Atlassian has announced Code Context, a new capability within the Atlassian Teamwork Graph designed to give developers, Rovo, and coding agents secure access to source code across large, multi-repository environments. The capability combines codebase understanding with organizational knowledge, helping AI agents access architectural decisions, product strategies, implementation discussions, and other context needed to produce more precise results. Code Context creates a secure, queryable representation of connected codebases that can be accessed through IDEs, terminals, AI coding applications, Jira, Rovo Chat, and the broader Atlassian ecosystem. Through the Teamwork Graph CLI, coding agents including Cursor, Claude Code, and Codex can use exact search, natural-language queries, and semantic retrieval to identify relevant source code across repositories before planning, generating, or reviewing code.
Also Read: Oracle Launches Agentic HR Applications to Strengthen Workforce Development
The capability also connects code with information from Jira work items, Confluence pages, Loom videos, and more than 50 third-party connectors, helping agents understand dependencies and system-wide relationships beyond the code available locally. Atlassian said internal benchmarks showed agents enriched by the Teamwork Graph delivered 44% more accurate results while using 48% fewer tokens than agents without the additional context. “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,” said Sanchan Saxena, senior vice president and head of product for Teamwork Collection, Atlassian.