Atlassian launches AI agents and visual tools in Confluence to transform documentation workflows

Atlassian Introduces Visual AI Tools to Transform Confluence Pages

Atlassian announced a significant expansion of its AI capabilities on Wednesday, rolling out Remix, a visual AI tool now in open beta that transforms data stored in Confluence into charts, graphics, infographics, and scorecards without requiring users to open another application 1

1

. The tool addresses a persistent friction point in knowledge management: teams document extensively in Confluence, then manually reformat that content for different audiences. Remix allows users to highlight any content on a Confluence page and generate a visual from it, with the output layered on top of the original content and linked to its source 3

3

.

The intelligence guiding Remix's format recommendations comes from the Teamwork Graph, Atlassian's unified data layer built from more than 100 billion data points across Jira, Confluence, and connected enterprise tools 3

3

. Rather than asking users to choose a format manually, Remix uses that graph to surface the visual type most likely to be useful given the content's structure. According to Atlassian, Confluence pages with visual elements are nearly two times as likely to be read by a wider audience compared to pages without 2

2

.

Third-Party Agents Connect Confluence to Specialist Applications

Alongside Remix, Atlassian introduced three new AI agents that run within Confluence using Model Context Protocol, launching April 13 3

3

. One agent connects Confluence users to Lovable to turn product ideas and data into working prototypes. Another agent connects to app builder software Replit and allows users to convert technical documents into starter apps. The third agent works with AI presentation builder Gamma to build slides and other presentation materials 1

1

.

Each agent is invoked directly from a Confluence page through Rovo Chat, Atlassian's AI assistant. When triggered, the agent reads the page's content and metadata, including authorship, project association, and decision context, and carries all of it into the partner tool without requiring manual reconstruction 3

3

. The artifact produced links back to the source page, preserving the chain of reference between documentation and output.

Agentic Capabilities Built on Open Standards

Atlassian's choice to build on Model Context Protocol rather than a proprietary integration layer represents a strategic signal: any partner can build an agent that works with Confluence content without waiting for Atlassian to construct a bespoke connection 3

3

. For administrators, enabling a partner's Model Context Protocol server in Atlassian Administration takes minutes, after which the agent appears in the team's Rovo directory, pre-configured and inheriting the workspace's existing permissions.

The agents have no independent ability to carry out tasks without user permission. "They don't silently deploy apps or make architectural decisions on their own," an Atlassian spokesperson told The Register. "The user initiates. They might say 'turn this into an app' or ask what's possible - and the agent suggests options and scaffolds a starting point" 2

2

. Users must review and confirm outputs before anything is published or deployed.

Strategy to Embed AI into Existing Workflows

The new tools represent Atlassian's push to incorporate AI-powered tools directly into the apps workers are already using, as opposed to launching new software platforms 1

1

. In February, the company added AI agents to its product management software Jira. "With Remix and agents in Confluence, a single page becomes the starting point for whatever comes next: a clear story for leaders, a prototype for builders, or a walkthrough for customers, all from the same source of truth," Sanchan Saxena, senior vice president of teamwork collaboration at Atlassian, wrote in a blog post 1

1

.

This follows a trend across the industry of companies looking to streamline workflows by embedding capabilities directly into existing platforms. While Salesforce launched a separate AI agent management platform, Agentforce, in 2024, it has since released many innovations through existing software like its recent upgrade that turned Slack's chatbot into an AI agent 1

1

. OpenAI is also leaning into this movement through its Frontier Alliances initiative, partnering with consultant firms to task them with embedding OpenAI's tech into clients' existing tech stacks 1

1

.

AI Investment Following Workforce Reduction

The announcement arrives less than a month after Atlassian cut 1,600 jobs, approximately 10 percent of its staff, explicitly to fund AI investment 3

3

. Late last year, the Australia-based company migrated more than 3,000 Jira and Confluence instances to AWS Graviton processors, resulting in roughly 10 percent savings, lower latency, and better customer response times 2

2

. The company's ability to turn Confluence data into software applications, presentations, and prototypes through these partner integrations signals a shift in how enterprise software vendors are approaching data visualization and prototyping workflows.