Sourcegraph

Take control of your codebase.

[Sourcegraph @Sourcegraph]

Code Finder is now generally available.

https://t.co/6kuMiP8nI0

[Dan Adler @DanielNealAdler]

Many customers ask me what Code Finder is, and why we introduced a second agentic search on top of Sourcegraph's (deterministic) code graph.

On the 2x2 of cost vs. comprehensiveness, it was important to us to have an offering at the frontier in both the top right and bottom left. Code Finder is NOT for a deep, global investigation like Deep Search. It's faster, cheaper, and a perfect daily driver upgrade over ripgrep (not to mention for high-volume automated workflows).

Code Finder is also our *first* MCP-only product 👀. Humans need not apply.

[Sourcegraph @Sourcegraph]

Starting December 7, federal agencies will have as little as three days to remediate vulnerabilities in the highest-risk class of flaws.

That urgency extends beyond the federal government. Remediation windows are shrinking while enterprise codebases keep expanding.

At codebase scale, critical gaps emerge between the tools security teams rely on, slowing teams down as the pressure to act increases.

See where enterprise security programs break down and what closing the gaps looks like: https://t.co/jxWzyVNJsf

[Sourcegraph @Sourcegraph]

For the fifth consecutive year we're on the Inc. 5000's list of fastest growing companies!

"We’re honored to be recognized on the Inc. 5000 again,” said @DanielNealAdler, CEO of Sourcegraph.

https://t.co/rDyatpsAPR

[Sourcegraph @Sourcegraph]

We traced 517,604 commits across 120 established open source repositories to see how quickly agents are being adopted, where their code lands, and whether it sticks. https://t.co/8DptUTXStX

[Sourcegraph @Sourcegraph]

A vulnerability discovered in one repository may exist across hundreds more.

Prevention, detection, and response share a hidden dependency. When visibility breaks at repository boundaries, all three weaken together.

AI-generated code and dependency sprawl are making those gaps harder to see and the consequences harder to contain.

See what connects the three and why repository-level security leaves critical gaps across the codebase: https://t.co/35rckXR5kb

[Sourcegraph @Sourcegraph]

@tsenart You got a DM :)

[Erik Seliger @erikseliger]

When shipping code is getting easier than ever.. it's also harder than ever to build the right stuff. Join my team @Sourcegraph as *the* Product Manager!
https://t.co/RDzJZDspPH

[Sourcegraph @Sourcegraph]

From the Changelog

Introducing Code Finder Beta and Compare Page GA

https://t.co/a8UzDEGoa0

[Sourcegraph @Sourcegraph]

Not all AI coding tools approach codebase context the same way. Some rely on prompts. Others use indexing, repositories, MCP servers, or long-context approaches. Our comparison breaks down five approaches to codebase context and the tradeoffs behind each so you can determine which is best suited for your team's needs.

https://t.co/uxy0xNuM5j

[Dan Adler @DanielNealAdler]

Absolutely love this conversation between industry legend and co-creator of .NET, Peter Smulovics (@MountGellert) from Morgan Stanley, and @erikseliger and @bobheadxi on @Sourcegraph's new Agentic Batch Changes tech for large-scale migrations! Thank you @FINOSFoundation for hosting us.

https://t.co/DTOpRkOYOH

[Sourcegraph @Sourcegraph]

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: https://t.co/dPwi90zcXa

[Sourcegraph @Sourcegraph]

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.

[Sourcegraph @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 experimentation to production adoption.

Get the guide: https://t.co/5FVoaIcQnN

[Sourcegraph @Sourcegraph]

4/
That's the workflow we broke down in this webinar.
See how it works: https://t.co/dQqqFxD8xw

[Sourcegraph @Sourcegraph]

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]

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]

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 codebase.

"I was able to fix it with one prompt on both the Help Center frontend and backend, then extended this to all repos in Mercari. I found around 80 potential repos affected."

The thing that made this work wasn't speed. It was the agent's ability to reason about each repository individually. Mercari's repos have similar setups, but not the same setup. A scripted find-and-replace would have collapsed. The agent handled the variation per repo, reacted to CI, and pushed follow-up commits where needed.

Canva has been in the preview too, using it to split Batch Changes by code ownership across a Bazel monorepo.

This is a public beta. There are rough edges and we're honest about that. But the core capability is working in real customer environments and we're ready to put it in more hands.

Available today for Sourcegraph Cloud customers. Free during the beta period. Self-hosted arrives July 8 with Sourcegraph 7.5.

Full announcement: https://t.co/Gn3VrVZPel