Foundational agents

Foundational agents are specialized AI assistants that extend the capabilities of GitLab Duo Chat with domain-specific expertise and context awareness.

Unlike the general-purpose GitLab Duo agent, foundational agents understand the unique workflows, frameworks, and best practices of their specialized domains. Each agent combines deep knowledge of GitLab features with role-specific reasoning to provide targeted help that aligns with how practitioners actually work.

When you interact with a foundational agent, you’re engaging with an AI tool that understands not just what you’re asking, but the broader context of your role and objectives. For example:

• A product planning agent that understands prioritization frameworks and dependency management.
• A security agent that recognizes vulnerability patterns and compliance requirements.

These agents integrate into your existing GitLab workflows through Chat, and can help provide specialized support without requiring you to leave your current context.

GitLab provides foundational agents for workflows where specialized knowledge significantly improves outcome quality. Each agent maintains awareness of GitLab-specific implementations, organizational standards, and industry best practices in its domain. This specialization helps enable more accurate, actionable, and contextually appropriate responses compared to general-purpose AI help.

Available foundational agents

The following foundational agents are available:

• GitLab Planner Agent, for product management and planning workflows.
• GitLab Security Analyst Agent, for security analysis and vulnerability management.

Turn foundational agents on or off

By default, foundational agents are turned on. You can turn them on or off for a top-level group (namespace) or for an instance.

If you turn foundational agents off, you can still use the default GitLab Duo agent.