We envision a world where our innovations in AI-driven code creation not only enhance productivity but also inspire creativity, enabling developers to tackle more complex challenges and push the boundaries of what’s possible in software development.
Develop cutting-edge AI-powered tools that enhance the efficiency and creativity of software engineers. We are committed to providing intelligent code suggestions that not only streamline coding tasks but also elevate the quality of software products. We aim to empower developers worldwide, making complex coding more accessible, and accelerating the creation of exceptional software.
One of the main features we work on in the Create:Code Creation group is Code Suggestions. Here is some quick information to get you started with Code Suggestions.
A lot of the terms we use in this area sound similar and can be confusing at first. Here are the basic terms we use:
If it helps, here are these terms in a diagram:
stateDiagram
direction LR
state "Code Creation" as creation
state "Code Suggestions" as suggestions
state "Code Completion" as completion
state "Code Generation" as generation
state "Duo Chat Features" as duo
creation --> suggestions
creation --> duo
suggestions --> completion
suggestions --> generation
| Category | Handle |
|---|---|
| GitLab Team Handle | @code-creation-team |
| Slack Channel | #g_code_creation |
| Slack Handle (Engineers) | @code-creation-engs |
The following people are permanent members of the Code Creation Team:
| Name | Role |
|---|---|
 Matt Nohr
|
Backend Engineering Manager, Create:Code Creation |
 Allen Cook
|
Senior Backend Engineer, Create:Code Creation |
 Backend Engineer
|
Backend Engineer, Create:Code Creation |
 Jan Provaznik
|
Staff Backend Engineer, Create:Code Creation |
 Leaminn Ma
|
Senior Backend Engineer, Create:Code Creation |
 Mikołaj Wawrzyniak
|
Staff Backend Engineer, Create:Code Creation |
 Missy Davies
|
Backend Engineer, Create:Code Creation |
 Pam Artiaga
|
Senior Backend Engineer, Create:Code Creation |
|
Shola Quadri
|
Associate Backend Engineer |
 Sri Rangan
|
Staff Fullstack Engineer, Create:Code Creation |
 Tian Gao
|
Backend Engineer, Create:Code Creation |
 Vitali Tatarintev
|
Senior Backend Engineer, Create:Code Creation |
You can reach the whole team on GitLab issues/MRs by using the @code-creation-team handle.
The following members of other functional teams are our stable counterparts:
| Category | Counterpart |
|---|---|
| Product Manager |
 Jordan Janes
|
| Technical Writing |
 Jon Glassman
|
| UX |
 Andy Volpe
(Create Stage) |
| SET |
 Jay McCure
(Create Stage) |
| Support | TBD |
| AppSec | TBD |
Here are other groups within GitLab that we work closely with:
To help get started as a developer with the Create:Code Creation team, we have created an onboarding issue template.
Sync: Code Creation - a meeting held once a week on Tuesday at 15:00 UTC to align on group priorities. If there are no points on the meeting agenda one hour before the meeting starts, that meeting is considered as canceled.
All of our meetings and videos are uploaded to the Code Creation YouTube Playlist. Some meetings are marked as private, so internal team members will need to swtich to use the Unfiltered YouTube account.
We maintain a practice of weekly async status updates to ensure clear communication, track progress effectively, and maintain transparency across our team. This process aligns with our core values by fostering collaboration, driving results, and promoting efficiency through structured communication.
This is the template to use for the updates
## Async Status Update yyyy-mm-dd
- **Progress & Status**: _What progress have you made? What's the current state?_
- **Next Steps**: _What are your planned next actions?_
- **Blockers**: _Are you blocked or need assistance with this?_
- **How confident are you that this will make it to the current milestone?**
- [ ] Not confident
- [ ] Slightly confident
- [ ] Very confident
_Remember to update the workflow label!_
/cc @mnohr @jordanjanes
Be sure to tag the engineering manager, product manager, and any team members you are collaborating with.
The AI Context Framework Task Force aims to create a robust and scalable system for storing, managing, and utilizing additional context across all AI features within GitLab. We envision a framework that enhances the intelligence and effectiveness of our AI-powered tools by leveraging project-specific information, ultimately leading to more accurate and tailored AI responses for our users.
Our mission is to develop a comprehensive context framework that will:
Welcome to the technical overview of GitLab’s Code Suggestions, a feature designed to enhance the coding experience by integrating advanced AI technologies directly within your development environment. This page serves as your guide to understanding the architecture and interactions behind our innovative Code Suggestions feature, which significantly streamlines coding processes through intelligent completions and generative coding capabilities.
At its core, Code Suggestions operates through a sophisticated workflow involving multiple components such as IDE extensions, the Language Server, GitLab Workhorse, and our AI Gateway, all culminating in providing you with real-time, context-aware coding suggestions. From simple code completions that speed up your typing tasks to complex code generations that craft entire code blocks, our system is designed to support a wide array of coding activities and enhance productivity.
At GitLab and on the Code Creation team, we believe in a structured yet flexible approach to milestone planning to ensure that our engineering and product teams are aligned, focused, and able to deliver high-quality work efficiently. This page outlines our process for planning and preparing for milestones.
Here are the weights we use for issue estimation:
This document contains Code Suggestions development guidelines for engineers.
For an overview of Code Suggestions, please refer to Create:Code Creation Group engineering guide
As the Code Suggestions offering continues to mature and we discover more about our users’ needs as well as available AI models, we will need to add or switch to new AI models that Code Suggestions will use.
Integrating a new AI model into our systems generally consists of three steps:
0c8c1b24)
