# AI Coding Agents Are Breaking Big Codebases — Dan Adler, Sourcegraph

## Executive summary

The talk addresses the critical challenge of maintaining massive, decades-old codebases (tens of thousands of repositories) in the era of AI coding agents. While agents accelerate development, they also accelerate codebase decay through duplicated code, drifting standards, and new vulnerabilities. Dan Adler argues that the bottleneck is not model quality, but the infrastructure required for large-scale code visibility. Sourcegraph introduces 'Agentic Batch Changes,' a product designed to execute code changes across thousands of repositories from a single prompt, ensuring auditability and consistency across complex, distributed systems.

## Key takeaways

- The Scale Problem: Most software industry employment is in large enterprises managing thousands of repositories and decades of code history, making codebase ownership increasingly difficult.
- Codebase Decay: AI-generated code, while fast, is causing decay by proliferating duplicated code, creating brittle cross-service dependencies, and introducing new vulnerabilities.
- Visibility is Infrastructure: The core problem is the volume of code; agents cannot understand what they cannot see. Large-scale code visibility and a comprehensive 'code graph' are essential infrastructure requirements.
- Agentic Batch Changes: Sourcegraph launched 'Agentic Batch Changes,' a frontier agent that allows owners to execute code changes across hundreds or thousands of repositories from a single prompt, providing necessary tracking and auditability.

## Technical details

- Codebase Architecture: Large enterprises manage massive codebases, often comprising tens of thousands of repositories and millions of lines of code, which exceed the capacity of standard context windows.
- Agentic Development: AI coding agents are accelerating development but require infrastructure to manage cross-repository changes and ensure consistency across distributed microservices.
- Sourcegraph Solution: The proposed solution involves building a foundational 'code graph' that provides deep visibility, enabling 'Agentic Batch Changes' to patch vulnerabilities or implement features across vast numbers of repos simultaneously.

## Practical implications

- Build teams must prioritize code visibility infrastructure (code graph) over relying solely on LLM context windows.
- Adopting agentic tools requires robust mechanisms for cross-repository change management and auditability (e.g., Agentic Batch Changes).
- Codebase owners must anticipate that the volume of code will continue to grow, necessitating scalable tooling to prevent decay.

## Topics

Codebase Management, AI Development Tools, Software Architecture, DevOps, Code Visibility, Sourcegraph, Agentic Batch Changes

Source: https://www.youtube.com/watch?v=Bdrs3uAX0_M