GitLab has made its Duo Agent Platform typically accessible, offering growth groups with agentic AI automation that has entry to a company’s full context, requirements, and guardrails.
The GA launch consists of Agentic Chat, offering context-aware help all through the GitLab platform. Agentic Chat builds on the beforehand launched Duo Chat, and brings in context from points, merge requests, pipelines, safety findings, and extra, and might carry out actions on a developer’s behalf.
For instance, within the Internet UI, Agentic Chat can create points, epics, merge requests, and spotlight key findings and create actionable steering primarily based on organizational context. Moreover, within the IDE, it will possibly generate code, configurations, and infrastructure-as-code, in addition to repair bugs, generate texts, and produce documentation.
Different methods Agentic Chat can be utilized are serving to builders perceive, configure, or troubleshoot CI/CD pipelines or create new ones, and on the safety entrance, it will possibly clarify vulnerabilities, assist with concern prioritization, and suggest fixes.
GitLab Duo Agent Platform additionally comes with pre-built foundational brokers which might be prepared out of the field. Two can be found at launch, and extra are in beta and shall be launched later. The Planner Agent helps construction, prioritize, and break down work in GitLab, and the Safety Analyst Agent critiques vulnerabilities and safety indicators and explains their impression.
Builders may construct customized brokers to suit their very own particular wants, or leverage exterior brokers, comparable to Claude Code or OpenAI’s Codex CLI.
“Collectively, these approaches give groups flexibility in how they undertake agentic AI, from specialised brokers, to organization-specific automation, to integrating exterior AI instruments — all inside a single, ruled platform,” GitLab wrote in a publish.
Foundational Agentic Flows are one other necessary part of the platform, enabling a number of brokers to be chained collectively to sort out advanced duties. A number of flows are actually accessible, together with:
- Developer: Builds a merge request from a problem
- Convert to GitLab CI/CD: Helps migrate pipeline configuration
- Repair CI/CD pipelines: Analyzes failures, identifies doubtless causes, and prepares beneficial modifications
- Code Assessment: Streamlines code overview by analyzing code modifications, merge request feedback, and extra
- Software program Growth in IDE: Guides work by means of growth and overview phases
GitLab additionally provides an MCP Consumer to allow the platform to connect with different techniques like Jira, Slack, Confluence, Playwright, and Grafana. Present options embrace configuration on the workspace and consumer stage, group-level controls to allow or limit utilization, and a consumer approval circulation for software entry.
Lastly, the platform consists of various options for governance and suppleness, together with being accessible throughout all GitLab platforms within the 18.8 launch cycle, mannequin choice the place subgroups inherit the selection of the top-level namespace, group-based entry management to customise which customers can entry sure options, and LDAP and SAML integration.
