Anthropic published how their teams use Claude Code, ranging from engineering, legal, to product development and design. Here are some high-level tips that might resonate with you as you’re considering AI adoption at your workplace:
Get proper setup help from engineers since the technical onboarding can be challenging for non-developers.
Overcome the urge to hide “toy” projects or unfinished work - sharing prototypes helps others see possibilities and sparks innovation across departments that don’t typically interact. This also helps spread best practices and knowledge. Hold sessions where team members can demonstrate their Claude Code workflows to each other.
Rather than expecting Claude to solve problems immediately, approach it as a collaborator you iterate with. For example, while supervising, don’t hesitate to stop Claude and ask “why are you doing this? Try something simpler.”
The better you document your workflows, tools, and expectations in Claude.md files, the better Claude Code performs.
Learn to distinguish between tasks that work well asynchronously (peripheral features, prototyping) versus those needing synchronous supervision (core business logic, critical fixes).
Regularly commit your work as Claude makes changes so you can easily roll back when experiments don’t work out.
Instead of trying to handle everything in one prompt or workflow, create separate agents for specific tasks (like their headline agent vs. description agent). I’ve been working on this myself (and mention this here.
If you’ve already been working with AI tools, which tips are validating your own findings? Or which are ones that are newly insightful to you? I’m curious to know!
This post was originally on LinkedIn.