[{"data":1,"prerenderedAt":836},["ShallowReactive",2],{"/en-us/blog/inside-look-how-gitlabs-test-platform-team-validates-ai-features":3,"navigation-en-us":45,"banner-en-us":455,"footer-en-us":465,"blog-post-authors-en-us-Mark Lapierre|Vincy Wilson":706,"blog-related-posts-en-us-inside-look-how-gitlabs-test-platform-team-validates-ai-features":732,"blog-promotions-en-us":774,"next-steps-en-us":826},{"id":4,"title":5,"authorSlugs":6,"body":9,"categorySlug":10,"config":11,"content":15,"description":9,"extension":31,"isFeatured":13,"meta":32,"navigation":13,"path":33,"publishedDate":22,"seo":34,"stem":39,"tagSlugs":40,"__hash__":44},"blogPosts/en-us/blog/inside-look-how-gitlabs-test-platform-team-validates-ai-features.yml","Inside Look How Gitlabs Test Platform Team Validates Ai Features",[7,8],"mark-lapierre","vincy-wilson",null,"ai-ml",{"slug":12,"featured":13,"template":14},"inside-look-how-gitlabs-test-platform-team-validates-ai-features",true,"BlogPost",{"title":16,"description":17,"authors":18,"heroImage":21,"date":22,"body":23,"category":10,"tags":24},"Inside look: How GitLab's Test Platform team validates AI features","Learn how we continuously analyze AI feature performance, including testing latency worldwide, and get to know our new AI continuous analysis tool.",[19,20],"Mark Lapierre","Vincy Wilson","https://res.cloudinary.com/about-gitlab-com/image/upload/v1750099033/Blog/Hero%20Images/Blog/Hero%20Images/blog-image-template-1800x945%20%2811%29_78Dav6FR9EGjhebHWuBVan_1750099033422.png","2024-06-03","AI is increasingly becoming a centerpiece of software development - many companies are integrating it throughout their DevSecOps workflows to improve productivity and increase efficiency. Because of this now-critical role, AI features should be tested and analyzed on an ongoing basis. In this article, we take you behind the scenes to learn how [GitLab's Test Platform team](https://handbook.gitlab.com/handbook/engineering/infrastructure/test-platform/) does this for [GitLab Duo](https://about.gitlab.com/gitlab-duo-agent-platform/) features by conducting performance validation, functional readiness, and continuous analysis across GitLab versions. With this three-pronged approach, GitLab aims to ensure that GitLab Duo features are performing optimally for our customers.\n\n> Discover the future of AI-driven software development with our GitLab 17 virtual launch event. [Watch today!](https://about.gitlab.com/eighteen/)\n\n## AI and testing\n\nAI's non-deterministic nature, where the same input can produce different outputs, makes ensuring a great user experience a challenge. So, when we integrated AI deep into the GitLab DevSecOps Platform, we had to adapt to our best practices to address this challenge.\nThe [Test Platform team's mission ](https://handbook.gitlab.com/handbook/engineering/infrastructure/test-platform/) is to help enable the successful development and deployment of high-quality software applications with continuous analysis and efficiency to help ensure customer satisfaction. The key to achieving this is by delivering tools that help increase standardization, repeatability, and test consistency.\nApplying this to GitLab Duo, our AI suite of tools to power DevSecOps workflows, means being able to continuously analyze its performance and identify opportunities for improvement. Our goal is to gain clear, actionable insights that will help us to enhance GitLab Duo's capabilities and, as a result, better meet our customers' needs.\n## The need for continuous analysis of AI\n\nTo continuously assess GitLab Duo, we needed a mechanism for analyzing feature performance across releases. Therefore, we created an AI continuous analysis tool to automate the collection and analysis of data to achieve this.\n![diagram of how the AI continuous analysis tool works](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750099041/Blog/Content%20Images/Blog/Content%20Images/image1_aHR0cHM6_1750099041503.png)\n\n\u003Ccenter>\u003Ci>How the AI continuous analysis tool works\u003C/i>\u003C/center>\n\n### Building the AI continuous analysis tool\n\nTo gain detailed, user-centric insights, we needed to gather data in the appropriate context – in this case, the integrated development environment (IDE), as it is where most of our users access GitLab Duo. We narrowed this down further by opting for the Visual Studio Code IDE, a popular choice within our community. Once the environment was chosen, we automated entering code prompts and recording the provided suggestions. The interactions with the IDE are handled by the [WebdriverIO VSCode service](https://github.com/webdriverio-community/wdio-vscode-service), and CI operations are handled through [GitLab CI/CD](https://docs.gitlab.com/ee/ci/). This automation significantly scaled up data collection and eliminated repetitive tasks for GitLab team members. To start, we have focused on measuring the performance of GitLab Duo Code Suggestions, but plan to expand to other GitLab AI features in the future.