Dan Ochs

Dan Ochs is based in Boston in the United States and has 25 years of experience helping enterprises solve their technical challenges. He has done this at large companies like Accenture, Oracle and AWS where he covered financial services, insurance, media and entertainment, manufacturing, gaming, and sports. He also enjoys the challenges of smaller businesses such as Blitzy, where he is currently the Head of Technical Customer Delivery. He has studied generative AI since he first saw the text to image generator from Stability.ai and has been hooked ever since.

Blitzy, USAenterprisegenai.substack.com danochs

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