Operations | Monitoring | ITSM | DevOps | Cloud

Dave Killeen will tell you, on record, that his relationship with AI has crossed into unhealthy territory. He also says he has never felt more alive, that he is 50 and feels 30, and that he sometimes waits for his two small children to go to bed so he can start a coding session. In between, he gives Axel Sooriah the most practical answer on this show yet to the question every product team is facing: your exec says "we need AI," and you have no idea what they actually want.

Jira Planner is an AI planning agent in Jira that turns high-level product requirements into ready-to-build plans (requirements, technical specs, and Jira work items) grounded in your actual codebase, architecture, and Confluence context. In this video, you'll see how Jira Planner brings due diligence to the pre-build phase, so engineers and AI coding agents start from a plan that reflects the real code instead of a vague prompt. It's useful for product managers, engineering leads, and developers who want to cut the rework that comes from AI guessing at requirements.

Enterprise AI is only useful when it actually runs in production, inside the tools teams already depend on. Getting there is harder than it sounds. Forward Deployed Engineers at Atlassian work directly inside some of the world's largest organizations, building AI-powered agents, connectors, and workflows on Atlassian's platform. They work alongside customers to understand the real constraints, design solutions that hold up at scale, and see them through to deployment.

In the Startup Stories with Atlassian series, we interview founders about their entrepreneurial journey, learn about the problems they are trying to solve, and explore how their teams are using Atlassian tools to grow and deliver value to their customers. In this episode of Startup Stories with Atlassian, Adam sits down with Stan Suchkov, Founder and CEO of Evolve, to explore why pivoting isn't the failure most founders fear – and why the best founders do it deliberately, quickly, and without losing their team in the process.

Most CI/CD pipelines are fragile bash scripts that break when things change. What if your pipeline could think? Agentic Pipelines lets you add AI agents as steps in Bitbucket Pipelines. In this video, I show an agent that reads a design spec from Confluence, generates frontend code, runs tests, and opens a PR, all inside a pipeline. With Agentic Pipelines, Bitbucket goes from a CI/CD platform to a full workflow and automation engine you can use far beyond builds and deploys.

Customer interviews are one of the most powerful ways to build better products — but they’re also time-consuming. In this video, Avinoam “Avi” Zelenko, Principal Product Manager at Atlassian, shares how he transformed the way he runs customer interviews using AI automation and Rovo agents. What used to take hours of coordination, note-taking, and manual summaries now happens automatically. By stitching together the Teamwork Collection and Slack, Avi built a workflow that captures conversations, summarizes insights, and shares them across teams in real time.

Bitbucket Pipelines already supports triggering on repository pushes and pull request pushes. But if you wanted to react to other events like a deployment finishing, a build failing, or a PR getting merged, you had to wire that up yourself with webhooks or external glue code. New trigger types let you define those conditions directly in your YAML. You can fire custom pipelines on events like pipeline-completed, deployment-completed, pullrequest-created, pullrequest-fulfilled, and more.

AI transformation doesn’t succeed without people at the center. At Atlassian, HR is leading the way. Our People team believes that the best AI culture isn’t mandated from the top. It’s built by meeting employees where they are, partnering with leaders across the business, and making AI part of how work gets done from day one. See how Atlassian’s HR team is building a culture of experimentation where everyone builds, and what that looks like in practice.

Bitbucket Pipelines lets you invoke child pipelines from a parent step, but until now there was no way to pass information between them. Variable sharing changes that. You can define variables in a parent step and pass them directly to child pipelines as custom pipeline variables. With dynamic step conditions, those child pipelines can make decisions at runtime based on the values they receive, like skipping a deployment when a security scan detects critical vulnerabilities.

What used to take months now takes weeks, and it’s changing what it means to build great products. At Atlassian, product managers and designers are using Rovo and Jira Product Discovery to move faster at every stage of the development lifecycle. From running deep research across all their tools and documents, to capturing ideas, surfacing insights, and prioritizing what to build next. AI is transforming how product decisions get made.