Atlassian first confirmed off Rovo six months in the past. Rovo is what the corporate calls its “AI teammate” that mixes smarter search and chat-based AI instruments with brokers that may assist customers automate a few of their workflows in instruments like Jira and Confluence. At its Staff ’24 Europe occasion in Barcelona, the corporate has now introduced the final availability of Rovo. As well as, Atlassian additionally introduced a variety of further new AI options that, like Rovo, are a part of the corporate’s Atlassian Intelligence platform.
On the core of Rovo is Rovo Search, which mixes knowledge from core Atlassian instruments like Jira and Confluence, but additionally permits companies to attach all kinds of third-party SaaS instruments. Jamil Valliani, Atlassian’s head of product for Atlassian Intelligence, advised me that Search will assist about 80 connectors within the subsequent months. For now, it helps bringing in knowledge from companies like Slack, Figma, Google Drive, and GitHub, however the plan is to assist all the main SaaS apps that Atlassian’s clients use.
From there, they’ll then search this knowledge, but additionally use Rovo Chat to ask questions on it. Now with the brand new Rovo browser extension, individuals can use this chat expertise on any web site on the internet.
As for Rovo Search, Valliani additionally famous that the corporate now takes social indicators under consideration when rating search outcomes, primarily based on knowledge from its group graph, which permits it to know who you sometimes collaborate with.
Past these core options, what bought individuals most excited when Atlassian first demoed Rovo, was Rovo Brokers. That is the place the clever help idea totally takes kind within the Atlassian ecosystem. The promise right here is that these brokers can deal with a number of the routine and repetitive duties for workers and free them as much as do extra vital work. There are about 20 brokers obtainable proper now, starting from a software that may draft launch notes, a bug report assistant, an OKR generator, a translator, and a trivia host (as a result of why not?).
The actual energy right here, although, is that staff can construct their very own brokers, Valliani mentioned. “We really want to inspire people across the business on what is possible,” he mentioned.
Over time, Atlassian plans to deliver extra brokers and agent capabilities into its Market, the place it’s already partnering with Appfire, Usertesting, Onward, and Zapier to focus on a few of these capabilities.
Not everyone inside an organization makes use of Atlassian merchandise, although, which may doubtlessly restrict the attain of a product like Rovo and Rovo Search — and make it a more durable promote for Atlassian as a variety of different firms are additionally vying to supply equally complete AI-powered companies. However as the corporate introduced Wednesday, it’s making Rovo obtainable to non-Atlassian customers at no further price.
Atlassian Intelligence for builders
Rovo is perhaps essentially the most seen a part of Atlassian Intelligence proper now, however as a part of this launch, the corporate can also be launching a variety of further options, largely for builders and venture managers, that can assist them with time-consuming duties that don’t instantly contain programming.
Now, a brand new AI Agent will have the ability to generate code plans, code suggestions, and pull requests in Jira primarily based on a process description that the developer writes, along with necessities and extra context from throughout the group.
“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 mentioned. With Jira and Confluence, Atlassian has plenty of context from contained in the developer’s firm to search for points and assist builders repair and — ideally — keep away from 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, after all, received’t act autonomously however will at all times preserve the human within the loop and present precisely what it plans to do.
One other new software will velocity up pull request critiques — regardless of the code administration software — by routinely analyzing the code and providing suggestions for areas of enchancment.
