GitLab expands AI coding partnership with Google Cloud

GitLab has reached an expanded agreement with Google Cloud enabling customers to count usage of the GitLab Duo Agent Cloud Platform towards their existing Google Cloud commitments.

Under the agreement, AI agents in GitLab Duo Agent Platform can now call foundation models including Gemini models through Google’s Vertex AI platform. Organisations will meanwhile be able to run GitLab’s AI Gateway on Google Cloud without the need for separate AI infrastructure.

GitLab is a system of record for issues, code, merge requests, pipelines and security findings during software development. When an AI agent generates a code suggestion, it draws context from this repository such as existing patterns and the continuous integration pipeline, with every action flowing through a standard set of access controls, approval rules and audit logging.

The Vertex AI Model Garden meanwhile provides joint customers with a choice of foundation models to enable selections based on criteria such as performance, cost or regulatory requirements.

GitLab Chief Product and Marketing Officer Manav Khurana said the collaboration is based on the fact that AI agents are only as good as the context they operate on and the governance around them.

“GitLab is where that context lives across issues, code, pipelines [and] security findings, and this partnership connects it to Vertex AI’s strongest models,” he said. “As agents take on more of the software lifecycle, the platform that provides both the context and the controls becomes the critical layer.”

Google Cloud MD for AI and Data Partnerships Ritika Suri added that the partnership will “provide customers with innovative capabilities that can improve operations, enhance customer experiences, and drive innovation in the DevSecOps industry”.

Image credit: iStock.com/Aree Sarak