お知らせ • Jul 16
Atlassian Corporation Announces System for Ai-Native Software Development in Jira
Atlassian Corporation announced new capabilities in Jira to advance AI-native software development for every engineering organization. This launch addresses a widening productivity gap: while AI usage by engineers has increased by 65%, developer velocity gains remain at approximately 10%. This plateau is driven by three core bottlenecks: a lack of enterprise context causing AI output to drift from requirements; unsolved SDLC bottlenecks outside of code generation, such as planning, review and maintenance; and difficulty of integrating AI across team workflows. Atlassian’s Teamwork Graph provides the enterprise context behind many of these capabilities, connecting work, teams, goals, code, and knowledge across the SDLC so agents can act with greater relevance and accuracy. In internal benchmarking, agents enriched by Teamwork Graph showed 44% more accurate results while using 48% fewer tokens than agents operating without that context. Jira for Slack closes the gap between team conversations and structured work. Now, you can turn conversations into context-rich specs. Create work items and kick off agent tasks from feedback or ideas in Slack just by asking @Jira. The agent updates work items, syncs conversations as comments, and assigns work to coding agents while your team collaborates in Slack, with expanded Microsoft Teams capabilities coming soon. The all-new Jira Planner enables spec-driven development to modern software teams. For complex projects, Jira Planner pulls from the Teamwork Graph, including your codebase, Jira and Confluence history, and team context, to define requirements and generate a structured technical spec in Confluence, ready for a developer or coding agent to build upon. Now, Loom turns what you show and say into structured instructions that agents can use to execute tasks. Record your screen and talk through what you want done. Loom captures your screens, clicks, links, and voice instructions and generates an action plan you can share with any agent or turn into agent-ready Jira work items in a few clicks. Now you can assign work items to Claude Code, Cursor, or GitHub Copilot directly from Jira (with Codex coming soon). Work stays grounded in Jira as the single source of truth, with context feeding improved responses from coding agents. The Jira Coding Agent uses the Teamwork Graph’s enterprise context and code intelligence to turn work items into ready-to-review pull requests, allowing rapid fixes and workflows within Jira without requiring local environment setup. Every engineer working in Jira gets visibility into agent sessions running across their spaces and repos in a single view, grouped by what needs attention first. Now, every engineering team can automate any business process using coding agents directly in Jira's enterprise-grade automation rule builder. Teams can route bug fixes, vulnerability remediation, test generation, and doc updates to agents in the background, with engineers notified when a PR is ready for review. The new Agentic Engineering project template and a guided setup wizard help engineering teams stand up agent-ready projects in minutes, with workflows, statuses, tracking, and integrations pre-configured. Teams can leverage the new DX AI cost management report to unify spend and token data across third-party tools like Claude, Cursor, and GitHub Copilot alongside Jira projects and teams, mapping total AI investment directly to engineering outputs to calculate an estimated cost per PR within DX. Agents in Jira (Claude Code, Cursor, and GitHub Copilot), Jira for Slack, Jira coding agent, Jira agent automations, agentic templates, and agent sessions in Jira are available for paid Jira Cloud customers at no additional cost. The waitlist for Jira Planner EAP is open, Rovo for Microsoft Teams is available in early access, and Codex in Jira is coming soon. DX AI cost management is available for Atlassian DX customers.