.jpg)
GitLab has announced the general availability of GitLab Duo Agent Platform, introducing agentic AI to orchestrate intelligent agents across the full software development lifecycle. This addresses the AI paradox where faster code generation from AI tools yields only incremental gains in overall delivery speed, as coding occupies just a fraction of developers' time.
GitLab Duo Agent Platform expands intelligent AI capabilities to overcome bottlenecks created by accelerated coding, such as backlogs in reviews, security issues, compliance, and bug fixes. By orchestrating agents with deep context from issues, merge requests, pipelines, security findings, and more, it enables true end-to-end automation while maintaining organizational control.
Agentic Chat delivers advanced, context-aware assistance that performs multi-step reasoning and autonomous actions. In the Web UI, it analyzes projects to create issues, epics, merge requests, summaries, and actionable insights. Developers can use it to understand unfamiliar code, dependencies, architecture, and structures in IDEs or repositories. For coding, it generates code, configurations, infrastructure-as-code, bug fixes, modernizations, tests, and documentation across languages and frameworks in supported IDEs like VS Code, JetBrains, Cursor, and Windsurf, with customizable rules.
In CI/CD, Agentic Chat aids in understanding, configuring, troubleshooting, and creating pipelines. For security, it explains vulnerabilities, prioritizes based on reachability, and suggests fixes to reduce manual effort.
Prebuilt Foundational Agents from GitLab experts include the Planner Agent for structuring, prioritizing, and breaking down work in GitLab, and the Security Analyst Agent for reviewing vulnerabilities and security signals in plain language to guide prioritization.
Custom Agents are created, published, managed, and shared via the AI Catalog, allowing teams to tailor agents to their specific engineering standards and guardrails. External Agents integrate leading tools like Claude Code from Anthropic and Codex CLI from OpenAI directly into GitLab for code generation, review, and analysis with built-in security and LLM access.
Foundational Agentic Flows chain agents to handle complex, multi-step tasks automatically. Examples include Developer (Issue to Merge Request) flow for structured merge requests from issues, Convert to GitLab CI/CD and Fix CI/CD pipeline flows for modernization and troubleshooting, Code Review flow for AI-driven analysis and feedback, and Software development in IDE flow for guided everyday workflows.
The platform offers robust governance with visibility into agent usage, actions, and contributions to work, helping leaders track adoption and impact. It supports all deployment types, model selection with inheritance, self-hosted models on Self-Managed, and namespace-level access controls integrated with LDAP and SAML for scalable, phased rollouts.
Pricing introduces GitLab Credits as virtual currency for usage-based features. Active Premium and Ultimate subscribers receive monthly included credits ($12 for Premium, $24 for Ultimate per user), refreshing automatically and covering Duo Agent Platform access, with options to purchase more as needed.
“GitLab Duo Agent Platform enhances our development workflow with AI that truly understands our codebase and our organization,” said Bal Kang, engineering platform lead at NatWest. “Having GitLab Duo AI agents embedded in our system of record for code, tests, CI/CD, and the entire software development lifecycle boosts productivity, velocity, and efficiency. The agents have become true collaborators to our teams, and their ability to understand intent, break down problems, and take action frees our developers to tackle the exciting, innovative work they love.”
“IDC forecasts that by 2030, 70% of organizations will embed AI agents into DevOps and DevSecOps pipelines, making orchestration platforms an increasingly important category,” said Katie Norton, research manager at IDC. “In more autonomous delivery models, the ability to coordinate agents across the software lifecycle while maintaining clear boundaries and visibility becomes a key requirement. GitLab’s approach aligns with this shift by focusing on policy enforcement and governance alongside efforts to reduce operational friction.”
“The general availability of GitLab Duo Agent Platform marks a fundamental shift in how AI delivers value in software development,” said Manav Khurana, chief product and marketing officer at GitLab. “We've seen AI make coding faster, but that is just one part of what it takes to deliver innovation at scale. Now organizations can orchestrate AI agents across the entire lifecycle in one unified system, with the comprehensive context and governance they need to help them innovate and ship software faster.”
To explore GitLab Duo Agent Platform further, check the official GitLab blog. Register for GitLab Transcend, a virtual event on February 10, 2026, to learn how agentic AI is transforming software delivery.
About GitLab
GitLab is the most comprehensive, intelligent DevSecOps platform for software innovation. 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 more than 50% of the Fortune 100** trust GitLab to ship better, more secure software faster.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.