Jules: An AI Agent That Thinks, Argues, and Writes

I built Jules — a Claude Code-based AI agent with a personality, opinions, and structured decision-making workflows. Jules isn’t just a coding assistant — it’s a strategic thinking partner that follows multi-step reasoning processes, pushes back on my ideas, runs adversarial reviews before recommending anything, and writes content in my voice. I’ll demo the live system: how a single prompt triggers structured thinking workflows with visible reasoning steps, how the agent challenges my framing before agreeing with me, and where this is headed — multi-agent coordination through Paperclip and a conversational gateway called Hermes.