My Claude best practices (so far)
Prompting rules built by trial and error. Pick the right model, curate context, and iterate on your own process.
Here you'll find my guides to working with Claude, Anthropic's AI assistant, from a practical, hands-on angle. The focus is on what you can actually do with these tools, so I stick to real workflows: getting useful output, wiring Claude into the work you already do, and turning it into something that saves you time. A big part of that is Claude Code, and I show you how to use it as an automation tool rather than just a chat window. You'll see how it can read a project, run commands, edit files, and carry out multi-step tasks on your behalf, so it feels less like a chatbot and more like a capable assistant you can hand real work to. Along the way I share the prompting techniques that make a difference, the patterns for integrating Claude through its API, and the guardrails that keep an AI helper reliable.
Prompting rules built by trial and error. Pick the right model, curate context, and iterate on your own process.