Kranthi Manchikanti

Kranthi Manchikanti is an AI engineering and solutions leader focused on taking AI systems from prototypes to production at enterprise scale. He has worked with global organizations on production AI architecture, developer platforms, agentic systems, and large-scale software modernization. He also runs The AI Runtime, a community and publication focused on production AI engineering, Forward Deployed Engineering, and the systems behind reliable AI applications. Kranthi is also an NVIDIA Developer Champion and regularly brings together engineers and AI infrastructure teams through technical workshops, events, and conversations.

Blitzy, Bostonogkranthi kranthimanchikanti

The Context Window Is Not Your Codebase: Enterprise Lessons for Scaling Coding Agents

AI Coding Summit NYC

Upcoming

The Context Window Is Not Your Codebase: Enterprise Lessons for Scaling Coding Agents

AI coding agents work impressively when the task fits inside a few files. Enterprise software rarely does.
A seemingly simple requirement can cross hundreds of files, shared libraries, APIs, data models, tests, infrastructure, and years of architectural decisions. At that scale, putting more source code into an LLM context window is not the same as giving an agent an understanding of the system.
This talk shares lessons from building AI-augmented software development for large enterprise codebases. We’ll examine why file-level retrieval and ever-larger context windows break down, how coding agents can construct a task-specific model of a codebase using structural relationships and iterative exploration, and why planning and verification become more important than code generation as agent autonomy increases.
The goal is to move the conversation from “How much code can the model see?” to “How does the agent determine what actually matters for this change?”

builders and founders