\n\n### Analyzing the data\n\nAt the core of our AI continuous analysis tool is a mechanism for collecting and analyzing code suggestions. This involves automatically entering code prompts, recording the suggestions provided, and logging timestamps of relevant events. We measure the time from when the tool provides an input until a suggestion is displayed in the UI. In addition, we record the logs created by the IDE, which report the time it took for each suggestion response to be received. With this data, we can compare the latency of suggestions in terms of how long it takes the backend AI service to send a response to the IDE, and how long it takes for the IDE to display the suggestion for the user. We then can compare latency and other metrics of GitLab Duo features across multiple releases. The GitLab platform has the ability to analyze [code quality](https://docs.gitlab.com/ee/ci/testing/code_quality.html) and [application security](https://docs.gitlab.com/ee/user/application_security/), so we leverage these capabilities to enable the AI continuous analysis tool to analyze the quality and security of the suggestions provided by GitLab Duo.\n\n### Improving AI-driven suggestions\n\nOnce the collected data is analyzed, the tool automatically generates a single report summarizing the results. The report includes key statistics (e.g., mean latency and/or latency at various percentiles), descriptions of notable differences or patterns, links to raw data, and CI/CD pipeline logs and artifacts. The tool also records a video of each prompt and suggestion, which allows us to review specific cases where differences are highlighted. This creates an opportunity for the UX researchers and development teams to take action on the insights gained, helping to improve the overall user experience and system performance.\n\nThe tool is at an early stage of development, but it's already helped us to improve the experience for GitLab Duo Code Suggestions users. Moving forward, we plan to expand our tool’s capabilities, incorporate more metrics and consume and provide input to our [Centralized Evaluation Framework](https://docs.gitlab.com/development/ai_features/ai_evaluation_guidelines/), which validates AI models, to enhance our continuous analysis further.\n\n## Performance validation\n\nAs AI has become integral to GitLab's offerings, optimizing the performance of AI-driven features is essential. Our performance tests aim to evaluate and monitor the performance of our GitLab components, which interact with AI service backends. While we can monitor the performance of these external services as part of our production environment's observability, we cannot control them. Thus, including third-party services in our performance testing would be expensive and yield limited benefits. Although third-party AI providers contribute to overall latency, the latency attributable to GitLab components is still important to check. We aim to detect changes that might lead to performance degradation by monitoring GitLab components.\n### Building AI performance validation test environment\n\nIn our AI test environments, the [AI Gateway](https://docs.gitlab.com/ee/architecture/blueprints/ai_gateway/#summary), which is a stand-alone service to give access to AI features to GitLab users, has been configured to return mocked responses, enabling us to test the performance of AI-powered features without interacting with third-party AI service providers. We conduct AI performance tests on [reference architecture environments of various sizes](https://docs.gitlab.com/ee/administration/reference_architectures/). Additionally, we evaluate new tests in their own isolated environment before they're added to the larger environments.