Sourcegraph (@Sourcegraph) / X

Pinned

Today we're launching Agentic Batch Changes in public beta, and we're proud of how it's turning out. Mercari engineer Patrick Klitzke used Agentic Batch Changes during our experimental preview to scope and begin patching a GitHub Actions security vulnerability across their

Sourcegraph

@Sourcegraph

17h

1/2) Most AI coding agent failures aren't model failures. They're context failures. When an agent can't see across your repos, it has to guess. Wrong paths, missing dependencies, and confident nonsense.

00:00

Sourcegraph

@Sourcegraph

17h

2/2) We tested it on real large-scale codebases (Kubernetes, Apache Kafka) with CodeScaleBench. The results: ✅ 3x better precision ✅ A cross-file task that took 2 hours now takes 89 seconds Give your agents the context to get it right:

Make AI coding agents effective at scale | Sourcegraph

What does it take to run coding agents reliably in enterprise codebases? Not just better models. Better context. Better workflows. Better systems around the agent. Running Coding Agents in Enterprise Codebases explores the patterns emerging among teams moving from AI

Sourcegraph

@Sourcegraph

Jul 16

1/ Changing code in one repo is easy. Rolling that same change across tens or hundreds of repos is a different problem entirely.

Sourcegraph

@Sourcegraph

Jul 16

Replying to @Sourcegraph

3/ What if you could define the migration in plain English, validate it on one repo, then apply it across your whole codebase with deterministic execution and a human in the loop?

Sourcegraph

@Sourcegraph

Jul 16

4/ That's the workflow we broke down in this webinar. See how it works:

Modernizing Code at Scale: What's Now Possible with Agentic Batch Changes

On owning a codebase, and why it may be the hardest job in software

It may feel anachronistic to think about a codebase as anything more than an temporary artifact of a prompt. And it feels positively uncool to care about the code as much as the product. But this is...

Replying to @DanielNealAdler

Today we launch Agentic Batch Changes into public beta. It is the frontier agent that lets the owner of a massive codebase execute code changes across hundreds (or hundreds of thousands) of repositories at once, starting with a single prompt. It iteratively rolls out the

Agentic Batch Changes

Heading to AI Engineer World's Fair? Visit Sourcegraph to learn how engineering teams are modernizing large codebases, managing AI-generated change, and building the foundation for reliable coding agents at enterprise scale. Stop by the booth, catch our sessions, and join us

Sourcegraph

@Sourcegraph

Jun 24

Deep Search will now automatically compact long conversations when a follow-up question is close to the context window limit. (1/2)

00:00

Sourcegraph

@Sourcegraph

Jun 24

(2/2)

Longer Deep Search conversations with automatic compaction

From our changelog: - Auto-compaction for longer, uninterrupted Deep Search convos - New "Finder" subagent for smarter, token-efficient file discovery - Smart hover summaries are now GA

I’m giving a talk at the @aiDotEngineer World’s Fair 🥳 The talk will be focused on the emerging role of Agent Advocates, what changes when agents are your product users and recommenders, and agent-powered GTM.

Sourcegraph

@Sourcegraph

Jun 15

You can now have longer Deep Search conversations on Sourcegraph Cloud. We added automatic compaction to help keep your threads manageable as they grow.

Sourcegraph

@Sourcegraph

Jun 11

Agent failures in large codebases are not random. Data from 1,281 agent runs across 40+ large open source repositories reveals five repeatable failure patterns that show up across coding agents. Each failure pattern points to a different infrastructure problem and a different

Why coding agents fail in large codebases (and what to do about it)

Pin the dependencies that matter most sourcegraph.com/blog/dependenc…

00:00

Sourcegraph

@Sourcegraph

Jun 8

We automated our security workflow by connecting @Hacker0x01 webhooks to Sourcegraph Deep Search. The system validates and finds fixes for vulnerability reports before you even start work. This helps us address issues faster and removes the manual effort of triaging reports.

Automating Security Triage with HackerOne and Deep Search

From sourcegraph.com