A multi-agent orchestration system emerged from a hack days frustration—manually copying code between two Claude Code windows. What started as a simple experiment became a tool that reduced a 22-hour task to 7 minutes and saw significant adoption across Shopify.
Key lessons from the journey:
- The best automation starts with your own pain - Personal frustrations often lead to broadly useful tools
- Specialization beats complexity - Focused agents outperform monolithic prompts
- Users reveal what you actually built - Unexpected adoption from non-technical teams showed use cases never imagined
- Listen more than design - Real usage teaches more than any framework
- Evolution beats perfection - Ship, learn, iterate
- Patterns emerge organically - Tree-based collaboration appeared from how people naturally break down problems
This talk walks through the journey from copy-paste frustration to production tool, sharing the decisions made, surprises encountered, and lessons learned from real-world adoption. You'll see the messy reality of building AI systems and gain a practical perspective on when and how to use multi-agent approaches.
Speaker
Paulo Arruda
Senior Production Engineer @Shopify, Author of faastRuby
Paulo Arruda is a Staff Engineer at Shopify, helping shape AI orchestration strategy for Revenue Data after serving as tech lead for the company's Augmented Engineering Developer Experience team. Creator of Claude Swarm (1.4k+ GitHub stars) and its successor SwarmSDK—a multi-agent orchestration framework in Ruby—he has delivered 65-190x automation speedups and reduced 20-hour workflows to minutes. With 15+ years as a backend and infrastructure engineer, Paulo combines platform thinking with pragmatic skepticism, advocating for AI that augments rather than replaces developers—and isn't afraid to question the hype.
Slides are not
available
