Highlights:
- Supported by over two decades of public and customer data, Atlassian Corp.’s AI offerings empower individuals as virtual agents and enable large organizations to leverage their extensive information repositories in unprecedented ways.
- Atlassian unveils the introduction of natural language prompts for Jira Query Language, enabling users to delve deeper into Jira issues.
Atlassian Corp. Plc. recently announced the integration of generative artificial intelligence agents and services into its primary collaborative software suite. This enhancement provides customers with conversational access to organizational data and quick insights.
In April, the company unveiled the initial services within Atlassian Intelligence, which were introduced in beta mode and crafted using Atlassian’s proprietary in-house AI models.
It leverages OpenAI’s GPT-4, a prominent large language model that is the foundation for its widely-used ChatGPT chatbot.
The Head of Atlassian Intelligence, Sherif Mansour, stated in an interview, “Many of our products help teams plan and track projects or deliver a service, whether they be technical or non-technical teams. And we think that AI is going to help our customers achieve great things and accelerate their productivity with the different types of teamwork that we serve our customers in.”
Supported by over two decades of public and customer data, the company’s AI offerings empower individuals as virtual agents and enable large organizations to leverage their extensive information repositories in unprecedented ways.
Currently, generative AI is accessible in Jira, the company’s project and issue-tracking software. This capability will empower users to swiftly generate customer responses that are both factual and empathetic directly to the editor. It is now widely accessible in the Confluence team collaboration platform, enabling teams to efficiently familiarize themselves with projects by summarizing documents and posing questions to the AI.
Utilizing organization and domain-wide information, the AI service can assist new users in seamlessly integrating into the culture, ensuring they stay informed about crucial information, including industry-specific jargon terms. Mansour explained that it surpasses an employee handbook wiki or search functionality as a virtual agent can effectively manage questions and answers.
Mansour said, “One great example is your classic company glossary like all these; a lot of our big customers have a ton of content in Jira, Confluence, and Trello, with a lot of internal jargon and acronyms that could be project names or system names. One of the things we’re delivering is a definitions capability where you can highlight any content in Confluence and say, explain what is ‘Project Veritas.’”
Subsequently, the AI will respond to a conversational language akin to engaging with someone well-versed in the subject matter. Users can pose additional questions and delve deeper into the topic if the explanation is insufficient. This presents numerous opportunities to clarify otherwise esoteric company jargon, facilitating quicker onboarding for new employees.
In beta mode, this new capability is integrated into Confluence; however, it will soon extend its reach to pull content from other Atlassian products.
Mansour mentioned that 10% of Atlassian customers have already embraced and implemented the new AI services. For instance, Domino’s Pizza Inc. has effectively utilized it to manage post-incident reports. The robust summarization capabilities enable management to glean high-level takeaways swiftly, saving hours typically spent reading reports and eliminating the need to delve into details for insights. Matthias Hansen, Domino’s Group Chief Technology Officer, has highlighted how it has already proven its worth by improving productivity across their product teams.
Accessing information from extensive enterprise data repositories is equally crucial for companies. Atlassian unveils the introduction of natural language prompts for Jira Query Language, enabling users to delve deeper into Jira issues. This combines the simplicity of basic search with the capability to construct intricate queries using JQL, facilitating the swift discovery of tracked issues in the system.
Leveraging natural language searches for SQL, non-technical teams can utilize Atlassian Analytics to access insights, pose questions, and explore visualizations of crucial business metrics. This enables a manager to inquire about business trends, customer support trends, or team health.
Traditionally, a data scientist would need to craft a SQL query to delve into company data, extract such information, and then format it accordingly. A straightforward, conversational query can prompt the AI to generate the underlying SQL code for reports, streamlining the process significantly.
Mansour highlighted that knowledge stored in Confluence can be accessed through AI agents, enabling employees to pose questions and receive answers in the full context of their identities. For instance, the system would be cognizant of the projects individuals are engaged in and the locations where they work.
He explained that one could ask the AI about HR policies, tailoring responses based on a user’s location. For instance, in Sydney, it would provide specific leave policies for Australia compared to other locations.
The current beta mode for Confluence incorporates this new capability. A comparable question-and-answer capability will launch in beta mode for Compass, the company’s developer experience platform designed to track and discover software components. Leveraging the same AI agent technology, users can inquire about their software stack, reducing the process of locating information about their tools and microservices, thereby reducing time and effort.