AI Engineering

Vision

Our goal is not merely to launch features, but to ensure they land successfully and provide real value to our customers. We strive to develop a best-in-class product that exceeds expectations across all user groups by meeting high-quality standards while ensuring reliability and maintaining an ease of operation and scalability to meet diverse customer needs. All team members should remain mindful of our target customers and the multiple platforms we support in everything we do.

Ensure our product excels in all aspects especially for our primary customer organization archetypes of large enterprises. This includes scalability, adaptability, and seamless upgrade paths. When designing and implementing features, always keep in mind compatibility for all our deployment options: self-managed, dedicated and Software as a Service (SaaS).

Develop our technical, diverse and global team to drive results that support our product and customer growth, while maintaining our values and unique way of working.

Mission

GitLab’s unique way of working asynchronously, handbook first method, utilization of the product we develop and clear focus on our values enables very high productivity. We focus on constantly improving quality, usability and reliability of our product to reach maximum customer satisfaction. Community contributions and customer interactions rely on efficient and effective communication. We are a data-driven, customer experience first, open core organization delivering one secure, reliable, world leading DevSecOps platform. Join us in setting new standards, driving innovation, pushing the boundaries of DevSecOps, and consistently delivering exceptional results for our customers.

Organizational Structure

@startwbs
* AI Engineering
** Editors Extensions
** Code Creation
** AI Framework
** Duo Chat
** Duo Agent Platform
** Duo Workflow Catalogue
** Global Search
** Analyze
*** Product Analytics
*** Analytics Instrumentation
*** Optimize
@endwbs

AI Engineering stakeholders

This section provides an overview of all teams invested in implementing and maintaining AI features. Our Duo initiative is a cross-category effort.

These are the stakeholders:

Team Responsible For
Editor Extensions Maintains the GitLab Workflow VS Code Extension (maintainers), JetBrains, Neovim, Visual Studio extensions and the language server. Also contributes with UX improvements for Code Suggestions within GitLab Workflow.
Cloud Connector (@mkaeppler, @nmilojevic1) Supports access to Duo for Self-Managed: Cloud Connector, Unit Primitives
AI Framework Abstraction Layer / AI Gateway for LLM integration to the application (GitLab Chat, Code Suggestions and other AI capabilities)
AI Framework (formerly Model Validation) Custom feature evaluators, evaluation support, automated evaluation tooling
Global Search Abstraction Layer / Vector Storage / Semantic search
Duo Chat GitLab Chat for VSCode and WebIDE
Code Creation Code Suggestions (Code completion, Code generation)
Infrastructure Platforms - Runway AI Gateway Scalability / Runway infrastructure

| Duo Agent Platform | Agentic observability / Reusable Agentic components / Duo workflow service |

Counterparts

The AI department engineering structure is different from the Product structure. To read about how we collaborate and who are the counterparts, you can check the AI product’s page.

ClickHouse Datastore usage

ClickHouse usage by Monitor:Platform Insights group

AI Experimentation

We strongly encourage team members to experiment and develop AI-related projects as part of their exploration and learning journey. These experimental initiatives help accelerate our work and allow AI teams to embrace emerging challenges and opportunities.

Existing projects may be reviewed by product and engineering teams on a case-by-case basis for potential migration into GitLab-managed projects.

To protect GitLab’s brand while maintaining our commitment to transparency, all experimental AI projects must prominently display the following disclaimer at the top of their README:

“⚠️ This is an unofficial project. It is not endorsed or supported by GitLab Inc. and is not recommended for use in production environments.”


AI Framework Group
The AI Framework group is focused on how to support other product groups at GitLab with the AI Abstraction Layer, and GitLab AI feature development.
Code Creation Group
The Code Creation Group is responsible for all product categories that fall under the Code Creation group of the AI Engineering organization.
Create:Editor Extensions Group
The Create:Editor Extensions Group is responsible for all product categories that fall under the Editor Extensions group of the Create stage.
Custom Models Group
The Custom Models group focuses on additional, custom models that power GitLab Duo functionality in support of our customers unique data and use-cases.
Duo Chat Group
We are dedicated to enhancing DevSecOps productivity by building an AI natural language interface to GitLab's Platform.
Duo Workflow Group
The Duo Workflow group is focused on developing GitLab Duo Workflow, an AI system to automate tasks and help increase productivity in your development workflow.
Global Search Group
The Global Search team is focused on bringing world class search functionality to GitLab.com and self-managed instances.
Workflow Catalog Group
The Workflow Catalog group is focused on developing Workflow Catalog, a catalog of AI Agents, tools, and workflows that can be created, curated, and shared across organizations, groups, and projects.
Last modified June 27, 2025: Cleanup AI Engineering Handbook (7faf63b4)