Atlassian AI upgrades Jira with agentic software development tools and governance features

Atlassian AI Introduces Governed Agentic Software Development

Atlassian announced a comprehensive set of AI capabilities designed to help engineering organizations adopt and scale agentic software development across Jira, Confluence, and DX platforms1

1

2

2

. The launch addresses a critical enterprise gap: while 94% of engineering leaders report using AI, only 6% say they have the systems required to scale it across the software development lifecycle2

2

. According to Taroon Mandhana, Atlassian CTO of AI & Teamwork, the biggest bottleneck in AI software engineering isn't model intelligence—it's organizational context2

2

. The company is positioning Jira as the orchestration layer for agentic engineering workflows, extending its role as the system of record for how teams work.

Code Context Powers AI Coding Agents with Multi-Repository Intelligence

Atlassian introduced Code Context, built on the company's Teamwork Graph, which gives AI coding agents secure intelligence across complex, multi-repository codebases1

1

4

4

. This foundational capability enables more accurate results across the entire software development lifecycle, from vetting backlog ideas for architectural feasibility and generating code-aware implementation plans to accelerating bug triage and root-cause discovery2

2

. Recent analysis by DX found that teams whose AI tools used the most Atlassian context shipped roughly 64% more per developer4

4

. Agent Context Controls complement this by letting platform teams govern which Jira and Confluence spaces agents can access, ensuring outputs align with curated requirements, architectural decisions, and project standards4

4

.

Agentic Loops in Jira Automate Backlog-to-Code Workflows

Atlassian unveiled autonomous agentic loops in Jira that fundamentally shift how engineering teams handle routine development tasks1

1

. The system continuously scans backlogs for well-defined, unassigned work items, delegates them to Jira Coding Agent for execution and testing, and opens ready-to-review pull requests directly in Jira2

2

4

4

. This AutoDev system turns backlog items into code merge requests inside Jira without requiring iterative prompting1

1

. The agents can run for hours or days autonomously, activating when work needs to be done and checking in—moving beyond chatbot-style interactions to true always-on agentic software development1

1

.

Standards and AI Review Ensure Quality and Governance

To maintain code quality across agentic engineering workflows, Atlassian introduced Standards, which enable platform teams to define organizational coding standards once and map them to repositories2

2

. This creates consistent guardrails automatically shared across every agent and developer operating in the codebase4

4

. A dedicated AI Review agent reviews pull requests against these organizational standards, flagging issues before code ships2

2

4

4

. Additionally, a DevDocs agent automatically generates or updates technical documentation in Confluence directly from code repositories, ensuring documentation doesn't fall behind as agents ship code1

1

.

DX for Agentic Development Measures AI Impact and Accountability

Atlassian launched DX for Agentic Development to provide governance and accountability for AI coding agents2

2

. The platform measures AI impact across throughput, quality, adoption, and cost, mapping total AI investment directly to engineering outputs4

4

. It unifies AI Code Insights, tool and MCP tracking, model-to-task fit, and academic-validated Agent Experience research with rich software context and guardrails4

4

. Every time agents run, they generate audit logs with diagnostics that display and measure AI impact, letting teams understand spend across software as it ships1

1

. The Jira Agent Usage Dashboard helps team leaders understand which agents are used in their workflows, correlate agent sessions with Jira work, and improve delivery velocity with agents4

4

.

Rollout Timeline and Enterprise Adoption Path

Code Context is gradually rolling out to paid Atlassian customers through open beta2

2

4

4

. Agent loops, Standards, and AI Review are available in private early access3

3

4

4

. Agent Context Controls and Agent Usage Dashboard will be generally available to paid Jira customers in the coming months, while DX for Agentic Development will be generally available for Atlassian DX customers this quarter3

3

4

4

. The phased rollout reflects Atlassian's approach to helping engineering organizations transition from ad hoc AI experimentation to governed, enterprise-wide agentic software development at scale.