We're building a GTM agent for a private equity firm. It'll run outbound campaigns for all of their portfolio companies. We've built GTM agents before. But we're running a fun experiment behind the scenes for this one: We're going to build it on 5 different agent harnesses. Then give the client the one that performs best. This is AI-native engineering at it's finest. The hardest part of this project is the architecture and development plan: - Defining the desired outcome - Aligning on what good looks like - Context engineering for each port co - Making it scalable and reliable across campaigns The easiest part of this project is getting Claude Code to write the code that meets the specs of the plan. Code is abundant now. So we're taking advantage. Plan once, build 5 different versions. Throw away 4, ship 1.