AI Integration

Attributes

Property	Value
Date Created	2022-03-23
Target End Date	TBD
Slack	`#wg_ai_integration` - Slack channel for the working group and the high level alignment on getting AI ready for Production
Slack	`#ai_integration_dev_lobby` - Channel for all implementation related topics and discussions of actual AI features
Slack	`#ai_enablement_team` - Channel for the AI Enablement Team which is building the base for all features (experimentation API, Abstraction Layer, Embeddings, etc.)
Slack	`#ai_strategy` - Discussion on strategic and business initiatives surrounding AI/ML at GitLab.
Slack	`#ai-experiments-infra` - Infrastructure/Platform support for AI integration. See also &969.
AI Architecture Documentation	Doc
Google Doc	Working Group Agenda
Feature Tracking	Sheet
YouTube playlist	Playlist on GitLab Unfiltered
Parent Epic	Parent epic
Epic/Issue Working Group label	`wg-ai-integration` issue board and `wg-ai-integration` epic search
Epic label for prioritized prototypes	`wg-ai-integration-prioritized-prototype`
Issue Board for AI enablement group	Issue board link using label `group::ai-enablement`
Overview & Status	See Exit Criteria below
Meeting schedule	Monday, Tuesday, and Wednesday at 8am Pacific and Thursdays at 1pm Pacific

Goal

The GitLab AI Integration Working Group aims to define, coordinate and ramp up integration of AI capabilities into all product areas

Overview

Corresponding Epic

We want to enable all product teams to be able to use advanced AI capabilities for improving and adding functionality to the product so users can be faster and more productive in their DevSecOps lifecycle. For product teams we want to establish a clear and fast way for going from idea, experiment to production when using AI functionality. Incorporating the services, models and knowhow that the MLOps group has built over time and can provide to the wider team.

The working group will facilitate fast experimentation and prototyping of AI capabilities. We will also advise on what must be considered (and in some cases, get explicit approval on) before moving to production, including legal approval, ethical use of AI, potential necessary changes to terms of service, performance implications, hosting cost implications, infrastructure readiness, security readiness, licensing of 3rd party software/services, appropriate GitLab licensing levels for features, value add in helping users achieve their goals and needs, etc.

More information on the effort and plans can be found in the internal handbook.

Goals

This is a list of topics that we want to discuss:

Classification of AI possibilities and complexities
Ideation and understanding how experimentation can be done
Rapid ML Prototyping
- API's and Framework for experimentation
- Feature Flagged Prototypes
- Determine how teams without Product Design representation can progress with validation
Groundwork
- Base API's for all teams
- Infrastructure
- Documentation
- Understanding of Jobs and user needs to be affected
Existing ML features
Road to production for features
- Different gates

Exit Criteria

The table below lists all exit criteria for the working group. This is the top-level epic.

Q2 OKRs

Deliver X experimental, Y beta, and Z GA AI features

Roles and Responsibilities

Working Group Role	Username	Person	Title
Executive Stakeholder	@hbenson	Hillary Benson	Senior Director, Product Management - Sec, Data Science & Monitor
Executive Stakeholder	@timzallmann	Tim Zallmann	Senior Director of Engineering, Dev
Facilitator	@tmccaslin	Taylor McCaslin	Group Manager, Product - Data Science
Facilitator	@wayne	Wayne Haber	Director of Engineering
Functional Lead - AI Assisted	@mray	Monmayuri Ray	Engineering Manager AI Assisted
Functional Lead - UX	@jmandell	Justin Mandell	Product Design Manager: Analytics, Govern, ModelOps, and Secure
Functional Lead - UX	@pedroms	Pedro Moreira da Silva	Staff Product Designer
Functional Lead - Legal	@m_taylor	Matthew Taylor	Sr. Director of Legal
Pricing representative	@seanhall	Sean Hall	Principal Pricing Manager, Product
Product representative	@mushakov	Melissa Ushakov	Group Manager, Product - Plan
Product representative	@sarahwaldner	Sarah Waldner	Group Manager, Product - Create
Product representative	@abellucci	Alana Bellucci	Senior Product Manager, Govern:Threat Insights
Product representative	@joshlambert	Joshua Lambert	Director of Product, Enablement
Product representative	@tlinz	Torsten Linz	PM, Source Code
Development representative	@johnhope	John Hope	SEM, Plan
Development representative	@andr3	André Luís	FEM: Source Code
Development representative	@cdu1	Chun Du	Director of Engineering, Enablement
Development representative	@igor.drozdov	Igor Drozdov	Staff Backend Engineer, Source Code
Development representative	@jeromezng	Jerome Ng	Director of Engineering, Fulfillment
Development representative	@pcalder	Phil Calder	Senior Engineering Manager, Anti-abuse, Govern, and Growth
Development representative	@nmccorrison	Neil McCorrison	Engineering Manager, Govern: Threat Insights
Development representative	@carlad-gl	Carla Drago	Senior Backend Engineer, Manage: Import & Integrate
Development representative	@donaldcook	Donald Cook	EM, Project Management
Legal representative	@jbackerman	Jesse Backerman	Managing Legal Counsel
Vulnerability Research Representative	@idawson	Isaac Dawson	Staff Vulnerability Researcher
Vulnerability Research Representative	@dbolkensteyn	Dinesh Bolkensteyn	Sr. Vulnerability Researcher
Third Party Security Risk Representative	@tdilbeck	Ty Dilbeck	Security Risk Manager
Governance and Field Security Representative	@jlongo_gitlab	Joseph Longo	Governance and Field Security Manager
Security Compliance Representative	@kbray	Ken Bray	Sr. Security Compliance Engineer (Dedicated Markets)
Security Compliance Representative	@lcoleman	Liz Coleman	Security Compliance Manager (Commercial)
Security Automation Representative	@agroleau	Alexander Groleau	Senior Security Engineering Manager (Automation)
Security Automation Representative	@imand3r	Ian Anderson	Staff Security Engineer (Automation)
Application Security Representative	@greg	Greg Myers	Security Engineer (Application Security)
Solutions Architecture Representative / Rapid Prototyping Team Member	@bartzhang	Bart Zhang	Channel Solutions Architect
Product Marketing Representative	@laurenaalves	Laurena Alves	Senior Product Marketing Manager
Developer Relations Representative	@johncoghlan	John Coghlan	Senior Manager, Developer Evangelism
Privacy Representative	@emccrann	Eugene McCrann	Lead Legal Counsel, Privacy
Quality Engineering Representative	@at.ramya	Ramya Authappan	Engineering Manager, Quality, Dev & Analytics Section
Infrastructure	@lmcandrew	Liam McAndrew	Engineering Manager, Scalability Frameworks
Infrastructure	@igorwwwwwwwwwwwwwwwwwwww	Igor Wiedler	Staff SRE, Scalability Frameworks
Infrastructure	@mbursi	Michele Bursi	Engineering Manager, Delivery System
Support	@ralfaro	Ronnie Alphero	Support Engineering Manager
Enablement	@cs.wang	Christopher Wang	Sr. Manager, Enablement (Sales Development)

