Atlassian Adds Agent Orchestration to Jira and Confluence

Atlassian has introduced a suite of capabilities designed to help engineering organizations integrate AI agents into their software development workflows with built-in governance and measurement tools.

The company announced updates to Jira, Confluence, and its DX platform that address what it identifies as a critical gap: while 94% of engineering leaders report using AI, only 6% say they have systems to scale AI across the full development lifecycle, according to Atlassian.

Three pillars for agentic workflows

The new capabilities center on three areas: context, execution, and governance.

Code Context, built on Atlassian's Teamwork Graph, provides AI agents with secure access to information across multiple code repositories. This allows agents to assess backlog items for architectural feasibility, generate implementation plans, and accelerate bug triage with awareness of the broader codebase. Agent Context Controls enable platform teams to define which agents can operate in specific spaces and what data they can access.

Agentic loops in Jira automate the path from backlog item to pull request. The system continuously scans for well-defined, unassigned work, delegates tasks to Jira Coding Agent for execution and testing, then opens pull requests ready for human review directly in Jira. Platform teams can define organizational coding standards once and apply them across repositories. A dedicated AI review agent checks pull requests against these standards before code ships.

DX for Agentic Development measures AI impact across throughput, quality, adoption, and cost. The tool maps AI investment to engineering outputs and combines AI Code Insights, tool tracking, model-to-task fit analysis, and Agent Experience research with software context and guardrails.

Why it matters

The announcement reflects a shift from isolated AI coding assistants to orchestrated agent systems that integrate with existing project management infrastructure. For enterprises, the challenge isn't whether to adopt AI coding tools—it's how to deploy them at scale without losing visibility into what agents are doing, whether they're following organizational standards, and what return they're delivering. Atlassian's approach embeds agents into the workflow management layer where engineering work is already tracked, rather than requiring teams to adopt entirely new tooling.

"The biggest bottleneck in AI software engineering isn't model intelligence, it's organizational context," said Taroon Mandhana, Atlassian CTO for AI and Teamwork. "Enterprises need more than isolated sessions and one-off prompts."

Availability

Code Context is rolling out to paid Atlassian customers through open beta. Agent loops, Standards, and AI Review are in private early access. Agent Context Controls and Agent Usage Dashboard will be generally available to paid Jira customers in coming months. DX for Agentic Development will be generally available for Atlassian DX customers this quarter.

These details were first reported by CXOToday.