When Boris Cherny, the creator of Claude Code, shared his personal workflow, it revealed something fascinating: the most powerful way to use AI coding assistants isn’t to replace your terminal with a single chatbot. Instead, it’s about orchestrating multiple AI agents working in parallel, each on their own task, while you context-switch between them like a conductor managing an orchestra.

Boris Cherny’s Post on X

After months of testing various AI coding platforms (as I detailed in my vibe coding review), I’ve come to appreciate that the implementation details matter as much as the underlying AI model. Boris’s approach represents... read more

If you’ve used Claude Code for any length of time, you’ve probably found yourself repeatedly prompting Claude to do the same tasks. Run tests. Format code. Commit changes. Deploy to staging. These repetitive prompts slow you down and introduce inconsistency.

The solution? Custom skills, which Claude Code calls “slash commands.” These are reusable scripts that Claude (and you) can invoke with a simple command like /test or /deploy. They’re essentially bash scripts with superpowers, and they’re one of the most underutilized features of Claude Code.

What Are Skills?

Skills in Claude Code are executable scripts stored in your... read more

You’ve probably seen the headlines from Fortune, Yahoo Finance, and others: “MIT Study Shows 95% of AI Pilots Fail.” It’s been making rounds across tech media, spooking investors, and reinforcing every AI skeptic’s worldview. But when you dig into the actual research from MIT’s NANDA project, a different story emerges—one that reveals more about sensationalist journalism than AI failure rates.

When you’re reading something (yes, even this post), you should always question the sources. Who is saying what? What is their agenda? For example, if an oil company is releasing their research on climate impact, you should be skeptical, right?

“I... read more