<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/ai-coding-agents-are-breaking-big-codebases-dan-adler-sourcegraph-oi3xfnhvv" -->

---
title: AI Coding Agents Are Breaking Big Codebases — Dan Adler,...
description: A conference talk by Sourcegraph's CEO Dan Adler argues that AI coding agents, while accelerating code production, are destabilizing massive legacy codebases...
canonical: https://daily.dev/posts/ai-coding-agents-are-breaking-big-codebases-dan-adler-sourcegraph-oi3xfnhvv
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: AI Coding Agents Are Breaking Big Codebases — Dan Adler, Sourcegraph | daily.dev
og:description: A conference talk by Sourcegraph's CEO Dan Adler argues that AI coding agents, while accelerating code production, are destabilizing massive legacy codebases...
og:url: https://daily.dev/posts/ai-coding-agents-are-breaking-big-codebases-dan-adler-sourcegraph-oi3xfnhvv
og:image: https://api.daily.dev/og/posts/oi3XfnHVv.png
og:image:alt: AI Coding Agents Are Breaking Big Codebases — Dan Adler, Sourcegraph
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

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

**[AI Engineer](https://daily.dev/sources/aidotengineer)** · 12 min read · 2 upvotes · 0 comments

## Summary

A conference talk by Sourcegraph's CEO Dan Adler argues that AI coding agents, while accelerating code production, are destabilizing massive legacy codebases at large enterprises—introducing inconsistent standards, duplicate code, fragile inter-service dependencies, and new vulnerabilities faster than teams can review them. He claims current agent tooling from OpenAI, Anthropic, and Cursor lacks the infrastructure to see and understand codebases spanning tens of thousands of repositories, and positions a code graph (search plus accurate compiler output) as the missing visibility layer. He announces Sourcegraph's new batch-changes agent product, now in beta, which can commit changes across hundreds or thousands of repositories from a single prompt, citing a Mercari user who used it to find 80 additional instances of a configuration vulnerability beyond the two they already knew about.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.youtube.com/watch?v=Bdrs3uAX0_M>

## Questions this post answers

### What is Sourcegraph's new batch changes agent product announced in this talk?

It is an agent product, launched into beta, that lets owners of massive codebases commit changes across hundreds or thousands of repositories simultaneously from a single prompt. It iteratively implements changes across an entire codebase, independently fixes errors, responds to CI status and PR comments, and provides tracking and auditing to confirm full coverage of required changes.

_Teams managing sprawling multi-repo codebases can follow coverage of agent tooling like this on daily.dev._

### How did a Mercari engineer use an AI agent to find security vulnerabilities across their codebase?

An early-access user at Mercari, a Japanese trading service with hundreds of microservices in production, ran the agent on two repositories where a code injection issue involving misconfigured environment variables was already known, then let it explore the rest of the codebase. It found 80 additional potential vulnerabilities in configuration files and fixed them in one deterministic pass.

_Developers hunting for similar config vulnerabilities across repos can track these agent security workflows on daily.dev._

## Similar posts on daily.dev

- [Coding agents are scaling fast. How do teams keep up?](https://daily.dev/posts/coding-agents-are-scaling-fast-how-do-teams-keep-up--spuq20grp) · Dynatrace · 0 upvotes · 0 comments
- [When Agentic Coding Goes Off the Rails](https://daily.dev/posts/when-agentic-coding-goes-off-the-rails-901po5tdi) · RUBYLAND · 0 upvotes · 0 comments
- [Using AI agents to secure Google infrastructure](https://daily.dev/posts/using-ai-agents-to-secure-google-infrastructure-n2sosodh7) · Google Cloud · 0 upvotes · 0 comments
- [When code is abundant](https://daily.dev/posts/when-code-is-abundant-gezbqtizx) · GitLab · 0 upvotes · 0 comments

---

Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#devtools](https://daily.dev/tags/devtools), [#security](https://daily.dev/tags/security)

[View this post on daily.dev](https://daily.dev/posts/ai-coding-agents-are-breaking-big-codebases-dan-adler-sourcegraph-oi3xfnhvv)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"AI Coding Agents Are Breaking Big Codebases — Dan Adler, Sourcegraph","url":"https://daily.dev/posts/ai-coding-agents-are-breaking-big-codebases-dan-adler-sourcegraph-oi3xfnhvv","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/ai-coding-agents-are-breaking-big-codebases-dan-adler-sourcegraph-oi3xfnhvv"},"datePublished":"2026-10-04T19:47:18.649Z","dateModified":"2026-11-12T02:15:47.428Z","description":"A conference talk by Sourcegraph's CEO Dan Adler argues that AI coding agents, while accelerating code production, are destabilizing massive legacy codebases...","image":"https://i.ytimg.com/vi/Bdrs3uAX0_M/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/Bdrs3uAX0_M/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/ai-coding-agents-are-breaking-big-codebases-dan-adler-sourcegraph-oi3xfnhvv","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,devtools,security","timeRequired":"PT12M","video":{"@type":"VideoObject","name":"AI Coding Agents Are Breaking Big Codebases — Dan Adler, Sourcegraph","description":"A conference talk by Sourcegraph's CEO Dan Adler argues that AI coding agents, while accelerating code production, are destabilizing massive legacy codebases...","thumbnailUrl":"https://i.ytimg.com/vi/Bdrs3uAX0_M/sddefault.jpg","uploadDate":"2026-10-04T19:47:18.649Z","duration":"PT12M","url":"https://api.daily.dev/r/oi3XfnHVv","embedUrl":"https://www.youtube.com/embed/Bdrs3uAX0_M"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"AI Coding Agents Are Breaking Big Codebases — Dan Adler, Sourcegraph"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/ai-coding-agents-are-breaking-big-codebases-dan-adler-sourcegraph-oi3xfnhvv#faq","mainEntity":[{"@type":"Question","name":"What is Sourcegraph's new batch changes agent product announced in this talk?","acceptedAnswer":{"@type":"Answer","text":"It is an agent product, launched into beta, that lets owners of massive codebases commit changes across hundreds or thousands of repositories simultaneously from a single prompt. It iteratively implements changes across an entire codebase, independently fixes errors, responds to CI status and PR comments, and provides tracking and auditing to confirm full coverage of required changes. Teams managing sprawling multi-repo codebases can follow coverage of agent tooling like this on daily.dev."}},{"@type":"Question","name":"How did a Mercari engineer use an AI agent to find security vulnerabilities across their codebase?","acceptedAnswer":{"@type":"Answer","text":"An early-access user at Mercari, a Japanese trading service with hundreds of microservices in production, ran the agent on two repositories where a code injection issue involving misconfigured environment variables was already known, then let it explore the rest of the codebase. It found 80 additional potential vulnerabilities in configuration files and fixed them in one deterministic pass. Developers hunting for similar config vulnerabilities across repos can track these agent security workflows on daily.dev."}}]}
```

