to Claude Code. Here is the honest comparison for DevOps and infrastructure work, from someone who ships with both.
Agent mode is when you stop typing code and start directing an AI that reads your codebase, writes the change, runs the tests, and reports back. Here is what it actually is, how the loop works, and when to reach for it, from someone who ships production systems this way.
I don't think in fragments. I don't think in lines. I think in systems. In architectures. In complete solutions to complete problems. So I stopped fighting autocomplete and found what actually works: agent mode.