Atlassian’s New Jira AI Features Give Coding Agents the Context to Build Software
In this era of AI-assisted software development, developers need to know what to build and how to control it, while coding agents need context to understand how to do it right.
To help organizations navigate and succeed with AI development and delivery, Atlassian today is releasing a new set of Jira capabilities that the company says successfully built a context-rich orchestration layer for autonomous coding agents.
Atlassian added these capabilities to address the gap between how much code AI is generating and the lack of productivity gains by developers. Among the challenges the industry faces in successfully implementing AI are lack of context that causes agents to deviate from needs, information that has no memory so previous work must be redone, and lack of control over autonomous agents.
“When a customer feels that they have to learn a new set of things, but rather with their existing Jira experience, and that we put those new features in a place where they can easily find and use them, the concept should be intuitive,” Ming Wu, Head of Engineering, DevaI, at Atlassian, explained to SD Times.
Among the new capabilities in Jira is Jira for Slack, which enables teams to create context-rich clarifications from conversations, feedback and ideas using @Jira. According to Atlassian’s announcement, “the agent updates work items, syncs conversations like comments, and assigns work to coding agents while your team collaborates on Slack.”
With this release, the company introduced Jira Planner for spec-driven development. Jira Planner collects pull codes, Jira and Confluence team history and team context to create requirements. Then, it can generate a spec in Confluence that developers or agents can build on. In addition, work items can be assigned to models and agents such as Claude Code, Cursor or GitHub Copilot directly within Jira, providing context for better responses from coding agents.
Additionally, video meetings can be turned by Atlassian’s Loom video messaging software into instructions and action plans agents can use to execute tasks. It’s these contextual assets that allow the agent to function effectively, Wu said. “Content engineering doesn’t just give you raw data. It’s an effective way to find the right content for your agent,” he said. “More content is not necessarily better. With Jira Planner, you can go and start in Jira and do planning work with your team. And during the planning phase, one of the important things is to connect all the stakeholders everywhere. We try to make that process very simple and effective, making sure that the right context appears during the planning.”
For complete visibility into agent behavior, Atlassian’s Teamwork Graph collects session records accessible from anywhere in Jira, the company announced, and new hooks in the Teamwork Graph CLI can connect local agent sessions directly to work in Jira, updating the context continuously to avoid agent flooding.
According to Atlassian, Jira for Slack, Jira Coding Agent, Jira agent automations, agent templates, and Jira agent sessions are available today to paid Jira Cloud customers at no additional cost. Jira Planner is available in early access, and Codex in Jira is coming soon. DX AI cost management is available to Atlassian DX customers.
