Atlassian’s Rovo AI is now generally available

Atlassian first showed off Rovo six months ago. Rovo is what the company calls its “AI teammate” that combines smarter search and chat-based AI tools with agents that can help users automate some of their workflows in tools like Jira and Confluence. At its Team ’24 Europe event in Barcelona, the company has now announced the general availability of Rovo. In addition, Atlassian also announced a number of additional new AI features that, like Rovo, are part of the company’s Atlassian Intelligence platform.

At the core of Rovo is Rovo Search, which combines data from core Atlassian tools like Jira and Confluence, but also allows businesses to connect a wide variety of third-party SaaS tools. Jamil Valliani, Atlassian’s head of product for Atlassian Intelligence, told me that Search will support about 80 connectors in the next months. For now, it supports bringing in data from services like Slack, Figma, Google Drive, and GitHub, but the plan is to support all of the major SaaS apps that Atlassian’s customers use.

From there, they can then search this data, but also use Rovo Chat to ask questions about it. Now with the new Rovo browser extension, people can use this chat experience on any site on the web.

As for Rovo Search, Valliani also noted that the company now takes social signals into account when ranking search results, based on data from its team graph, which allows it to know who you typically collaborate with.

Beyond these core features, what got people most excited when Atlassian first demoed Rovo, was Rovo Agents. This is where the intelligent assistance concept fully takes form in the Atlassian ecosystem. The promise here is that these agents can handle some of the routine and repetitive tasks for employees and free them up to do more important work. There are about 20 agents available right now, ranging from a tool that can draft release notes, a bug report assistant, an OKR generator, a translator, and a trivia host (because why not?).

The real power here, though, is that employees can build their own agents, Valliani said. “We really want to inspire people across the business on what is possible,” he said.

Over time, Atlassian plans to bring more agents and agent capabilities into its Marketplace, where it is already partnering with Appfire, Usertesting, Onward, and Zapier to highlight some of these capabilities.

Not everybody inside a company uses Atlassian products, though, which could potentially limit the reach of a product like Rovo and Rovo Search — and make it a harder sell for Atlassian as a number of other companies are also vying to offer similarly comprehensive AI-powered services. But as the company announced Wednesday, it is making Rovo available to non-Atlassian users at no additional cost.

Atlassian Intelligence for developers

Rovo is maybe the most visible part of Atlassian Intelligence right now, but as part of this release, the company is also launching a number of additional features, largely for developers and project managers, that will help them with time-consuming tasks that don’t directly involve programming.

Now, a new AI Agent will be able to generate code plans, code recommendations, and pull requests in Jira based on a task description that the developer writes, together with requirements and additional context from within the organization.

“When a developer wakes up in the morning, half the time they are working on issues that are like ‘this thing crashed,’ or ‘I have to go change this config.’ All these different things that are in the way of actually building the next feature or doing other, more complex, work,” Valliani said. With Jira and Confluence, Atlassian has a lot of context from inside the developer’s company to look for issues and help developers fix and — ideally — avoid them.

“We have this AutoDev agent look for issues it could help with, and when it thinks it could help, it just presents itself and says, ‘Hey, AutoDev here. I can handle this for you.’”

The agent, of course, won’t act autonomously but will always keep the human in the loop and show exactly what it plans to do.

Another new tool will speed up pull request reviews — no matter the code management tool — by automatically analyzing the code and offering recommendations for areas of improvement.