GitLab has announced new capabilities aimed at giving enterprises greater control as they scale agentic software development, including the ability for GitLab Dedicated customers to run GitLab Duo Agent Platform within the same single-tenant environment and region while connecting their own inference models and keeping AI-processed data inside existing security boundaries. GitLab 19.3 also introduces Secrets Manager, Flow Creator Agent, and bulk SAST false-positive detection and agentic vulnerability resolution, extending security and automation controls across software delivery workflows. The AI Gateway for GitLab Duo Agent Platform now operates within GitLab Dedicated infrastructure, supporting data residency and isolation requirements for regulated organizations. Secrets Manager applies consistent permissions to pipeline and infrastructure credentials while supporting Kubernetes, Terraform, OpenTofu, and custom tools.
Also Read: Harness Introduces AI Security Agents to Accelerate Vulnerability Detection and Remediation
Meanwhile, bulk SAST capabilities allow security teams to assess multiple findings, identify confirmed risks, and generate ready-to-merge fixes, helping reduce vulnerability backlogs. Flow Creator Agent enables process owners to describe custom automations in natural language and generate runnable workflows without manual schema mapping. Additional GitLab 19.3 updates include spending caps for GitLab Credits and restricted visibility for custom agents and flows. “These updates extend the speed and control enterprises need deeper into the regulated and data-sensitive segment of the enterprise market,” said Manav Khurana, chief product and marketing officer at GitLab. “Every capability we shipped this month, from where an agent runs to which secret it can touch, extends that same control into the trusted software delivery workflows enterprises already depend on.”