The following page may contain information related to upcoming products, features and functionality. It is important to note that the information presented is for informational purposes only, so please do not rely on the information for purchasing or planning purposes. Just like with all projects, the items mentioned on the page are subject to change or delay, and the development, release, and timing of any products, features or functionality remain at the sole discretion of GitLab Inc.
GitLab is embracing AI/ML technologies within the software development lifecycle, as the most comprehensive AI-powered DevSecOps platform. Since mid 2021, We've been leveraging AI/ML technologies to enrich features on our platform. We're calling these AI-powered capabilities, GitLab Duo.
The name GitLab Duo is rooted in You + GitLab AI = the AI dynamic duo. GitLab Duo goes beyond just being an AI pair programmer: It is an expanding toolbox of features integrated into the DevSecOps Platform to help teams across the entire software development environment become more efficient.
Duo improves team collaboration and reduces the security and compliance risks of AI adoption by bringing the entire software development lifecycle into a single AI-powered application. At GitLab, we believe everyone can contribute. By bringing GitLab Duo capabilities to every persona who uses GitLab, everyone can benefit from AI-powered workflows and organizations can ship secure software faster.
As we continue building GitLab Duo, there are some high level goals that drive our development process.
AI-powered workflows
We want GitLab Duo to be as knowledgeable as your most seasoned and tenured employee. That person who you can ask anything to and they are an encyclopedia of knowledge. We don't want to replace that person, but instead help scale them, to every employee in your organization. GitLab Duo will help everyone answer their own questions, learn on the fly, and become more efficient.
GitLab can't do this on our own. While we are working to allow Duo to access data and information across the software development lifecycle, we also rely on our third-party AI model vendors to provide widely knowledgeable foundation models. Together general knowledge and GitLab specific data about your software creates an AI-assistant that truly knows all.
What's an assistant, if not always at your side, ready to help at a moments notice. We're building GitLab Duo to meet you wherever you work: the GitLab web UI, the WebIDE, your local IDE, and even your CLI. Infusing the software development lifecycle with AI-powered features means Duo is primed and ready to help, from summarizing content, generating code, reviewing your code, troubleshooting failed CI jobs, or even resolving vulnerabilities. You can do more, faster, with Duo at your side wherever your software development journey takes you.
It's amazing to have a helpful assistant, but not if they are going to tell everyone all your deep dark secrets. GitLab Duo is designed to be private by default and secure. Leveraging modern security techniques, all data in encrypted in transit and at rest with GitLab Duo. Further we have worked with our third-party AI vendors to ensure they do not retain your data nor use it to train AI models. Your data is yours. Period.
We take Duo a step further than most other AI assistant solutions, Duo can function in an offline/air-gapped environment with Duo Enterprise, allowing organizations to host their own models within their own networks to power Duo functionality. Learn more about self-hosted models.
Learn more about Duo data privacy
The AI-powered stage consists of the following product led groups:
We're actively building many AI-powered features into GitLab Duo, some of our upcoming milestones include:
The wider AI industry is moving at light speed, and so are we. We are quickly building to keep up with the rapid innovations in the wider AI/ML market improving our existing Duo capabilities but also introducing new ones.
You can keep up with our latest releases by following our AI Features documentation
Major achievements include:
Major achievements include:
GitLab acquires UnReview as it looks to bring more ML tools to its platform
Integrating UnReview’s technology into the GitLab platform marks our first step in building GitLab’s AI Assisted features for DevOps.
We are currently actively working on an ML model that automatically labels GitLab internal issues based on issue content. You'll see GitLab issues with the automation:ml label that have been automatically labeled by our model. You can also provide training feedback to the model if it is incorrect by applying the automation:ml wrong label. GitLab team members can view a feed of these issues with probability data in Slack in the #feed-tanuki-stan channel.
We pursued this feature first as a way to get a data science workload working within GitLab's existing CI/CD as well as running on top of production GitLab data and interacting with the GitLab data model. This will set the foundation for work in our MLOps group and our other AI Assisted categories listed above.
Based on GitLab’s 2023 What's Next in DevSecOps survey,
These statistics validate the importance of GitLab’s AI Assisted features for DevOps, and integrating automation and machine learning technology like UnReview into the GitLab platform.
Industry analyst research into successful operationalization of machine learning outlines the many challenges organizations face by adopting point solution technologies. This is contrasted with the business value provided by integrating AI Assisted features, DataOps, MLOps, and ModelOps into existing DevOps processes.
"With the rapid increase in cloud adoption, spurred by the COVID-19 pandemic, we’re seeing increased demand for cloud-enabled DevOps solutions," said Jim Mercer, research director DevOps and DevSecOps at IDC. "DevOps teams who can capitalize on cloud solutions that provide innovative technologies, such as machine learning, to remove friction from the DevOps pipeline while optimizing developer productivity are better positioned to improve code quality and security driving improved business outcomes."
GitLab team members can learn more in our internal handbook:
Last Reviewed: 2024-10-05
Last Updated: 2024-10-05