< session />
The AI-Native Codebase
AI coding assistants are transforming how software is written, but scaling their use across teams introduces new challenges in reliability, maintainability, and quality. Many teams rely on trial and error when adopting AI for development, resulting in inconsistent and difficult-to-manage codebases. This session presents a five-level maturity model for evolving into an AI-native codebase, one that supports sustainable, production-quality development with AI at scale.
Each level includes practical checklists, assessment criteria, and real-world case studies that show how to balance AI’s strengths with human oversight. The framework helps teams design verification systems that emphasize correctness, guide developers toward higher-quality collaboration with AI tools, and lead their organizations through a structured transformation process.
What You Will Learn
-
A five-level maturity model for building AI-native codebases
-
Success criteria for assessing progress and quality at each stage
-
How to design verification and governance systems for AI-assisted development
-
Strategies for guiding teams toward sustainable human-AI collaboration
Who Should Attend
Software architects, engineering managers, technical leads, and developers interested in scaling AI-assisted development practices and building maintainable, production-grade systems.
< speaker_info />
About the speaker
Ragunath Jawahar
Founder, Legacy Code HQ
Ragunath Jawahar is the Founder of Legacy Code HQ, where he specializes in helping developers and organizations master massive, complex codebases. With nearly 15 years in the industry and 5 years working with large codebases across startups and enterprises, he discovered that software complexity is fundamentally a human comprehension problem, not just a technical one.
To solve this challenge, Ragunath has built innovative visualization tools including Eureka and Timelapse (open-sourced on GitHub), which help developers navigate complex systems by surfacing relevant information while filtering out noise. His unique expertise combines legacy codebase rescue with 2+ years of AI-assisted development experience, positioning him to address a critical emerging problem: AI's acceleration of generating hard-to-maintain codebases.
Through his work at Legacy Code HQ, Ragunath teaches developers how to harness generative AI to build production-grade applications while avoiding maintainability pitfalls—leveraging first principles from human cognition, software development, and AI. This rare combination of legacy code mastery and AI expertise makes him uniquely qualified to help teams build maintainable software in the age of AI acceleration.
