AI coding
Duo Chat
Duo Chat, as part of the GitLab Duo Agent Platform, is an enterprise-grade AI programming and automation suite by GitLab.
What is Duo Chat?
Duo Chat, as part of the GitLab Duo Agent Platform, is an enterprise-grade AI programming and automation suite by GitLab.It goes beyond simple code completion by functioning as an intelligent agent system that understands the entire software development lifecycle.Powered by the GitLab Orbit context graph, Duo Chat connects code, pipelines, and deployment data to provide AI agents with precise project context, resulting in more relevant and reliable development assistance.
The platform supports end-to-end automation from planning and coding to security analysis and CI/CD troubleshooting.Users can leverage pre-built specialized agents for common tasks or customize agent workflows to match organizational standards.With integration capabilities for external models like Claude Code and Codex, alongside strict policy-driven governance, Duo Chat helps teams significantly accelerate software delivery while maintaining security and compliance.
Key features
- GitLab Orbit ConLeverages the native context graph to provide AI agents with real background information on code, pipelines, and deployments, enhancing accuracy and relevance.
- Full-Lifecycle AOffers expert-built agents designed for planning, coding, security analysis, and analytics, covering every stage from idea to production.
- Automated WorkflAutomates complex tasks such as merge request reviews, security scans, and pipeline testing, pushing changes to production with minimal manual intervention.
- Enterprise GoverEnables policy-driven AI control to define allowed agents and models, tracing every action back to user identities for full compliance and transparency.
- Flexible Model ISupports integration with external agents like Claude Code and Codex, and allows running self-hosted or bring-your-own models via a single-tenant AI Gateway.
- Measurable ROIUses Impact Analytics to measure the true value of AI investments by team, task, and model, enabling evidence-based decision making for future AI adoption.
How to use it
- 1.Log in to your GitLab account and navigate to the GitLab Duo Agent Platform.
- 2.Browse the AI Catalog to select pre-built agents suitable for your current task, such as code review or security analysis.
- 3.Configure agent parameters as needed, or create custom agents to align with your team's coding standards and workflows.
- 4.Trigger agent workflows within your projects via GitLab events, scheduled runs, or directly through the chat interface.
- 5.Review the merge requests, fix suggestions, or analysis reports generated by the agents, applying human checkpoints where required.
- 6.Use Impact Analytics to monitor agent usage and effectiveness, optimizing your AI strategy based on real data.
Where it fits
- CI/CD Pipeline DAutomatically analyzes root causes of build failures and generates fixes in new merge requests, reducing troubleshooting time.
- Automated Code RAgents gather feedback and iterate on merge requests to ensure code quality meets team standards, accelerating the review process.
- Security VulneraAutomatically analyzes vulnerabilities in the codebase, dismisses false positives, and provides specific security remediation guidance.
- Legacy System MiAutomatically converts existing CI/CD configurations to GitLab CI/CD format, reducing manual effort and error rates during migration.
Pricing and free quota
Pricing and any free quota follow the official site.
Who it is for
- Software Developers
- DevOps Engineers
- Security & Compliance Teams
- Technical Leaders
FAQ
Which external AI models does Duo Chat support?
The platform supports integrating external agents like Claude Code and Codex, and also allows users to use self-hosted or bring-your-own models via the AI Gateway.
How do I ensure AI agent actions comply with company security policies?
Through policy-driven AI control, administrators can define allowed agents and models, and trace all actions back to specific user identities to ensure full compliance.
What is GitLab Orbit?
GitLab Orbit is the lifecycle context graph that provides AI agents with real background information on code, pipelines, and deployments, improving agent accuracy and efficiency.
Can I customize AI agent workflows?
Yes.You can create or refine agents to follow your organization's conventions and quality expectations, managing and deploying these custom workflows via the AI Catalog.