Atlassian Introduces Rovo, its new AI Helper

Atlassian introduced its latest AI assistant, Rovo, at its Team ’24 conference in Las Vegas. Rovo can gather data from various sources, both first- and third-party tools, and present it smoothly through an AI-driven search feature, along with other integrations across Atlassian’s suite of products. However, what truly stands out are the innovative Rovo Agents, designed to streamline workflows within platforms like Jira and Confluence. Notably, these agents can be crafted by anyone using a user-friendly natural language interface, eliminating the need for programming skills.

Atlassian’s head of product for Atlassian Intelligence, Sherif Mansour, said, “We like to think of Rovo as a large knowledge model for organizations. It’s a knowledge discovery product for every knowledge worker. When you look at what a knowledge worker has to do, they sort of go through this process of: I need to find a piece of work, I need to learn and understand it and then I take action. Most people that have some sort of desk job go through that loop. I think what’s exciting about Rovo is that we’re finally at the genesis of generative AI landing that helps accelerate what we can do in that area for teams.”

Atlassian Team `24 Las Vegas. Image Credits: Atlassian

Rovo is built upon Atlassian’s “cloud teamwork graph,” the backbone of Atlassian Intelligence’s year-old initiative to integrate AI into its products. This graph combines data from Atlassian’s tools and various third-party SaaS platforms. Interestingly, the rise of SaaS tools has made solutions like Rovo essential, as each tool typically keeps its data isolated, complicating the process for employees to access necessary information.

search information

According to Mansour, Rovo is centered on three key aspects of teamwork: aiding teams in discovering and engaging with their tasks, helping those teams learn, and empowering them to take action.

In some way, Enterprise search emerges as the most accessible benefit, given Atlassian’s existing data aggregation efforts. It offers immediate utility to users by preventing the constant need to switch between different contexts for information retrieval. Notably, Rovo seamlessly integrates with various third-party tools like Google Drive, Microsoft SharePoint, Microsoft Teams, GitHub, Slack, and Figma right off the bat.

Moreover, enterprises, often equipped with numerous custom tools, can create their own connectors. For instance, Atlassian developed a connector to incorporate its internal developer documentation, available in Rovo. Mansour highlighted that simply by making this documentation accessible through Rovo ,developers saved an hour or two each week—an efficiency gain surpassing that reported by the same developers using an AI code-generation tool.

As Mansour emphasized, beyond constructing the AI infrastructure that drives Rovo, the primary technical hurdle lies in developing connectors while ensuring they stick to the access permissions set by a company’s IT and security teams. He explained, “When you search, you get a different set of results to my search. We make sure that it’s tailored to you and respects your permissions,  and only shows what you have access to.”

By 2024 standards, it was expected that Rovo would also be available as a chat service. With access to extensive data, leveraging retrieval-augmented generation (RAG) to feed a large language model enables Rovo to deliver personalized responses effortlessly.

Despite the use of RAG, which notably reduces the likelihood of the model drifting away from the intended context, there remains a potential for errors known as hallucinations. To ensure users can trust the responses, Rovo consistently cites its sources. Moreover, for certain types of content like slideshows and Figma designs, interactive previews are often available to further enhance clarity.

Atlassian has also incorporated a fascinating feature into Rovo: the ability to identify and explain company-specific jargon. Accompanying this feature is a Chrome extension that automatically highlights and explains proprietary terms while users browse documents such as Google Docs. This functionality is powered by Rovo’s semantic search engine.

Read More: Atlassian Merges Jira Software and Work Management Tools

Rovo Agents

Finding information is one aspect; taking action is another. Rovo Agents bridge this gap. In essence, they expand upon Atlassian Intelligence’s foundation. The company even labels Rovo Agents as “virtual teammates.”

Mansour writes in an announcement, “Rovo Agents will transform teamwork with their ability to synthesize large volumes of enterprise data, break down complex tasks, learn as they take action, and partner with their human teammates to make critical and complex decisions. Agents aren’t just some souped-up version of chatbots. They bring specialized knowledge and skills to a wide variety of workflows and processes.”

Rovo Agents

This implies that Rovo Agents possess the capability to perform various tasks such as generating, reviewing, and editing content for marketing materials, product specifications, or Jira issues. Users also have the ability to create agents that can address specific inquiries or suggest optimal practices. Moreover, Rovo Agents can automate tasks triggered by events like the progress of a Jira issue, assist users in managing their Jira backlogs, or organizing confluence pages, all while ensuring human oversight.

“We have a strong belief that the future of teamwork is teammates working alongside virtual teammates — agents. There’ll be many of them and you’ll be interacting with them in your day-to-day workflows.” said Mansour.