Engineering Groups

We currently have two core AI Development groups at GitLab: AI Enablement group and AI Assisted group.

AI Assisted group

The AI Assisted group helps all product groups to match the right model(s) and AI/ML-based techniques to the user problem they must solve. They do that by evaluating, building, training, and tuning many of the models GitLab uses as well as by proactively sharing AI resources and experience. Today, they also directly build and maintain some user-facing AI features.

AI Assisted group develops in-house AI features that run natively within GitLab infrastructure. The group develops these models to meet capability, quality, customizability, privacy, and cost requirements. These components include an inference engine, abstraction layer, and models.
The custom-built models help in use cases when there is a need to train models on customer-proprietary data (like all merge requests and commits for a customer) and when 3rd party models do meet our needs.
Their currently released features are code suggestions which is currently in customer beta and suggested reviewer which is GA.
This group can help evaluate models for functional correctness and model perplexity based on metrics and (often large) benchmark datasets, which is a more statistical evaluation than manual testing. This can help determine the most quality model for a feature's use-case.
They work in many languages, including Ruby on Rails, Golang, Python (for machine learning and data science), and Typescript (for the VS Code Plugin). The group comprises of ML Scientistists, MLOps Engineers , ML Infrastructure Engineers, and Fullstack engineers.

You can contact this group via Slack in #g_ai_assisted. View their issue board here. To see who is engaged on this effort please see here.

AI Enablement

AI Enablement exposes AI services and the underlying models (third party or native GitLab models) to all product groups.

The AI Enablement group enables the rest of the development department to build AI features through the abstraction layer.
The abstraction layer supports OpenAI and is being extended to support equivalent Google AI functionality. Other commercial, open-source, and GitLab custom-built models are also being considered.
This group empowers other groups to evaluate models via manual human testing, through the Experimentation API.
This group works with Ruby on Rails as they make it easy for the GitLab product to add AI functionality through the gitlab/gitlab-org repo.

You can contact this group via Slack in #ai_enablement_group. View their issue board here.

AI Engineering Allocation

Because of the dynamic nature of the AI work and folks to be engaged, we are putting the AI work under an Engineering Allocation. This means that assignments may change rapidly as focus and priorities shift. Current focus is on Code Suggestions adoption.

Name	Role	Area of Work
Alexandru Croitor	Senior Backend Engineer	AI Enablement
George Koltsov	Senior Backend Engineer	AI Enablement
Gosia Ksionek	Staff Backend Engineer	AI Enablement
Nicolas Dular	Senior Backend Engineer	AI Enablement
Denys Mishunov	Staff Frontend Engineer	AI Enablement
Patrick Bajao	Senior Backend Engineer	AI Enablement
Bojan Marjanović	Senior Backend Engineer	AI Enablement
Jan Provaznik	Staff Backend Engineer	AI Enablement
Daniel Tian	Senior Frontend Engineer	Threat Insights
Gregory Havenga	Backend Engineer	Threat Insights
Kerri Miller	Staff Backend Engineer	Code Review
Stanislav Lashmanov	Senior Frontend Engineer	Code Review
Pavel Shutsin	Senior Backend Engineer	Plan:Optimize
Simon Knox	Senior Frontend Engineer	Plan:Project Management
Nikola Milojevic	Senior Backend Engineer	Application Performance
Aleksei Lipniagov	Senior Backend Engineer	Application Performance
Matthias Käppler	Staff Backend Engineer	Application Performance
Roy Zwambag	Backend Engineer	Application Performance
Dmitry Gruzd	Staff Backend Engineer	Global Search
Terri Chu	Senior Backend Engineer	Global Search
Madelein van Niekerk	Backend Engineer	Global Search
John Mason	Senior Backend Engineer	Global Search
Matt Kasa	Senior Backend Engineer	Database
Igor Drozdov	Staff Backend Engineer	Source Code
Patrick Cyiza	Backend Engineer	Source Code
Natalia Radina	Frontend Engineer	Source Code
Allison Browne	Senior Backend Engineer	Verify:Pipeline Execution
Andrei Zubov	Senior Frontend Engineer	Deploy:Environments