Home
News
Tech Grid
Interviews
Anecdotes
Think Stack
Press Releases
Articles
  • Home
  • /
  • News
  • /
  • AI
  • /
  • Agentic AI
  • /
  • GitLab 18.11 Extends Agentic AI with Security Remediation and Pipeline Agents
  • Agentic AI

GitLab 18.11 Extends Agentic AI with Security Remediation and Pipeline Agents


GitLab 18.11 Extends Agentic AI with Security Remediation and Pipeline Agents
  • by: Business Wire
  • |
  • April 17, 2026

GitLab has released version 18.11, extending its agentic AI capabilities across the software lifecycle. The update introduces automated security remediation, simplified pipeline setup, and delivery analytics through new agents in the GitLab Duo Agent Platform, addressing key bottlenecks in code delivery, security, and operations.

Quick Intel

  • GitLab 18.11 expands agentic AI with Agentic SAST Vulnerability Resolution now generally available
  • New CI Expert Agent (beta) automatically generates and sets up CI pipelines from repository analysis
  • New Data Analyst Agent (generally available) provides natural language answers with visual insights on software lifecycle data
  • Agentic SAST generates ready-to-merge code fixes for confirmed vulnerabilities before production
  • New subscription-level and per-user spending caps for GitLab Credits enable predictable AI spend control
  • Agents leverage deep context from code, pipelines, issues, and security findings within GitLab

Agentic SAST Vulnerability Resolution Now Generally Available

Developers reportedly spend significant time remediating vulnerabilities after release. The new Agentic SAST Vulnerability Resolution agent analyzes confirmed true positives from SAST scans, generates code fixes targeting the root cause, and opens a ready-to-merge merge request with a confidence score. This allows teams to resolve issues before they reach production without extensive context switching.

New Agents to Eliminate Pipeline and Analytics Bottlenecks

The CI Expert Agent, now in beta, inspects a repository, identifies its language and framework, and proposes a complete build-and-test pipeline in natural language, enabling teams to have a running pipeline in minutes without manual YAML configuration.

The Data Analyst Agent, now generally available for Free, Premium, and Ultimate customers with GitLab Duo Agent Platform enabled, answers natural-language questions about live software lifecycle data. It provides fast visual answers on merge request cycle times, pipeline health, deployment frequency, and more.

Both agents are available on GitLab.com, Self-Managed, and Dedicated environments.

Predictable AI Usage Controls

New subscription-level and per-user spending caps for GitLab Credits give organizations better control over on-demand AI spend. Subscription-level caps allow billing managers to set monthly limits with enforcement, while per-user caps prevent any single user from exhausting the pool. Administrators gain full visibility through the GitLab Credits dashboard and Customers Portal.

“Much of the AI investment in software development has focused on writing code faster. The bigger opportunity is what comes next,” said Manav Khurana, chief product and marketing officer at GitLab. “Agents are only as effective as the context they can access. GitLab 18.11 extends our agents deeper into security, pipelines, and delivery analytics, where that context already lives. That's how GitLab is defining the future of software engineering in the AI era.”

About GitLab

GitLab is the intelligent orchestration platform for DevSecOps. GitLab enables organizations to increase developer productivity, improve operational efficiency, reduce security and compliance risk, and accelerate digital transformation. More than 50 million registered users and 50% of the Fortune 100* trust GitLab to ship better, more secure software faster.

  • Agentic AIDev Sec OpsSoftware Delivery
News Disclaimer
  • Share