Atlassian Corp. today announced Agentic Multiplayer Protocol, a platform update designed to change how humans and artificial intelligence agents collaborate and get work done using shared context and tasks within the same digital space.
At the unveiling at Team ‘26 Europe, Atlassian said it wants AI agents to function like employees and bring what it calls “multiplayer” into a fully governed system of work so humans and agents can operate side by side in the open.
AMP is designed to give every agent the data context they need to be useful and limitations to stay safe within the confines of the platform – this includes an identity assigned by administration, including authority and scope.
“This is a multiplayer game,” Head of AI Product Jamil Valliani told SiliconANGLE in an interview. “Humans and agents are working together in a very dynamic space, and there are lots of players.”
However, agents cannot run rampant. Valliani added that Atlassian has an internal statement: “Headless software means brainless software.” The company’s role isn’t merely to provide software for autonomous agents to connect to and operate without people; autonomy is useful, but it isn’t useful without teamwork.
Rovo, the company’s AI assistant that became an autonomous powerhouse, can disappear for hours doing work, but the user sets and guides the objective, reviews the proposed plan, course-corrects it and ultimately reviews the result.
To tackle this, Atlassian announced Rovo Work, a new mode for Rovo Chat that handles complex, multi-step tasks that humans review and approve. It is designed for long-horizon tasks.
“When you opt to send a query to Rovo Work, you’re actually giving Rovo permission to go and actually unleash itself fully,” Valliani said.
In fact, Rovo can go a step further than straightforward work completion. For example, when Work is asked to approach a task it is unfamiliar with, and it doesn’t have what it needs in its model training data, it will attempt to train itself.
In one case, a product manager asked Work for an Instagram-ready reel. Instead of using whatever it had associated with its base model, Rovo researched the right instructions, learned what it needed for the output format, and got tooling for video synthesis.
This is materially different from the standard AI model approach of “is this already available in my training?” to “how do I learn to do this?”
Valliani also confirmed that for power users, Rovo could generate custom skills as part of its work. Although this is a separately supported capability, rather than every learned behavior becoming a skill users can export.
“We can’t really imagine the creativity our customers are going to ask it to unleash,” Valliani said. “We want customers to go and challenge it, and tell it what they really want.”
Loom: Replacing prompt engineering with “show me what you mean”
Atlassian is also bringing something to everyday users that developers have been using with agents in coding for a long time: showing instead of telling.
Loom is a product Atlassian produces that allows users to record video of themselves and their computer screen and share with one another to provide instruction. It can also be used to instruct agents. For example, Loom can be used to draw circles around parts of the user interface, show buttons being clicked and information being entered into fields.
The problem with AI agents isn’t always intelligence. Sometimes humans have trouble explaining in words what they want, but if they can visually point out what they need along with words: “Make this larger, move this, turn it green.” That makes the entire process trivial. Two humans looking at the same screen while speaking to one another have the same context and they have a visual “prompt” plus the words.
“With Loom, it’ll actually capture you saying all that, and the actual references on screen that you’re pointing to when you say it, and then format it into the prompt,” Valliani said.
Atlassian broadens the envelope around code and context for developers
For developers, Atlassian’s broader platform changes amount to an expanded context and operating environment for AI agents.
Unveiled today, Rovo Code Search brings the source itself into the Teamwork Graph, a centralized data intelligence and context engine that maps relationships among people, code and documents. Data Context extends that view into structured information stored in platforms such as Databricks Inc., Snowflake Inc. and Google LLC’s BigQuery. Together, they give agents a wider picture of not only how software is built, but the business information surrounding why it is being built.
The company’s expanded Model Context Protocol server also gives external coding and AI agents a common interface into its platform. Valliani said a substantial portion of those interactions now involve agents writing information back, not just retrieving it. MCP turns Atlassian from a data source into part of the shared workspace where agents leave work for humans and other agents to pick up.
Atlassian’s MCP server now exposes 200 tools and handles roughly 15 million tool calls daily.
This calls back to the company’s desire to make agents part of the team and the “multiplayer” wording, giving agents a place in the company, roles and permissions.
Imagine an AI agent working in Confluence, the company’s knowledge management and document collaboration digital workspace similar to an internal centralized wiki, and it sees another agent or human editing the same document. Because all pages are live and structured, it would know it’s collaborating with another teammate in real time, check for any edits and adjust its approach.