On this period of AI-assisted software program improvement, builders have to know what to construct and methods to govern it, whereas coding brokers want context to grasp methods to execute accurately.
To assist organizations navigate and succeed with AI-native improvement and supply, Atlassian in the present day is releasing a brand new set of capabilities in Jira that the corporate mentioned successfully create a context-rich orchestration layer for autonomous coding brokers
Atlassian added these capabilities to deal with the hole between how a lot code AI is producing and the shortage of productiveness good points by builders. Among the many points the business faces with implementing AI efficiently are an absence of context that causes brokers to float from necessities, prompts that haven’t any reminiscence so prior work must be redone, and an absence of governance over autonomous brokers.
“When the shopper doesn’t really feel like they need to study a very new set of issues, however fairly with their data of the present Jira, and that we put these new options within the place the place they’ll simply uncover and use them, the idea needs to be intuitive,” Ming Wu, Head of Engineering, DevAI, at Atlassian, defined to SD Occasions.
Among the many new capabilities in Jira are Jira for Slack, which allows groups to create context-rich specs from conversations, suggestions and concepts utilizing @Jira. In accordance with Atlassian’s announcement, “the agent updates work objects, syncs conversations as feedback, and assigns work to coding brokers whereas your staff collaborates in Slack.”
WIth this launch, the corporate is introducing Jira Planner for spec-driven improvement. Jira Planner gathers up code pulls, the staff’s Jira and Confluence historical past in addition to staff context to create necessities. Then, it could possibly generate a spec in Confluence that builders or brokers can construct on. Additional, work objects will be assigned to fashions and brokers similar to Claude Code, Cursor or GitHub Copilot straight from inside Jira, offering the context to get higher responses from coding brokers.
Moreover, video conferences will be turned by Atlassian’s Loom video messaging software program into directions and motion plans brokers can use to work on duties. It’s these contextual property that enable the agent to carry out properly, Wu mentioned. “Context engineering isn’t just providing you with the uncooked knowledge. It’s the environment friendly strategy to retrieve the best context on your agent,” she mentioned. “Extra context doesn’t essentially imply higher. With Jira Planner, you may go begin from Jira and do the planning work together with your staff. And in the course of the planning section, one of many key issues is placing all of the contacts collectively from in all places. We’re tryingto bare that course of tremendous handy and likewise efficient, ensuring the best context surfaces in the course of the starting stage.”
To get complete visibility into agent habits, Atlassian’s Teamwork Graph collects session data accessbile from wherever in Jira, the corporate introduced, together with new hooks within the Teamwork Graph CLI that may hyperlink native agent periods on to work in Jira, updating context constantly to keep away from agent drift.
In accordance with Atlassian, Jira for Slack, Jira Coding Agent, Jira agent automations, agentic templates, and agent periods in Jira can be found in the present day for paid Jira Cloud prospects at no further price. Jira Planner is accessible in early entry, and Codex in Jira is coming quickly. DX AI price administration is accessible for Atlassian DX prospects.
