Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Don't Lose the Engineering: Parallel Development with AI Agents, Human Orchestration & a Real Methodology
Learn a methodology for parallel AI agent development, human-orchestrated, to build SaaS products efficiently. Discover how to validate AI output, avoid tech debt, and streamline processes for real value.
We built an internal development methodology and orchestration system where AI agents develop features in parallel — coordinated by human architects — shipping an international-grade SaaS product in 3 months. The demo shows our real workflow: how we structure agent-driven development cycles, how our CTO/CPO + backend architect (Lorgi) + frontend architects (Francisco, Mike) validate and audit every AI-generated output, and how we stripped Scrum down to what actually works — killing the bureaucracy and replacing it with product development iterations focused on real value. I’ll walk through our local-first approach where each engineer runs their own AI pipeline before integration, our governance structure, and how we recovered engineering rigor after almost losing it to uncontrolled vibe coding. Live demo on our actual codebase and orchestration tools.