From Prompt to Production: Building AI Systems That Actually Work
AI can now generate code, tests, documentation, and even entire applications in minutes. Yet many organizations are discovering that faster code generation has not translated into faster delivery, higher quality, or greater business impact. Instead, teams are often facing more code churn, more technical debt, and more production incidents. The challenge is no longer getting AI to write code. The challenge is building systems that consistently deliver value to end users. Drawing on real-world experience building AI products, agent-based systems, evaluation frameworks, and production applications, Jeremiah will share the practices that separate successful AI-native teams (product, design, engineering, and test) from those overwhelmed by "code overload." Attendees will learn practical approaches to context engineering, specification-driven development, problem decomposition, evaluation, testing, feedback loops, and AI-native CI/CD. The session will also explore the emerging Agentic Development Lifecycle (ADLC), including how to effectively orchestrate AI agents while maintaining quality, security, and trust. At its core, this talk is built around a simple idea: AI does not eliminate engineering. It shifts engineering from writing code to designing systems, orchestrating agents, evaluating outcomes, and accelerating learning. Whether you're building AI products, integrating AI into existing applications, or leading teams through AI transformation, you'll leave with a practical framework for moving from prompt experimentation to production systems that users can trust.
Jeremiah Marble is a technical AI product leader, author, and speaker who focuses on building high-quality, customer-centric software in the AI era. He’s currently writing code as the CTO of Playbook, an AI-based startup bootstrapping in the EdTech space. He also speaks, teaches, and leads workshops on AI, agents, and responsible AI (RAI) at 3rd Rodeo AI. Previously, Jeremiah held leadership roles at Mozilla and Microsoft—where he helped grow the Windows Insider Program from a whiteboard idea to more than 22 million people worldwide. An advocate for tech for good and social entrepreneurship, Jeremiah launched “Do The Thing Academy” and co-wrote Model 47: A Startup Storybook to help non-traditional founders turn napkin ideas into responsible businesses. He co-founded ethical fashion line Prima Dona Studios, empowering single mother tailors worldwide - including in Senegal, Mexico, and with Afghan refugees in Seattle. Previously, Jeremiah worked for the UN in Africa and Asia, was a Fulbright Scholar to Costa Rica, and volunteered in the Dominican Republic with the Peace Corps. He earned an MBA from Wharton, MA in International Studies from U Penn, and CS undergrad from Columbia.