Blog | Sourcegraph

JUN 30, 2026

Agentic Batch Changes is now in public beta

Agentic Batch Changes is now in public beta: an AI agent that scopes, executes, and ships large-scale code migrations across hundreds of repositories until every PR is mergeable.

JUN 26, 2026

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

AI coding agents are producing more code than ever, but the world still runs on massive, decades-old codebases. Why owning and understanding them may be the hardest job in software.

JUN 24, 2026

Why your migration tools are failing your engineers

The bottleneck in most large-scale migrations is not the engineers or the plan. It is that the tools cannot see the whole codebase.

JUN 16, 2026

Sourcegraph MCP server and a cheaper model beat a Mythos-class model alone

On nine CodeScaleBench tasks designed to evaluate agent effectiveness in large codebases, Claude Sonnet 4.6 with the Sourcegraph MCP server outscored Fable 5, winning six of nine at roughly half the cost for each point of quality.

JUN 16, 2026

The hidden cost of code that nobody touches

Every engineering org has the files nobody wants to open. Here's what that actually costs.

JUN 5, 2026

Automating Security Triage with HackerOne and Deep Search

How Sourcegraph uses HackerOne webhooks and Deep Search to automatically validate, triage, and investigate vulnerability reports before engineers start their day.

MAY 28, 2026

Security Automation Evolved: From SlackOps to Programmatic SIEM Triage (Part 1/2)

How Sourcegraph's security team evolved from a Slack-based triage bot to programmatic SIEM detection with expression-based auto-close rules.

MAY 22, 2026

Dependency prefixes are a supply chain risk: let's fix them

Dependency prefixes like ^ and ~ make updates easy, but the version ranges they create widen the path a compromised package can take into production.

MAY 13, 2026

How we're using Sourcegraph and a Slack bot to detect vulnerabilities and react quickly

A Slack bot triages every GitHub advisory, posts a rocket-to-trigger ask in the channel, and on one human reaction runs the full content pipeline: detection queries, blog scaffold, social drafts, a 35-second auto-cut demo. The operator's remaining job is to read the drafts and decide whether they're honest.

MAY 8, 2026

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

Data from 1,281 agent runs across 40+ large open source repos reveals five repeatable failure patterns in coding agents, and the infrastructure fixes for each.

MAY 4, 2026

Lessons on UX, security, and scale when building an enterprise-grade Slack agent

We built a Deep Search Slack agent for large companies. Here is what we learned about user experience, enterprise security, and Redis-backed rate limiting.

APR 22, 2026

Code Search, Deep Search, or MCP: When to Use Each

AI added new ways to search code, but not all of them apply to every problem. Here’s how to choose between Code Search, Deep Search, and MCP.

APR 21, 2026

What it actually takes to run code intelligence in-house

We audited what it would take to build a Sourcegraph equivalent internally, mapped the platform to 90 engineering requirements across 10 categories, and modeled 3-year costs for different environment sizes.

MAR 26, 2026

Detecting supply chain attacks at scale with Deep Search

Poisoned LiteLLM packages on PyPI started stealing credentials. Using Deep Search and Code Search, we traced which public repos were protected by version pinning and which were left exposed. Here's how—and how you can do the same for any supply chain incident.

MAR 25, 2026

The future of SCIP

We are excited to announce our transition to a community-driven open source project. While making this change, we reaffirm our deep commitment to remaining active members of the community.

MAR 20, 2026

MCP stories from the field

While direct API calls seem cheaper and easier, they lack the safety layer large organizations rely on. Tool connection protocols aren't dead; they remain vital for security, governance, and centralized control in big teams.

MAR 3, 2026

CodeScaleBench: Testing coding agents on large codebases and multi-repo software engineering tasks

The initial findings from CodeScaleBench, a new benchmark designed to evaluate coding agents against the true complexity of enterprise software development, including large codebases and multi-repository tasks.

FEB 25, 2026

A new era for Sourcegraph: The intelligence layer for AI coding agents and developers

Today, we're announcing Sourcegraph 7.0, a release that marks the beginning of a new chapter for our company and product.

FEB 6, 2026

Building DataBot: Our always-on data assistant

The hidden cost of being a data-driven company is context-switching for analysts due to "quick questions." DataBot allows the data team to focus on auditing analysis instead of performing it.

FEB 4, 2026

How our support engineers use Deep Search to investigate customer issues faster

Deep Search empowers our Support Engineers to bypass initial escalations, enabling them to dive directly into investigating the root cause of issues.