GitLab Duo Agent Platform solves the AI paradox in software delivery

GitLab announced the GitLab Duo Agent Platform, delivering agentic AI that enables teams to orchestrate agents across the entire software lifecycle.

AI tools have been improving developers’ ability to write code, and in some cases, developers are reporting 10x productivity gains. Unfortunately, since only about 20% of a developer’s time is spent writing code, the associated improvement in total innovation velocity and delivery gained by AI is incremental. This is often described as the AI paradox in software delivery.

In addition, for many teams, increasing the speed of code authoring has led to new bottlenecks, including a larger backlog of code reviews, security vulnerabilities, compliance checks, and downstream bug fixes.

GitLab Duo Agent Platform addresses the AI paradox by unlocking intelligent orchestration and agentic AI automation across the software lifecycle within an organization’s context, standards, and guardrails.

“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.”

Expanding intelligent AI agents and orchestration capabilities

The general availability release of GitLab Duo Agent Platform includes:

Agentic Chat, which provides context-aware assistance across the GitLab Web UI and IDEs, uses multi-step reasoning to answer complex questions and perform autonomous actions, drawing on project data from issues, merge requests, pipelines, security findings, and more.

Agentic Chat supports numerous use cases, including:

• Analyze: In the Web UI, Agentic Chat can create issues, epics, merge requests, and provide summaries, highlight key findings, and offer actionable guidance based on the real-time context of the specific project, issue, epic, and merge request, as well as many other types of content. Agentic Chat can help developers understand unfamiliar code, dependencies, architecture, and project structure, in the IDE or inside a GitLab repository.
• Code: Agentic Chat can generate code, configurations, and infrastructure-as-code across a wide range of languages and frameworks. It can fix bugs, modernize code, generate tests, and produce documentation. It works in VS Code, JetBrains IDEs, Cursor, and Windsurf, with optional user- and workspace-level rules to tailor responses.
• CI/CD: Agentic Chat can help users better understand, configure, and troubleshoot existing pipelines or create new ones from scratch.
• Secure: Agentic Chat can explain vulnerabilities, prioritize issues based on reachability, and recommend fixes that can save time.

Foundational Agents are prebuilt by GitLab experts and are ready out of the box to handle the most complex tasks in the software delivery cycle. Included at general availability:

• Planner Agent helps teams structure, prioritize, and break down work directly in GitLab, helping make planning faster and easier to act on.
• Security Analyst Agent reviews vulnerabilities and security signals, explains their impact in plain language, and helps teams understand what to address first.

Custom Agents can be built using the AI catalog, a central repository where teams create, publish, manage, and share custom agents and flows across the organization. Teams can create agents with specific context and capabilities to enable agents and flows to work the way their engineering team works and solve problems using the engineering standards and guardrails their engineers use.

External Agents are seamlessly integrated into GitLab and include some of the very best AI tools currently available, including Claude Code from Anthropic and Codex CLI from OpenAI. Users will enjoy native GitLab access to these tools for use cases, including code generation, code review, and analysis with transparent security and embedded LLM subscriptions.

Foundational Agentic Flows automate complex tasks by chaining multiple agents.

• Developer (Issue to Merge Request) flow builds a structured MR from a well-defined issue so teams can begin work immediately.
• Convert to GitLab CI/CD flow helps teams migrate or modernize pipeline configurations without manual rewriting.
• Fix CI/CD pipeline flow analyzes failures, identifies likely causes, and prepares recommended changes.
• Code Review flow analyzes code changes, merge request comments, and more to streamline code reviews with AI-native analysis and feedback.
• Software development in IDE flow guides work through everyday development and review stages.

Governance, visibility, and deployment flexibility provide visibility into how agents are used, what actions they perform, and how they contribute to work. Usage and activity details help leaders understand adoption, measure impact, and ensure AI is being used appropriately.

• Available on all platforms, including GitLab.com, GitLab Self-Managed, and GitLab Dedicated as part of the GitLab 18.8 release cycle.
• Model selection allows top-level namespace owners to choose a model, and subgroups inherit those settings automatically. For organizations that want more control, the platform supports self-hosted models as part of GitLab Self-Managed deployments.
• Group-based access control allows administrators to define namespace-level rules that govern which users can access GitLab Duo Agent Platform features, supporting flexible adoption, ranging from immediate organization-wide enablement to phased rollouts. Lightweight Directory Access Protocol (LDAP) and Security Assertion Markup Language (SAML) integration enable governance at scale without manual configuration.

Pricing: For new usage-based products, including GitLab Duo Agent Platform, GitLab is introducing GitLab Credits, a virtual currency. All customers with active Premium and Ultimate subscriptions will automatically receive $12 and $24 dollars in included credits per user, respectively.

These credits will refresh monthly and give teams access to all Duo Agent Platform features at no extra cost. Customers consume credits when they use Duo Agent Platform capabilities and can purchase additional credits through a shared-pool or pay for them monthly on-demand as needed.