Claude Code for Engineers — From Chat to Coworker

I run engineering at a US startup, and the single biggest gap I see between people who get value from Claude and people who do not is this: most engineers are still typing questions into a chat box and copy-pasting answers back into their editor. That is the slowest possible way to use it.

Claude Code closes the loop. It reads your files, runs your commands, and edits code in place — on your machine, in your repo. The jump from "smarter Google" to "coworker who does the work" is mostly about two habits.

Habit 1: write a CLAUDE.md

Drop a CLAUDE.md in a folder and Claude picks it up on its own whenever you start working there — no copy-pasting context into the prompt each time. It is the difference between onboarding a stranger every morning and working with someone who already knows your stack, your conventions, and the three things you never want them to touch.

Keep it short and specific. Mine usually has four sections:

• Stack — languages, framework, package manager, how to run tests.
• Conventions — naming, error handling, the patterns you actually use.
• Boundaries — what not to change without asking (migrations, auth, billing).
• Commands — the exact build, lint, and test commands.

Habit 2: give it the tools, then let it loop

Once context is solid, stop micromanaging. Let Claude read, plan, edit, and run the tests itself, then react to the result. A typical flow looks like:

# point it at the work, not the keystrokes
claude "add a guides-index.json build step, run the tests, fix until green"

The work that used to be twenty small instructions becomes one clear outcome plus the freedom to iterate. Anthropic's own guidance on context engineering makes the same point: give the model the right context and a tight feedback loop, and quality compounds.

What to do this week

Pick your most active repo. Write a one-page CLAUDE.md. Then hand Claude a real task end to end — not a question, a task — and watch where it gets stuck. Those stuck points are exactly what belongs in your CLAUDE.md for next time. That is the whole game: every session makes the next one sharper.

Sources

• Claude Code documentation
• Anthropic — Effective context engineering for AI agents
• Claude Code power-user tips