Automating mutation coverage across large Java projects with a dev‑in‑the‑loop AI assistant built on Rovo Dev CLI. This guided workflow reads mutation reports, prioritises classes, generates project‑aware tests, and auto‑validates coverage gains, helping Jira Platform teams reach 80%+ mutation coverage with ~70% less manual effort, while continuously improving prompts and collaboration across projects.

Atlassian provides insights into software development collaboration, project management, and team productivity, offering documentation, tutorials, and best practices for using Atlassian's suite of tools, including Jira, Confluence, and Bitbucket. By exploring Atlassian's curated content, developers can learn about agile methodologies, version control workflows, and continuous integration practices for managing software development projects effectively. Whether you're working in a small startup or a large enterprise, Atlassian offers resources to streamline your collaboration and drive project success.

Atlassian

A team at Atlassian built a Mutation Coverage AI Assistant using Rovo Dev CLI to automate the process of improving mutation test coverage across large Java projects. The assistant reads mutation reports, recommends which classes to target, generates project-aware tests following existing conventions, and auto-validates whether coverage actually improved. Using a dev-in-the-loop approach rather than full autonomy, the tool helped Jira Platform teams reach 80%+ mutation coverage with ~70% less manual effort. Key lessons include the need for package-level analysis on large projects, tightening prompt instructions to avoid bad code patterns, adding mutant-type-specific test guidelines, and treating prompts as evolving collaborative artifacts stored in version control.

Automating Mutation Coverage with AI: Our Journey and Key Learnings

How is this different from just using other AI tools or manual prompts?

Dev-in-the-loop AI Assistant (Guided Automation)

From experiment to real impact across teams