Jan 7, 2026

MUHAMMAD GHIFARY

I recently came across an insightful thread on X by Boris Cherny, one of the creators of Claude Code, detailing his workflow for AI-driven software engineering. I have included his full post below to serve as a study guide, as many of these patterns are platform-agnostic and equally applicable to other agentic coding tools.

Gone are the days when software engineering meant writing every line of code manually or staring blankly at a blinking cursor. We are entering the exciting era of Agentic Software Engineering (SE 3.0), where developers evolve from mere code writers into system architects and orchestrators.

In this new paradigm, the bottleneck is no longer how fast you can type syntax, but how clearly you can articulate intent. SE 3.0 isn't just about auto-completion; it is about delegating the entire OODA loop (Observe, Orient, Decide, Act) of development to AI. We are moving toward a workflow where the human engineer focuses on high-level system design, edge-case reasoning, and strategic decision-making, while AI agents handle the implementation, testing, and iterative refactoring.

With that context in mind, Boris Cherny’s thread offers a practical, real-world glimpse into what this workflow looks like today.

I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit.

My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently.

So, here goes.

  1. I run 5 Claudes in parallel in my terminal. I number my tabs 1-5, and use system notifications to know when a Claude needs input https://code.claude.com/docs/en/terminal-config#iterm-2-system-notifications

G9rtc4EasAELEzh.jpeg

  1. I also run 5-10 Claudes on http://claude.ai/code, in parallel with my local Claudes. As I code in my terminal, I will often hand off local sessions to web (using &), or manually kick off sessions in Chrome, and sometimes I will --teleport back and forth. I also start a few sessions from my phone (from the Claude iOS app) every morning and throughout the day, and check in on them later.

    G9reZjqaYAA9btU.jpeg

  2. I use Opus 4.5 with thinking for everything. It's the best coding model I've ever used, and even though it's bigger & slower than Sonnet, since you have to steer it less and it's better at tool use, it is almost always faster than using a smaller model in the end.

  3. Our team shares a single CLAUDE.md for the Claude Code repo. We check it into git, and the whole team contributes multiple times a week. Anytime we see Claude do something incorrectly we add it to the CLAUDE.md, so Claude knows not to do it next time. Other teams maintain their own CLAUDE.md’s. It is each team's job to keep theirs up to date.