\n\n### Testing multi-regional latency\n\nMulti-regional latency tests need to be run from various geolocations to validate that requests are being served from a suitable location close to the source of the request. We do this today with the use of the [GitLab Environment Toolkit](https://gitlab.com/gitlab-org/gitlab-environment-toolkit). The toolkit provisions an environment in the identified region to test (note: both the AI Gateway and the provisioned environment are in the same region), then uses the [GitLab Performance Tool](https://gitlab.com/gitlab-org/quality/performance) to run tests to measure time to first byte (TTFB). TTFB is our way of measuring time to the first part of the response being rendered, which contributes to the perceived latency that a customer experiences. To account for this measurement, our tests have a check to help ensure that the [response itself isn't empty](https://gitlab.com/gitlab-org/quality/performance/-/blob/cee8bef023e590e6ca75828e49f5c7c596581e06/k6/tests/experimental/api_v4_code_suggestions_generation_streaming.js#L70).\nOur tests are expanding further to continue to measure perceived latency from a customer’s perspective. We have captured a set of baseline response times that indicate how a specific set of regions performed when the test environment was in a known good state. These baselines allow us to compare subsequent environment updates and other regions to this known state to evaluate the impact of changes. These baseline measurements can be updated after major updates to ensure they stay relevant in the future.\nNote: As of this article's publication date, we have AI Gateway deployments across the U.S., Europe, and Asia. To learn more, visit our [handbook page](https://handbook.gitlab.com/handbook/engineering/development/data-science/ai-powered/ai-framework/#-aigw-region-deployments).\n\n## Functionality\n\nTo help continuously enable customers to confidently leverage AI reliably, we must continuously work to ensure our AI features function as expected.\n\n### Unit and integration tests\n\nFeatures that leverage AI models still require rigorous automated tests, which help engineers develop new features and changes confidently. However, since AI features can involve integrating with third-party AI providers, we must be careful to stub any external API calls to help ensure our tests are fast and reliable.\n\nFor a comprehensive look at testing at GitLab, look at our [testing standards and style guidelines](https://docs.gitlab.com/ee/development/testing_guide/).\n### End-to-end tests\nEnd-to-end testing is a strategy for checking whether the application works as expected across the entire software stack and architecture. We've implemented it in two ways for GitLab Duo testing: using real AI-generated responses and mock-generated AI responses.\n\n![validating features - image 2](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750099041/Blog/Content%20Images/Blog/Content%20Images/image2_aHR0cHM6_1750099041504.png)\n\n\u003Ccenter>\u003Ci>End-to-end test workflow\u003C/i>\u003C/center>\n\n#### Using real AI-generated responses\n\nAlthough costly, end-to-end tests are important to help ensure the entire user experience functions as expected. Since AI models are non-deterministic, end-to-end test assertions for validating real AI-generated responses should be loose enough to help ensure the feature functions without relying on a response that may change. This might mean an assertion that checks for some response with no errors or for a response we are certain to receive.\n\nAI-driven functionality is not accessible only from within the GitLab application, so we must also consider user workflows for other applications that leverage these features. For example, to cover the use case of a developer requesting code suggestions in [IntelliJ IDEA](https://www.jetbrains.com/idea/) using the GitLab Duo plugin, we need to drive the IntelliJ application to simulate a user workflow. Similarly, to ensure that the GitLab Duo Chat experience is consistent in VS Code, we must drive the VS Code application and exercise the GitLab Workflow extension. Working to ensure these workflows are covered helps us maintain a consistently great developer experience across all GitLab products.\n#### Using mock AI-generated responses\n\nIn addition to end-to-end tests using real AI-generated responses, we run some end-to-end tests against test environments configured to return mock responses. This allows us to verify changes to GitLab code and components that don’t depend on responses generated by an AI model more frequently.\n\n> For a closer look at end-to-end testing, read our [end-to-end testing guide](https://docs.gitlab.com/ee/development/testing_guide/end_to_end/).\n### Exploratory testing and dogfooding\n\nAI features are built by humans for humans. At GitLab, exploratory testing and dogfooding greatly benefit us. GitLab team members are passionate about what features get shipped, and insights from internal usage are invaluable in shaping the direction of AI features.