Your expertise no longer limits what you can build. After two decades in digital products, I help professionals build and manage their own AI agents, with practical, step-by-step how-to guides.
In Part 1 you designed your agent: three files that say who the agent is, who you are, and which tools it can use. Now you build it in Claude Code.
By the end of this guide, you'll:
Connect your agent's tools to Claude Code and set what it's allowed to do.
Build your agent from your design files in a plan-first session.
Test it, then set it live so it runs on its own.
Note: This is Part 2, where you build the agent you designed in Part 1. You need those three design files, the skills your agent uses from the Skills guide, and Claude Code, Anthropic's tool for running agents on your computer. It needs a paid plan, and its usage limits are tight, so choose Pro or higher for daily use. This part gets technical in places. Claude walks you through it, and you can always ask it to slow down and explain.
Build your agent
The method is the same for any agent: connect its tools, set permissions, add its skills, then build and test it in Claude Code. We'll keep building the personal assistant from Part 1, the one that triages the inbox, processes invoices, and tracks action items.
Your expertise no longer limits what you can build. After two decades in digital products, I help professionals build and manage their own AI agents, with practical, step-by-step how-to guides.
