Now generally available, Agentic Batch Changes plans, executes, and tracks code changes across hundreds or thousands of repositories. Pricing is based on changesets merged.

SAN FRANCISCO: #agenticbatchchanges--Sourcegraph, the code intelligence platform that helps enterprise engineering teams understand, oversee, and evolve their codebases, announced the general availability of Agentic Batch Changes for Sourcegraph Cloud customers. Agentic Batch Changes is the frontier agent for code change at scale, built on the indexing and change-management infrastructure Sourcegraph has run for the world's largest codebases for years. One prompt plans, executes, and tracks a change across hundreds or thousands of repositories.

“Every engineering leader I talk to has a list of changes that need to happen everywhere. Those are the projects that never get staffed,” said Dan Adler, CEO of Sourcegraph. “Batch Changes already merges half a million changesets a year for the largest enterprises in the world. Agentic Batch Changes now plans that work itself and adapts to each repository, and it has already merged nearly a thousand changesets for early adopters during our beta. You describe the change once and it keeps working until the pull requests are ready to merge, with the speed and confidence of changing a single repository.”

The problem with keeping an entire codebase up to date

Every engineering team eventually faces the same challenge: a change that needs to happen everywhere. A dependency needs upgrading. An API changes, and every caller needs updating. A security vulnerability drops, and the fix needs to reach every exposed repository before the next audit window.

Sourcegraph has been helping the owners of the largest codebases in the world make these changes for years with Batch Changes, which creates pull requests across all affected repositories and tracks their progress until they are all merged.

The AI era has brought a tidal wave of code, and updating all of that code is more difficult than ever. Enterprise codebases have outgrown what any one engineer can hold in their head, and coding agents are adding code faster than teams can read it. The bigger the codebase-wide change, the less anyone can vouch for it. A single migration turns into hundreds of pull requests, and it's nearly impossible to have the confidence to say that the work is done. So teams defer the work. Nobody volunteers to upgrade a framework across 10,000 repositories and disappear for three months. The backlog grows until something like a vulnerability forces the issue, and then patching one service doesn't help if the fix has to reach all of them.

An agent for code change at scale

With Agentic Batch Changes, an engineer describes the change once, in plain language. A coordination agent uses Sourcegraph code intelligence to scope the work across the customer's indexed codebase, builds a plan, and validates its approach in a single repository before generating the full set of diffs. It then pushes changes out in batches. It handles the variation between repositories, reacts when CI fails, and keeps working until the pull requests are ready for an engineer to review and merge. It tracks merge status for every pull request in one place.

Anything a single coding agent can do in one repository, Agentic Batch Changes can orchestrate across all of a customer's repositories at the same time.

Introducing outcome-based pricing

With general availability, Agentic Batch Changes introduces outcome-based pricing. The coordination agent, the part that plans and directs the work, is priced on the number of changesets merged into the customer's codebase. If it opens a pull request and the team decides not to merge it, the customer does not pay for that pull request. Sourcegraph's outcome-based pricing model is the result of a growing demand from engineering leaders industry-wide looking for more clarity in the costs they are charged for AI use. Outcome-based pricing for Agentic Batch Changes allows for pricing tied to impact, instead of traditional consumption-only pricing models.

From the Beta

During the Beta, customers merged nearly a thousand changesets created by Agentic Batch Changes on work that ranged from security remediation to library migrations.

Mercari, a Japan-based marketplace, turned to Agentic Batch Changes for a security fix across many repositories. Patrick Klitzke, Team Lead at Mercari, used it to identify a GitHub Actions environment-variable injection vulnerability across Mercari's codebase and began patching it across the affected repositories.

“I looked at a GitHub injection issue where you have to set environment variables correctly. 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,” Klitzke said. “With the help of Agentic Batch Changes, you're able to handle repos that have similar, but not identical setups. A normal scripted change would most likely be a text search and replace operation without any context of how it's actually used.”

At Canva, the work was a library migration. William L., Senior Software Engineer at Canva, used Agentic Batch Changes to carry it across the company's repositories and track every pull request through to merge from one place.

“We used Agentic Batch Changes to raise and merge 50+ pull requests across our repos as part of a library migration. The web UI made it easy to track each PR and its status. Without it, we would have been managing either huge PRs or spreadsheets; instead, Agentic Batch Changes made the process easier for both reviewers and me,” said William L.

What Agentic Batch Changes can do for you

Agentic Batch Changes is built for the changes that have been hardest to roll out reliably across a large codebase, including:

• Dependency upgrades with breaking changes. Major-version bumps where the API surface shifts and each service handles it differently.
• Security remediation. Scope the change across the indexed codebase to find the affected repositories, understand what the fix looks like in each context, and patch at scale.
• Code pattern updates that need judgment. Refactors where regex is not enough, like deprecated API replacement or internal style migrations.
• New APIs and libraries. Rolling out a new internal API or shared library that every service has to adopt, where each one implemented the old version a little differently.
• CI pipeline modernization. Build-system changes, test infrastructure, and pipeline standardization across a fleet.
• End-of-life deadlines. A language version, framework, library, or runtime goes EOL, the date is external, and the fleet has to move before it hits.

These are starting points, not a fixed list. Customers describe the change they need rather than picking from a set of supported ones, and they keep finding uses Sourcegraph did not plan for. The Sourcegraph engineering team is eager to hear about these use cases.

How the agent chooses its approach

Users start by planning a change with the coordination agent, which drives an Agentic Batch Change. For each part of a plan, the coordination agent decides whether the change needs a coding agent or, more often, a script. That routing is deliberate: it avoids paying for a coding agent to work out the same change a hundred times over. Where a change needs judgment, the agent delegates to Claude Code or Codex, with repository-specific instructions and codebase context through the Sourcegraph MCP. When CI fails, the agent adjusts its approach and tries again. Engineers see diffs as they are generated. They review and approve every changeset before it merges.

Availability and code hosts

Agentic Batch Changes is generally available as of September 14, 2026. It supports GitHub, GitLab, Bitbucket Server, Bitbucket Cloud, Azure DevOps, and Gerrit.

Learn more at sourcegraph.com/agentic-batch-changes or request a demo.

About Sourcegraph

Sourcegraph is the code intelligence platform for large, complex codebases. As the context layer for an organization's entire codebase, Sourcegraph helps engineering teams understand and navigate increasing codebase complexity and fragmentation while reducing technical debt and security risks. It gives agents and developers the context they need to make faster decisions, improve the quality and accuracy of AI-generated code, and execute codebase-wide changes with confidence. Learn more at sourcegraph.com.

Fonte: Business Wire