Atlassian Announces Code Context, Bringing Codebase Understanding Into the Teamwork Graph

New Atlassian Teamwork Graph capability brings large-scale, multi-repo codebase understanding into the Teamwork Graph so Rovo and coding agents produce better output with fewer tokens

TEAM Anywhere/SAN FRANCISCO--(BUSINESS WIRE)-- Atlassian Corporation (NASDAQ: TEAM), a leading provider of AI-powered collaboration and team productivity software, today announced Code Context, a new capability in the Atlassian Teamwork Graph that gives developers, Rovo, and coding agents secure access to source code across large-scale, multi-repository codebases.

As organizations adopt coding agents, their effectiveness depends on more than model intelligence. It depends on the context they have available to them before taking action. Coding agents can write, refactor, and review code, but quality output requires understanding the system of work around any given task and permission-aware access to the context it holds. The surrounding organizational knowledge is critical, from architectural decisions and product strategy to implementation discussions, prior tradeoffs, and the conversations that explain why systems work the way they do.

The Atlassian Teamwork Graph now includes Code Context, creating a context layer where large-scale codebase understanding and organizational knowledge come together. This gives agents an efficient way to reason across code and work to produce more precise output with fewer tokens.

From code search to codebase understanding

Code Context creates a secure, queryable representation of connected codebases and makes that knowledge available across development workflows, from IDEs and terminals to AI coding apps, Jira, Rovo Chat, and the broader Atlassian ecosystem. Developers and agents can use exact search, natural-language queries, and semantic retrieval to find relevant source code across multiple repositories.

Through the Teamwork Graph CLI, coding agents like Cursor, Claude Code, and Codex can ground their work in the relevant information before planning, generating, or reviewing code. Without Code Context, agents are often constrained to the code available on a developer's machine. They may miss implementation details, dependencies, or usage patterns that live elsewhere, creating risk through changes that do not account for the system as a whole.

Code Context lets agents uniquely combine code with related signals from Jira work items, Confluence pages, Loom videos, and third-party sources from 50+ connectors. In internal benchmarks, agents enriched by the Teamwork Graph delivered 44% more accurate results while using 48% fewer tokens compared to agents operating without that context.

Mark Walz, Chief Technology Officer of SpotOn, said, "When an agent starts in the wrong place, everything slows down and costs more. Developers end up explaining where to look, why the code works the way it does, and what else it touches. Code Context puts all of that in front of the agent from the start, so it can focus on getting the work done."

The AI context engine for software development

Code Context expands Atlassian's vision for the AI-native software development lifecycle, where Jira anchors the work, Confluence holds the knowledge, pull requests capture implementation history, and the Teamwork Graph connects the context around it. Large-scale, complex codebases are now part of that connected system.

The Teamwork Graph is continually cross referencing, interlinking, inferring, indexing, and pre-calculating relationships from billions of objects, building a unified map of how everything relates. This gives agents a path from hypothesis to verification, using relevant context to validate their reasoning before taking action. Instead of manually examining repositories or relying on tribal knowledge, developers can ask Rovo how a system works and get answers grounded in connected source code and organizational context.

For engineering teams adopting coding agents, Code Context helps reduce time spent manually stitching together context. Agents get a more direct path to the information they need before they plan, generate, or review code. Developers remain accountable for understanding changes and deciding what ships.

Sanchan Saxena, senior vice president and head of product for Teamwork Collection, Atlassian, said, "The organizations seeing the most success with AI aren't just spending the most; they're the ones giving it the best context with the right access. Frontier intelligence gives teams speed. Context points that speed in the right, most impactful direction. We're finding that real acceleration in software delivery comes from combining both."

Code Context is designed with security and governance in mind. Once enabled, results are scoped to what each user or authorized agent is permitted to see. The goal is not to give agents unlimited access. It is to give them the right access through a secure, governed system where developers stay in control.

Availability

Code Context is currently rolling out to Atlassian customers through open beta, with support for GitHub and Bitbucket. Organization admins can check whether Code Context is available for them to opt into under Rovo settings in Atlassian Administration. Learn more on the Atlassian blog.

About Atlassian

Atlassian unleashes the potential of every team. A recognized leader in software development, work management, and enterprise service management software, Atlassian enables enterprises to connect their business and technology teams with an AI-powered system of work that unlocks productivity at scale. Atlassian's collaboration software powers over 85% of the Fortune 500 and 350,000+ customers worldwide - including NASA, Rivian, Deutsche Bank, United Airlines, and Bosch - who rely on our solutions to drive work forward.

Any agent. Any model. One team → Discover the AI-native SDLC on jira.dev

Arseny Tseytlin, [email protected]