Atlassian introduces AI visual tools and partner agents to Confluence, a month following the layoff of 1,600 employees.

      In summary: Atlassian is launching Remix, a visual AI tool currently in open beta, which converts Confluence pages into charts, infographics, and scorecards without needing users to switch applications. Additionally, three partner agents based on the Model Context Protocol will integrate Confluence content directly into Lovable, Replit, and Gamma starting April 13. This announcement follows Atlassian's recent decision to reduce its workforce by 1,600 employees to fund AI initiatives.

      Knowledge management software faces a challenge with presentation. Teams spend considerable time documenting decisions, specifications, and meeting outcomes in Confluence, and then need to invest similar effort in manually formatting that content into desired charts, prototypes, and presentations for different audiences. Atlassian is aiming to bridge that gap with two related announcements made on Wednesday: a visual generation tool, Remix, which links outputs to their sources, and a collection of pre-built agents that transfer Confluence content directly to partner applications.

      Remix: self-transforming documentation

      Remix, now available in open beta, enables teams to select any portion of content on a Confluence page—be it a paragraph, table, or entire document—and command the tool to create a visual from it. At launch, it supports output formats such as data visualizations, infographics, scorecards, and charts, with plans to add more formats in the future. The generated visual is overlaid on the original content and connected to the source, allowing it to update as changes occur on the underlying page and eliminating the need for separate export or file management processes.

      The intelligence that informs Remix’s format suggestions is derived from the Teamwork Graph, Atlassian's unified data layer that aggregates over 100 billion data points from Jira, Confluence, and related enterprise tools. Instead of requiring users to manually select a format, Remix utilizes this graph to recommend the most suitable visual type based on the content’s structure and the organization’s usage patterns; for example, a quarterly roadmap page might suggest a scorecard while a dataset could lead to a chart.

      Sanchan Saxena, Atlassian's senior vice president of product for the Teamwork Collection, characterized the tool as an effort to streamline the platform: “With Remix and agents in Confluence, a single page becomes the launching point for whatever follows: a clear narrative for leaders, a prototype for builders, or a guide for customers, all from the same source of truth.”

      Three agents that bridge application boundaries

      While Remix keeps the output within Confluence, the partner agents introduced alongside it are meant to export content from Confluence into specialized tools without manual copying or custom integrations. Three agents will debut on April 13: Lovable, which transforms a product specification into a functional user interface prototype; Replit, which converts a technical document into a starter application that engineers can modify and develop; and Gamma, which turns meeting notes or a status page into a professional presentation.

      Each agent can be triggered directly from a Confluence page via Rovo Chat. Upon activation, the agent reads the content and metadata of the page—such as authorship, project affiliation, and decision context—transferring all this information into the partner tool without requiring the user to manually reconstruct the context. Each artifact created—whether a prototype in Lovable, a codebase in Replit, or a presentation in Gamma—links back to the original page it originated from, maintaining the reference chain between documentation and output.

      For administrators, setup does not require any custom scripting. Simply enabling a partner’s Model Context Protocol server in Atlassian Administration takes only a few minutes, after which the agent becomes available in the team’s Rovo directory, pre-configured by the partner and inheriting the existing workspace permissions and context.

      MCP as the open standard

      The technical foundation for the partner agents is the Model Context Protocol, an open standard that has quickly become the backbone of the agent software ecosystem. Atlassian’s decision to utilize MCP instead of a proprietary integration layer signals a strategic intent: any partner can develop an agent that works with Confluence content without waiting for Atlassian to create a custom connection. The protocol is open and properly documented, meaning the main hurdle to joining the ecosystem is technical expertise, rather than a commercial agreement with Atlassian.

      The three launch partners are intentionally designed for different use cases. Replit represents the developer workflow; Lovable targets product design and prototyping; and Gamma focuses on executive communication. Together, they address the three primary audiences that typically need Confluence documentation reformatted before becoming actionable.

      The AI transition in context

      Atlassian recently laid off 1,600 employees, around 10% of its global workforce, with CEO Mike Cannon-Brookes stating that the resulting savings would be reinvested in AI development and enterprise sales. The company also appointed two executives to replace the chief technology officer role, with Taroon Mandhana taking on the role of CTO for Teamwork, and Vikram