During its Team ’24 conference in Las Vegas, Atlassian today launched Rovo, its recent 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 into Atlassian’s products. Probably the most interesting part, though, could be the recent Rovo Agents, which will be used to automate workflows in tools like Jira and Confluence. One nifty aspect of those agents: Anyone can construct them using a natural language interface. No programming required.
“We like to think about Rovo as a big knowledge model for organizations. It’s a knowledge discovery product for each knowledge employee,” Sherif Mansour, Atlassian’s head of product for Atlassian Intelligence, told TechCrunch. “If you take a look at what a knowledge employee has to do, they form of undergo this strategy of: I would like to seek out a bit of labor. I would like to learn and understand it. After which I take an motion. Most folks that have some form of desk job undergo that loop. I feel what’s exciting about Rovo is that we’re finally on the genesis of generative AI landing that that helps speed up what we are able to do in that area for teams.”
Atlassian Team `24 Las Vegas. Image Credits: Atlassian
The premise for Rovo is Atlassian’s “cloud teamwork graph,” the identical graph that forms the inspiration of Atlassian Intelligence, the corporate’s year-old effort of bringing an AI teammate to its products. That graph brings together data from Atlassian’s own products and a lot of third-party SaaS tools. And in a way, it’s the proliferation of SaaS tools that necessitates applications like Rovo, because every tool tends to have its own data silo, making it harder for workers to seek out the data they need.
Image Credits: 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 a way, enterprise search is the low-hanging fruit here, since Atlassian is already aggregating all of this data. However it’s also a tool that ought to prove immediately useful for its users and keep them from having to continuously switch contexts to seek out information. A few of the third-party tools which are supported out of the box include Google Drive, Microsoft SharePoint, Microsoft Teams, GitHub, Slack and Figma.
Enterprises, which frequently have a number of custom tools, also can construct their very own connectors. Atlassian itself, for instance, built a connector that brings in its internal developer documentation. Simply making that documentation available in Rovo, Mansour said, saved developers an hour or two every week — the next time savings than what those self same developers report from using an AI code-generation tool.
As Mansour stressed, the most important technical challenge — except for constructing the AI infrastructure to power Rovo — is constructing all of those connectors and ensuring that they respect the access permission set by an organization’s IT and security teams. “If you search, you get a special set of results to my search. We make certain that it’s tailored to you and respects your permissions — and only [shows] what you will have access to.”
Image Credits: Atlassian
It wouldn’t be 2024 if Rovo didn’t also come as a chat service. Because it also has access to all of this data, it’s a comparatively easy task to make use of retrieval-augmented generation (RAG) to feed a big language model with it and have the model provide customized answers.
Even when using RAG, large language models are still liable to hallucinations (though RAG greatly reduces the probabilities of the model going off script). To make sure that users can trust the outcomes, Rovo all the time cites its sources, and more often than not (with slideshows and Figma designs, for instance), there’s even an interactive preview.
One interesting feature Atlassian also built into Rovo is its ability to detect and explain company jargon. There may be even a Chrome extension for this that may robotically underline and explain a certain company-specific term as you read a Google Doc, for instance. This feature is powered by Rovo’s semantic search engine.
Virtual teammates
It’s one thing to seek out information. It’s one other to take motion on it. That’s where Rovo Agents are available in. In a way, that is an extension of what the corporate did with Atlassian Intelligence. Indeed, the corporate describes Rovo Agents as “virtual teammates,” too.
“Rovo Agents will transform teamwork with their ability to synthesize large volumes of enterprise data, break down complex tasks, learn as they take motion, and partner with their human teammates to make critical and sophisticated decisions,” Mansour writes in today’s announcement. “Agents aren’t just a few souped-up version of chatbots. They convey specialized knowledge and skills to a wide range of workflows and processes.”
Image Credits: Atlassian
Meaning they will generate, review and edit content for marketing use, product specs or Jira issues. Users also can construct agents that answer specific questions or recommend best practices. But more importantly, they will automate tasks based on when a Jira issue progresses, for instance, or help users clean up their Jira backlogs or organize Confluence pages — all with humans within the loop.
“We’ve a powerful belief that the longer term of teamwork is teammates working alongside virtual teammates — agents,” Mansour said. “There’ll be a lot of them and also you’ll be interacting with them in your day-to-day workflows.”
