Transform MRs from manual tasks to an automated workflow (opens in new tab)

GitLab 19.0 expands Developer Flow from generating merge requests to managing much of their entire lifecycle. Its AI agent can respond to reviews, investigate codebases, resolve conflicts, and split oversized MRs, while automation handles rebasing and merging. The result is less manual effort between opening and merging an MR, with developers supervising rather than executing every step.

Developer Flow Across the MR Lifecycle

• Can be triggered from:
  • An issue via Generate MR
  • An issue or MR assigned to the Duo Developer service account
  • Any issue or MR discussion using the new @mention trigger
• Continues working on the same MR instead of creating separate changes to reconcile.
• Handles:
  • Multiple rounds of reviewer feedback
  • Merge conflicts on long-running branches
  • Codebase research and technical evaluations
  • Oversized MR splitting
  • New feature implementation
• Uses a single agentic loop with tools such as read, grep, file editing, and command execution.
• Reads AGENTS.md for project conventions and operational guidance.
• Uses agent-config.yml to configure dependencies, tooling, tests, and pre-commit hooks.

These capabilities are available through GitLab Duo Agent Platform on Premium and Ultimate plans.

Autonomous Merge Conflict Resolution

• The beta Resolve with Duo button is available on the MR conflict page and merge checks widget.
• The agent:
  • Reviews the MR’s intent and both branches
  • Selects a resolution strategy
  • Edits conflicting files
  • Commits and pushes the resolution
• It leaves a summary comment explaining the conflict and resolution path.
• If it cannot resolve the conflict safely, it reports that rather than guessing.

One-Click Rebase and Merge

• The beta feature combines rebasing and merging into one action.
• It is designed for teams using semi-linear or fast-forward merge methods.
• It is available on Free, Premium, and Ultimate tiers.

Reducing Manual MR Work

GitLab distinguishes between AI-driven judgment and mechanical automation:

• AI handles code changes, reviewer feedback, and conflict resolution.
• Automation handles tasks such as rebasing before merge.
• Together, these features reduce the time developers spend on repetitive MR maintenance while preserving human oversight for steering, reviewing, and final decisions.

Developers can try Developer Flow through a GitLab Duo Agent Platform trial. Existing Premium and Ultimate users with the platform can use it on merge requests, while older GitLab versions may require manually configuring the mention trigger.