Today, during its Team '24 conference in Las Vegas, Atlassian introduced Rovo, its latest AI assistant. Rovo can take data from first- and third-party tools and make it easily accessible through a brand new AI-powered search tool and other integrations with Atlassian's products. The most interesting part, nevertheless, is perhaps the brand new Rovo Agents, which might be used to automate workflows in tools like Jira and Confluence. A clever aspect of those agents: Anyone can create them using a natural language interface. No programming required.
“We like to consider Rovo as a big knowledge model for organizations. It’s a knowledge discovery product for each knowledge employee,” Sherif Mansour, Atlassian’s product lead for Atlassian Intelligence, told TechCrunch. “If you take a look at what a knowledge employee has to do, they type of undergo this process: I even have to seek out a job. I even have to learn and understand it. And then I take motion. Most individuals who have a desk job undergo this loop. I feel what’s exciting about Rovo is that we’re finally on the genesis of generative AI, which helps us speed up what we will do for teams on this space.”
Atlassian Team `24 Las Vegas
The foundation of Rovo is Atlassian's “Cloud Teamwork Graph,” the identical graph that forms the muse of Atlassian Intelligence, the corporate's years-long try and recruit an AI teammate to its products. This chart combines data from Atlassian's own products and a variety of third-party SaaS tools. And in some ways, it’s the proliferation of SaaS tools that creates the necessity for applications like Rovo, as each tool tends to have its own silo of information, making it harder for workers to seek out the data they need.
Photo credit: Atlassian
Rovo, Mansour said, revolves around three pillars of teamwork: helping teams find and connect with their work, helping those teams learn, after which helping them take motion.
In some ways, enterprise search is the low-hanging fruit here, since Atlassian already aggregates all of this data. But it's also a tool that ought to immediately prove useful to its users, saving them from having to continuously switch context to seek out information. Third-party tools supported out of the box include Google Drive, Microsoft SharePoint, Microsoft Teams, GitHub, Slack, and Figma.
Companies, which regularly have quite a few custom tools, can even create their very own connectors. For example, Atlassian itself has developed a connector that integrates the interior developer documentation. Just making this documentation available in Rovo, Mansour says, has saved developers an hour or two each week – a greater time savings than the identical developers report using an AI code generation tool.
As Mansour identified, the largest technical challenge — apart from constructing the AI ​​infrastructure to run Rovo — is constructing all of those connectors and ensuring that they respect the access permissions set by an organization's IT and security teams. “When you search, you get different results than after I searched. We be certain that it’s tailored to you, respects your permissions – and only (shows) what you could have access to.”
Photo credit: Atlassian
It wouldn't be 2024 if Rovo wasn't also offered as a chat service. Since it also has access to all this data, it’s a comparatively walk in the park to feed it to a big language model using Retrieval-Augmented Generation (RAG) and have the model provide custom answers.
Even when using RAG, large language models are still liable to hallucinations (although RAG significantly reduces the prospect of the model going off script). To ensure users can trust the outcomes, Rovo all the time cites its sources and more often than not (e.g. slideshows and Figma designs) there may be even an interactive preview.
An interesting feature that Atlassian has also integrated into Rovo is the flexibility to acknowledge and explain corporate jargon. There is even a Chrome extension for this that, for instance, routinely underlines and explains a certain company-specific term when reading a Google document. This feature is powered by Rovo's semantic search engine.
Virtual teammates
It's one thing to seek out information. It's one other thing to act against it. This is where Rovo Agents comes into play. In some ways, that is an extension of what the corporate did with Atlassian Intelligence. In fact, the corporate also describes Rovo Agents as “virtual teammates.”
“Rovo agents will transform teamwork with their ability to synthesize large amounts of enterprise data, break down complex tasks, learn as they take motion, and collaborate with their human teammates to make critical and sophisticated decisions,” Mansour writes in today's announcement. “Agents are usually not only a souped-up version of chatbots. They bring expertise and skills to a wide range of workflows and processes.”
Photo credit: Atlassian
This means they’ll create, review and edit content for marketing purposes, product specifications or Jira issues. Users can even create agents to reply specific questions or recommend best practices. But more importantly, you may automate tasks based on the progress of a Jira issue, for instance, or help users clean up their Jira backlogs or organize Confluence pages – all with human involvement.
“We firmly imagine that the long run of teamwork is teammates collaborating with virtual teammates – agents,” Mansour said. “There will likely be lots of them and you may interact with them in your day by day workflow.”
