Operations | Monitoring | ITSM | DevOps | Cloud

We’re excited to announce that Agentic Pipelines is now generally available across all paid Cloud Bitbucket plans. You can run agents on our cloud runners or on self-hosted Linux Docker runners, with support for more runner types coming soon. With this launch, Bitbucket Pipelines evolves from a CI/CD tool into an intelligent workflow engine that increases developer productivity by letting agents handle routine engineering tasks.

Starting new software work has never been easier. Developers can assign tasks to multiple coding agents, let them work independently, and turn their attention elsewhere while those agents write, test, and revise code. As models improve, teams have more opportunities to pursue work that previously would have waited. Getting all that work validated and merged is another matter. The 2026 State of Software Delivery Q3 Pulse report shows teams working across more branches and projects.

Running several coding agents at once is pretty straightforward. Give each a task, let them work independently, and you can make progress on multiple things at the same time. But the more agents you have working, the more changes you need to coordinate. Agents can edit overlapping code, make conflicting assumptions, or finish work that depends on changes another agent hasn’t completed.

Most teams reach for Ansible in CI/CD pipelines the same way: a shell step that runs ansible-playbook, SSH keys stored as secrets, and a growing list of manual steps nobody documented. It works until it doesn't : then the failure happens at the worst possible moment and the pipeline becomes a debugging session.

We’re refreshing the Bitbucket Pipelines experience to make it easier to read logs, find the steps you need, and navigate a pipeline run. The update focuses on the Pipelines list and Pipeline result pages. This is a visual refresh only. Your pipeline configurations, builds, data, runners, variables, deployments, and integrations stay as they are. It’s the same Bitbucket Pipelines underneath, with a cleaner, more focused view.

A decision model is a specialized AI model that evaluates inputs against predefined outcomes, returning a structured choice, classification, or score. Unlike large language models (LLMs), which handle a broad range of generative and reasoning tasks, decision models are optimized for tasks like routing requests, selecting agent actions, and evaluating AI outputs.

Agentic Pipelines now integrates with the redesigned Atlassian MCP server for Claude and Codex agents. Rovo Dev CLI agents in Agentic Pipelines currently use the original version of Atlassian MCP server and are unaffected by this update.

Git worktrees let you check out multiple branches of the same repository in separate directories. Each worktree has its own files and staging area, but they all share the same Git history. You can work on several branches without repeatedly switching between them, stashing changes, or cloning the repository again. Worktrees are especially useful when working with coding agents. Tools like Claude Code, Codex, and Cursor can use them to handle multiple tasks in parallel without editing the same files.