Agentic Batch Changes is available today. Describe a change once. It runs across 10 or 10,000 repositories, adapts where they differ, and reacts when CI fails. Agentic Batch Changes uses outcome-based pricing. You pay per changeset merged into your codebase. If a pull request doesn't merge, you don't pay for it. Read more here: sourcegraph.com/blog/introdu…

Code Finder is now generally available. sourcegraph.com/changelog/co…

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. businesswire.com/news/home/2…

From the Changelog Introducing Code Finder Beta and Compare Page GA piped.video/watch?v=VR74iU4m…

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. sourcegraph.com/resources/co…

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.

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: sourcegraph.com/resources/eb…

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

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: sourcegraph.com/agentic-batc…

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 after hours. Learn more and schedule time with the team: sourcegraph.com/events/ai-en…

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

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 piped.video/watch?v=yJU01Y_L…

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

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

Hope you’re enjoying Microsoft Build! If you use GitHub Copilot, you can connect it to the Sourcegraph MCP server to get context from all your repositories. This works even for your code on GitLab.

Keep track of Deep Search conversations shared with you. We didn't stop there, check out the changelog: sourcegraph.com/changelog/20…

Use Case of the Week: Understand unfamiliar code faster piped.video/watch?v=t7_Xgw_x…

You can now use search contexts in Deep Search to ask questions within a set of repositories.

Deep Search can now search Git tags, ancestry, and commits on any branch to pinpoint where a change lives in your Git history.

We just launched Smart Hover Summaries in beta. It reads your code to give you quick access to show key architectural details on hover.

Code coverage numbers do not mean much if parts of your pipeline are being skipped.

2/4) Export Deep Search conversations as PDFs

What's new in Sourcegraph, and no, we're not fooling around. 1/4) Query assist: search code in natural language

We're now live in the @GeminiApp CLI extensions marketplace, making integration easier than ever! Link in thread

Join us to learn how Sourcegraph enables agentic coding tools to work across large, complex codebases This webinar will feature expert advice and real-world examples of companies who've unlocked the next level of engineering efficiency streamyard.com/watch/RcBxPF2…

Sidebar action Interact with Deep Search while browsing code.

Sourcegraph Deep Search just got a major upgrade: • Lower latency + smarter reasoning • Star important threads for easy access • Export conversations as Markdown • Tab navigation in @-mentions • Enhanced context handling (1/2)

You can now ask Deep Search questions directly from code navigation. The code you select in the blob view is automatically added to your conversation as context. DM us if you want to try it out.

:)

New in Sourcegraph 6.12: @GitLab OAuth support for Batch Changes! Replace static API keys and streamline your workflow with stronger authentication.

Did you know you can ask questions about your codebase without leaving Slack? Just @-mention Sourcegraph in any thread and get answers with Deep Search, follow-ups included. Learn more about what's new in 6.12 below!

New year, new changelog.

Combining @cursor_ai and Sourcegraph's MCP Server allows you to run complex, multi-step queries, generate diagrams, and find security fixes (all from your editor.) Full video: piped.video/watch?v=71mHvFVW…

Stop guessing how a codebase works. With Sourcegraph Code Search, you can jump from repo discovery to exact symbols to full change history in seconds.

Large codebases = larger attack surface Traditional tools like grep can miss critical vulnerabilities, such as React2Shell, hidden in complex code. See the full video below

True story piped.video/u8GkvQAnM_o?si=05Ja…

The Sourcegraph for @Raycast extension by @bobheadxi now supports Deep Search!

Full video: piped.video/watch?v=IiuHpy1x…

This is React2Shell monitoring with Code Insights across 512 repos, totaling 17GB and 42M lines of public code. @trly_dev shows how it's done.

"Why code search at scale is essential when you grow beyond one repository" by @heyneighbor sourcegraph.com/blog/why-cod…

We have been busy: Deep Search Optimizations, UX Improvements, and Markdown Export Now available in v6.11 sourcegraph.com/changelog/de…

Build Crew Live: Episode 4 with @ColleenMBrady 00:00 - Introductions and "Four Corners of the Western World" 01:48 - What We Changed Our Mind About This Week 04:35 - Reading Physical Books Again 06:20 - Claude vs ChatGPT for n8n Workflows 14:20 - Database Test Data Generation with psql 18:45 - Divorce App Dev Database Scenarios 20:20 - Mock Data Files for Design Iteration 22:00 - Using Git Diffs for Context Loading 25:02 - Document AI vs LLMs for PDF Processing 32:00 - Colleen's Background and Build Crew Journey 35:50 - npm Scripts for Documentation Updates 36:50 - Custom Slash Commands vs Tools Explained 42:30 - Live Demo: Custom Slash Commands and Toolboxes 57:10 - Closing and Build Crew Community Invite

The founder journey with Sourcegraph CTO Beyang Liu and ex-CEO of Focal Systems Francois Chaubard at Stanford's Hazy Research Lab. They talk about coding agents, whether scale is all you need for AGI, and how industry and academia will advance from here: piped.video/watch?v=hR6zyA-E…

Check out @WorkOS's Secure AI Agents & MCP lead @TobinSouth's talk, "Let's make MCP not suck" at AI Dev Tools Night SF, August 5th. Join the waitlist (link in thread)

Check out @Netlify's CEO @biilmann's talk, "AX in Practice: Live-Coding Agent-Ready Workflows" at AI Dev Tools Night SF, August 5th. Join the waitlist (link in thread)

Check out @thorstenball's talk, "Subagents & the Multiplication of Context Windows," at AI Dev Tools Night SF, August 5th. Join the waitlist (link in thread)

Excited to announce our upcoming AI Dev Tool Night in San Francisco! With featured speakers: - @biilmann - Founder & CEO, Netlify - @thorstenball - Software Engineer, Sourcegraph - @hahnbeelee - Co-founder, Mintlify (YC W22) - @grinich - Founder & CEO, WorkOS - Annie Wang - Software Engineer, Google - (MC) @charu1603, Cofounder, Tacos AI - (Host) @ykdojo, Developer Experience Manager, Sourcegraph It'll be at this awesome venue, thanks to our friends at @mintlify lu.ma/ai-dev-tools-night-sf-…