✦ New tips daily
Claude Code: from zero to professional. Tips, tutorials and deep dive guides from an engineer who uses it 12 hours a day.
Claude Code first steps: the fundamentals that don't expire
The Claude Code fundamentals that don't expire: install, sessions, context, quota, models, permissions. What you actually need to grasp on day 1.
AI: the joy of missing out on what doesn't matter
You can't keep up with AI, and you shouldn't try. The answer isn't resistance or passive acceptance: go all in, but deep on one thing instead of scattered.
Claude Code Agent View: managing parallel agents without leaving the terminal
I spent months managing many Claude Code agents by hand. Agent View now does it: my terminal-native workflow with Warp and Neovim, and the gaps I patch.
Claude Code effort: not the level you think you have
You can spend months running at an effort level you never picked. Five places define it, four of them fail without saying a word, and your settings.json is one of them.
Claude Code thinking: you don't control it anymore, but you pay for it all the same
Thinking stopped being your switch: the model now decides on every step whether to reason at all. You're left with three knobs and, depending on the model you run, one or two of them do nothing at all.
Sonnet 5, Opus 5 and Fable 5: which one I reach for, and what changing your mind costs
You have three frontier models in the picker and the official guidance tells you which is for what. What nobody mentions is the price of changing your mind mid-session, which is the decision you actually make several times a day.
Dependent tasks in Claude Code: catch the flaw in your plan before it runs
Claude Code tasks can block each other. That turns the list into a graph, and a graph can be audited: it shows you how it understood the work before it writes a single line.
Get only what matters
If I have nothing worth saying, you won't hear from me. When I do, you'll be the first to know. 7,000+ people already trust this.
Unsubscribe at any time.