DEVOPSdigest

GitLab released GitLab 18.10, making it easier and more affordable to use agentic AI capabilities across the entire software development lifecycle.

As AI-assisted coding has made it faster than ever to write code, the bottleneck has shifted to the hundreds of software engineering tasks that must happen afterward. GitLab 18.10 helps make it easier for GitLab customers to meet the challenge with simpler adoption, at lower costs and with a higher degree of trust.

GitLab Duo Agent Platform is now available to organizations on the GitLab.com free tier through a GitLab Credits commitment

Organizations on the GitLab.com free tier can now start using GitLab Duo Agent Platform by purchasing a monthly commitment of GitLab Credits. Credits are shared across the group, giving every member immediate access to GitLab Duo Agent Platform without per-seat costs.

The GitLab Credits dashboard gives group owners visibility into which agents and flows consume credits, connecting AI activity directly to delivery work and helping them monitor costs across the team.

Agentic Code Reviews are now more affordable at scale

Manual code review backlogs can add days or weeks to delivery cycles, creating bottlenecks and slowing innovation. Agentic Code Review automatically reviews merge requests across all groups and projects with the full context of the repository, pipeline, and security policies. At a flat cost of $0.25 per review (4 code reviews per GitLab Credit today), every organization can now enable agentic code review on every change. Compared to the cost of time spent on a manual code review, that could mean substantial savings as review volume grows.

Agentic false positive detection for security scanning is generally available within GitLab Duo Agent Platform

SAST false positive detection is now generally available to GitLab Ultimate customers using GitLab Duo Agent Platform, helping security and development teams better prioritize serious vulnerabilities and remediation. After each SAST scan, GitLab Duo Agent Platform automatically analyzes new critical and high-severity findings, scores them by false positive likelihood, and surfaces that assessment directly in the Vulnerability Report, helping security teams source a faster path to findings that require action, with final control over what gets dismissed.

“Development teams are shipping more code faster than ever, and the AI automation that keeps code secure and ensures it gets safely deployed has to keep pace - running across every project and every group, with the context of the entire platform,” said Manav Khurana, chief product and marketing officer, GitLab. “We’re accelerating access to advanced agentic AI across the software lifecycle for all software teams of all sizes, making it easier to adopt, more affordable to run, and at a greater level of security. Software teams can scale their innovation velocity within their guardrails and budget, on their own terms.”