Atlassian today unveiled a slew of AI-driven updates at its annual Group event, marking a major shift toward an AI-native ecosystem. Key to this announcement is the expansion of the Teamwork Graph and the introduction of Rovo, Atlassian’s flagship AI agent, designed to leverage the organizational context to deliver unprecedented productivity benefits.
The Team Performance Graph: An Integrated Source of Truth
The foundation of Atlassian’s AI strategy is the Teamwork Graph, a context layer that maps more than 150 billion objects and relationships to organizational projects, goals, and teams.
Unlike traditional AI tools that rely on superficial searches and context windows that “do” with irrelevant data, the Teamwork Graph allows AI to dissect deep relationships. Atlassian reports that this method makes the AI answer 44% more accurate while using 48% fewer tokens.
To empower developers, Atlassian is releasing the Teamwork Graph CLI and MCP tools. This allows customers to connect their organizational memory to external AI builder tools like Cursor or Claude, ensuring that custom-built applications benefit from the same rich context available within Jira and Confluence.
“We already have more than 150 billion objects and relationships mapped on the Teamwork Graph, and billions of those are changing every month,” Jamil Valliani, head of the AI product team at Atlassian, told SD Times. “That’s a rich source of truth for us and our Rovo and other applications to use to bring the best quality results and capabilities and tools to our customers.”
Rovo Max: Pushing the Limits of AI Agency
The spotlight also fell on Rovo, Atlassian’s AI-powered search data tool for the organization, which saw a 50% increase in usage quarter over quarter, the company said.
Atlassian today introduced Rovo Max, a new mode for solving complex problems. When activated, Rovo Max spins up a virtual machine in the cloud to run tasks, write code for analysis, and test itself. At one show, Rovo Max produced a professional-quality audio podcast summarizing multiple pages of Confluence—a skill that wasn’t explicitly taught, but learned quickly by researching best practices.
Bridging the Gap Between Search and Action
Beyond agents, Atlassian is revolutionizing business search. The new connectors now connect Rovo to more than 50 third-party applications, including SharePoint, Slack, and Salesforce. This integration allows Jira users to reference Google Drive documents or Salesforce records directly within their workflows. “We can provide high-quality search across all those different applications,” Valliani said.
In Jira, agents become first-class citizens. Users can now assign problems to AI agents as easily as to humans. These agents can capture projects in Jira, review progress, and discuss feedback with team members. Early data shows a 7x increase in agent-led automation, with companies like Mercedes-Benz already using these tools to improve the quality of the bug report.
Valliani said that working on search is important so that customers can easily find documents that are important to them. “We make sure we get the right pieces of information to the customer, both in graph and search, to power the scenarios that matter most to them and make the best use of the data.” He said that data doesn’t just come from Atlassian objects but includes data from across the organization. “We are able to deliver better information and speed up the workflow by having that capability,” he said.
Studio Updates
Agent Build Studio has received significant investment to improve its capabilities beyond simple agent creation, now supporting automation and development of new applications. The goal is to make AI architecture more accessible, even to users without sophisticated technical knowledge.
Valliani said, “Users can now use natural language commands, like, ‘I need to automate X, Y, Z, so that every day at 9am X, Y and Z happen.'” Studio automates the system, including the necessary agents and automation, for updating. It has improved testing capabilities, allowing users to interact with and test the newly created agent from the panel. If there is a problem, users can simply describe the problem, and Studio will fix it, rather than requiring the user to review the basic information.
The Future of SDLC and Developer Happiness
For software teams, Code Intelligence now provides semantic understanding of large chunks of code. Rovo can run through more than 20 years of code in minutes to identify style inconsistencies or security vulnerabilities. Looking ahead, Atlassian teased “Rovo Dev,” which will soon be able to independently submit Pull Requests (PRs).
Reflecting on the joy of development, Atlassian emphasized that these tools are not intended to remove creativity but to remove the “boring machinery” of status reports and compliance. By outsourcing the nitty-gritty to AI, developers are free to focus on solving complex problems and building products that Valliani said “make the customer smile.”
