Here's what you did. You installed OpenClaw with npm install -g openclaw@latest and ran the onboarding wizard. Then you started the Gateway daemon as a system service. You connected at least one messaging platform and chose an AI model.
You wrote config files: SOUL.md for personality and AGENTS.md for safety boundaries. You also set up IDENTITY.md for presentation and USER.md for personal context. You learned how the permission system works in layers (identity, scope, model) and how tool policies and sandbox mode add further protection.
In the next section, I'll show you how to give your assistant tools so it can do more than just chat. That's where things get interesting.