Taming the Dragon: Ship Production Code with AI Coding Agents

Taming the Dragon: Ship Production Code with AI Coding Agents
Abstract:
Coding agents like Claude Code and Cursor promise to revolutionize how software gets built—but in untrained hands, they behave more like dragons: powerful, unpredictable, and capable of burning down a codebase. After using coding agents to build scalable, maintainable production applications, Steven Diamante has found that traditional software craftsmanship principles aren’t just relevant in AI-assisted development—they’re essential for survival.
In this session, Steven demonstrates how engineering practices such as test-driven development (TDD), continuous refactoring, and working in small batches turn unpredictable agents into reliable, collaborative partners. Through hands-on agent collaboration, attendees will build an application from scratch and see how tight feedback loops and precise task breakdown transform chaotic AI output into production-ready code.
By the end of this session, attendees will be able to:

• Configure coding agents to enforce a team’s coding standards
• Use TDD to guide AI code generation and prevent technical debt
• Collaborate with agents in small batches to produce production-ready code

About the Speaker:
Steven Diamante is a technical coach who helps software teams get real value from AI coding agents. Many teams use AI to generate code quickly—then lose time debugging and repairing unintended complexity. Steven teaches teams to apply TDD and strict quality gates to keep agents steerable, ensuring teams build the right thing in small, controllable steps. Through hands-on Samman Coaching, he helps teams transform how they work with AI while maintaining technical excellence.
Outside of coaching, Steven enjoys playing guitar at his local church, reading non-fiction, and spending time with his wife and two kids.