GitLab delivers GitLab Duo Agent platform
The GitLab Duo Agent platform has reached general availability.
This is an AI-native solution that embeds multiple intelligent assistants in the form of agents throughout the software development lifecycle.
The real issue when attempting to apply agentic services to software application development lifecycles and workflows is… we need to know exactly where the automations, copilot services and accelerations are likely to be applied.
Why?
Because today, perhaps only 20% of a developer’s time is spent writing code… therefore, we need to create agentic developer services that actually perform useful tasks.
If we fail here, then we risk slipping into the software delivery AI paradox… and we need to avoid this paradox while still applying new intelligence services that align with an organisation’s business context, best practices, standards and guardrails.
GitLab says that the latest service here means that instead of following a linear workflow, developers will be able to collaborate asynchronously with AI agents and delegate routine tasks (such as code refactoring, security scans or performing reseact tasks) to specialised AI agents.
AI paradox
This is often described as the AI paradox in software delivery.
“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 organisations 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.”
GitLab Duo Agent Platform introduces a unified user experience designed for integration between humans and their AI agents inside GitLab.
Issues, merge requests & pipelines
Developers can engage Duo Agentic Chat on nearly every page they work on, ask questions contextually, follow asynchronous agentic sessions and interact with agents within familiar workflows like issues, merge requests and pipeline activities.
All of which helps make AI actions transparent and easy to control through everyday work.
“IDC forecasts that by 2030, 70% of organisations will embed AI agents into DevOps and DevSecOps pipelines, making orchestration platforms an increasingly important category. 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,” said Katie Norton, research manager at IDC.
Foundational agents are pre-built by GitLab as out-of-the-box functions to handle complex tasks in the software delivery cycle – the following foundational agents are already included as part of GitLab Duo Agent Platform’s general availability:
- Planner Agent helps teams structure, prioritise and break down work directly inside GitLab so planning becomes clearer, 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.
GitLab says that GitLab Duo Agent Platform enables developers to delegate tasks to agents and the platform offers a combination of foundational, custom and external agents, all integrated into the GitLab user experience.
