GitLab, Google Cloud Partner to Deliver Agentic DevSecOps with Vertex AI

• AI agents in GitLab Duo Agent Platform can now call foundation models through Vertex AI, including Gemini models, with agent actions governed by GitLab’s built-in compliance and audit controls.

• Organizations can run GitLab’s AI Gateway on Google Cloud with no separate AI infrastructure to provision or manage.

• Customers with Google Cloud commitments can count GitLab Duo Agent Platform usage toward their existing spend.

GitLab Inc., the intelligent orchestration platform for DevSecOps, announced an expanded collaboration with Google Cloud. Google Cloud customers can now power GitLab Duo Agent Platform with the Vertex AI models they already use and count that usage toward their existing Google Cloud commitments.

Recommended: AI-Powered DevOps: From CI/CD to Continuous Intelligence

As AI agents become central to how teams build software, they need strong models and a governed environment to be effective in the enterprise. This partnership brings those together. Agents in GitLab Duo Agent Platform can now call Vertex AI models on Google Cloud natively, giving joint customers the model performance they expect with the governance GitLab already provides.

GitLab is the system of record for issues, code, merge requests, pipelines, and security findings. When an agent generates a code suggestion, it draws context from the issue that prompted the work, the repository’s existing patterns, and the CI pipeline that will validate the result without leaving GitLab. Every agent action flows through the same access controls, approval rules, and audit logging that developers already follow, so governance does not stop when an agent takes over a task.

Recommended: RAG vs Fine-Tuning vs Agents: Choosing the Right AI Approach

The Vertex AI Model Garden gives joint customers a choice of foundation models, including Gemini, so teams can select models based on performance, cost, or regulatory requirements. For self-hosted customers, GitLab’s Bring Your Own Model option extends that flexibility further, letting teams connect their approved models and gateways. GitLab’s AI Gateway, whether GitLab-managed or self-hosted, runs on Google Cloud runtimes like GKE or Cloud Run, keeping AI workloads on the infrastructure teams already manage.

Write to us [⁠wasim.a@demandmediaagency.com] to learn more about our exclusive editorial packages and programmes.