GIDS news media, articles, insights and virtual events educate and illuminate its audiences so they can be fully prepared to deal with the new realities at work and in their professions.
Get the latest event updates, and insights from today's leading voices.
< session />
AI-NativeArchitecture & Distributed Systems
Most advice about coding agents focuses on prompts, context, or learning the fundamentals. In practice, many teams are encountering a different challenge: modern tooling makes it easy to run multiple coding agents against the same codebase, but most codebases are not structured to support that way of working.
This session examines the workflows teams are using today and the demands those workflows place on software architecture. We will compare sequential single-agent development with approaches that involve multiple agents working concurrently. Topics include agents sharing a working directory, agents operating in separate git worktrees, and the practical trade-offs associated with each model, including isolation requirements, merge conflicts, duplicated dependencies, disk usage, and compute costs.
A central focus of the talk is the use of per-feature dependency graphs and overlap analysis to determine which tasks can be executed in parallel, how work should be sequenced, and how tasks can be decomposed to reduce conflicts during reconciliation. These dependency relationships ultimately define how much parallelism a codebase can support and how work can be distributed across multiple agents.
The session also addresses the reality that many teams cannot immediately restructure existing systems. Attendees will leave with practical patterns for organizing codebases that can support productive collaboration between multiple coding agents, along with a clear understanding of the constraints that limit parallel agent workflows.
What You Will Learn:
Who Should Attend:
< speaker_info />
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.
