Atlassian is rolling out new generative AI capabilities that will be integrated into the company's cloud-based workforce management portfolio of products designed to help project and service-based work teams become more efficient. .
The technology, called Atlassian Intelligence, was announced Wednesday and is based on internal AI models acquired through the company's 2022 acquisition of Perceived AI, and a collaboration with Microsoft's OpenAI, the creator of ChatGPT, whose launch last year sparked a virtual AI. arms race between the biggest tech companies, including Google and Meta.
Using large language models, the foundation of generative AI, Atlassian Intelligence creates custom teamwork charts that show the types of work performed and the relationship between them, while the platform's open approach: Atlassian provides context and additional data from third-party application equipment. are using, according to the company.
"It's really about accelerating teamwork across the different types of products that we have," said Sherif Mansour, Atlassian's chief product officer.
“Atlassian intelligence is a set of features that exist across all of our cloud products to address different use cases and scenarios, while leveraging the power of artificial intelligence and great language models,” he said.
Use generative AI to support teams
Atlassian outlined several ways that Atlassian Intelligence can help teams, including speeding up work, getting instant help, and creating a shared understanding of projects. Atlassian Intelligence can also translate natural language queries into the Jira Query Language to find issues across all Jira Cloud products.
To help speed work, Atlassian Intelligence uses OpenAI generative AI technology to create, summarize, and extract insights from content. For example, decisions and action items can be quickly summarized from meeting minutes, and tweets can be redacted based on information contained in Confluence.
While ChatGPT's technology will be used to help Atlassian Intelligence process natural language requests, Shariff notes that the company has an agreement that the software or OpenAI will not store customer data.
The technology can also provide employees and customers with immediate answers and quick resolutions through the new Jira Service Management virtual agent, which can automate Slack and Microsoft Teams support interactions. Atlassian Intelligence also handles repetitive requests on behalf of support teams, allowing them to focus on more important tasks.
Virtual agents to resolve work requests
The virtual agent is designed to instantly resolve help requests based on your understanding of knowledge base articles and can also ask follow-up questions to take action. You can also summarize activity on help requests to update assigned agents and help craft customer responses that can also be tuned for pitch.
In addition, Atlassian Intelligence can highlight related or previously resolved issues and recommend relevant articles and related pages to resolve requests and incidents faster.
Atlassian Intelligence also helps create a shared internal library of knowledge and terms used to describe projects, acronyms, and internal systems. You can provide a shared context with an on-demand dictionary specific to your business, your teams, and your work. You can highlight a term and ask Atlassian Intelligence to explain it with the definition, source of information, internal subject matter experts, and how it connects to related work based on the teamwork graph, Atlassian said.
Natural language instead of SQL queries
Atlassian Intelligence's understanding of questions in natural language also means that users can ask questions and the technology generates insights using data from multiple sources in Atlassian Analytics, a hub for analyzing and visualizing data in Atlassian products and connected third-party tools, without needing to know how to do it. write sql.
Since their public release, large language models like ChatGPT have been criticized for providing incorrect or sometimes even defamatory information in response to user requests, a problem Mansour is sympathetic to, but doesn't believe is a problem. major problem for companies looking to take advantage of technology.
"In business, it's less of a problem because there's a lot less fake news," he said. Referencing Atlassian Intelligence's internal library offering, Mansour acknowledged that while it's technically possible for someone to assign bogus definitions to terms, it's a highly unlikely scenario because there's nothing to be gained by doing so.
Despite this, a key tenet of Atlassian Intelligence is that the user remains in control. Mansour explained that while the technology can help an agent craft a response, that message will only be sent if the user manually presses the Send button.
Additionally, Mansour said that while Atlassian Intelligence largely adheres to the company's existing privacy policy, Atlassian users will also need to opt-in to the technology.
“The user should always be in control,” he said. "Technology should never do anything without the user confirming it first."
Atlassian customers can sign up for the Atlassian Intelligence early access waitlist starting April 19, though it cannot guarantee a specific time for user access.
Copyright © 2023 IDG Communications, Inc.