\n\n[Exploratory testing](https://about.gitlab.com/topics/devops/devops-test-automation/#test-automation-stages) allows the team to creatively exercise features to help ensure edge case bugs are identified and resolved. Dogfooding encourages team members to use AI features in their daily workflows, which helps us identify realistic issues from realistic users. For a comprehensive look at how we dogfood AI features, look at [Developing GitLab Duo: How we are dogfooding our AI features](https://about.gitlab.com/blog/developing-gitlab-duo-how-we-are-dogfooding-our-ai-features/).\n\n## Get started with GitLab Duo\nHopefully this article gives you insight into how we are validating AI features at GitLab. We have integrated our team's process into our overall development as we iterate on GitLab Duo features. We encourage you to try GitLab Duo in your organization and reap the benefits of AI-powered workflows.\n\n> Start a [free trial of GitLab Duo](https://about.gitlab.com/gitlab-duo-agent-platform/#free-trial) today!\n\n_Members of the GitLab Test Platform team contributed to this article._\n",[25,26,27,28,29,30],"AI/ML","features","DevSecOps platform","inside GitLab","testing","performance","yml",{},"/en-us/blog/inside-look-how-gitlabs-test-platform-team-validates-ai-features",{"title":16,"description":17,"ogTitle":16,"ogDescription":17,"noIndex":35,"ogImage":21,"ogUrl":36,"ogSiteName":37,"ogType":38,"canonicalUrls":36},false,"https://about.gitlab.com/blog/inside-look-how-gitlabs-test-platform-team-validates-ai-features","https://about.gitlab.com","article","en-us/blog/inside-look-how-gitlabs-test-platform-team-validates-ai-features",[41,26,42,43,29,30],"aiml","devsecops-platform","inside-gitlab","w7yY-5fTu-Jo0AqrTCN9Waj2R-nml9uZjA1jfDReAiQ",{"data":46},{"logo":47,"freeTrial":52,"sales":57,"login":62,"items":67,"search":375,"minimal":406,"duo":425,"switchNav":434,"pricingDeployment":445},{"config":48},{"href":49,"dataGaName":50,"dataGaLocation":51},"/","gitlab logo","header",{"text":53,"config":54},"Get free trial",{"href":55,"dataGaName":56,"dataGaLocation":51},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com&glm_content=default-saas-trial/","free trial",{"text":58,"config":59},"Talk to sales",{"href":60,"dataGaName":61,"dataGaLocation":51},"/sales/","sales",{"text":63,"config":64},"Sign in",{"href":65,"dataGaName":66,"dataGaLocation":51},"https://gitlab.com/users/sign_in/","sign in",[68,95,190,195,296,356],{"text":69,"config":70,"cards":72},"Platform",{"dataNavLevelOne":71},"platform",[73,79,87],{"title":69,"description":74,"link":75},"The intelligent orchestration platform for DevSecOps",{"text":76,"config":77},"Explore our Platform",{"href":78,"dataGaName":71,"dataGaLocation":51},"/platform/",{"title":80,"description":81,"link":82},"GitLab Duo Agent Platform","Agentic AI for the entire software lifecycle",{"text":83,"config":84},"Meet GitLab Duo",{"href":85,"dataGaName":86,"dataGaLocation":51},"/gitlab-duo-agent-platform/","gitlab duo agent platform",{"title":88,"description":89,"link":90},"Why GitLab","See the top reasons enterprises choose GitLab",{"text":91,"config":92},"Learn more",{"href":93,"dataGaName":94,"dataGaLocation":51},"/why-gitlab/","why gitlab",{"text":96,"left":13,"config":97,"link":99,"lists":103,"footer":172},"Product",{"dataNavLevelOne":98},"solutions",{"text":100,"config":101},"View all Solutions",{"href":102,"dataGaName":98,"dataGaLocation":51},"/solutions/",[104,128,151],{"title":105,"description":106,"link":107,"items":112},"Automation","CI/CD and automation to accelerate deployment",{"config":108},{"icon":109,"href":110,"dataGaName":111,"dataGaLocation":51},"AutomatedCodeAlt","/solutions/delivery-automation/","automated software delivery",[113,117,120,124],{"text":114,"config":115},"CI/CD",{"href":116,"dataGaLocation":51,"dataGaName":114},"/solutions/continuous-integration/",{"text":80,"config":118},{"href":85,"dataGaLocation":51,"dataGaName":119},"gitlab duo agent platform - product menu",{"text":121,"config":122},"Source Code Management",{"href":123,"dataGaLocation":51,"dataGaName":121},"/solutions/source-code-management/",{"text":125,"config":126},"Automated Software Delivery",{"href":110,"dataGaLocation":51,"dataGaName":127},"Automated software delivery",{"title":129,"description":130,"link":131,"items":136},"Security","Deliver code faster without compromising security",{"config":132},{"href":133,"dataGaName":134,"dataGaLocation":51,"icon":135},"/solutions/application-security-testing/","security and compliance","ShieldCheckLight",[137,141,146],{"text":138,"config":139},"Application Security Testing",{"href":133,"dataGaName":140,"dataGaLocation":51},"Application security testing",{"text":142,"config":143},"Software Supply Chain Security",{"href":144,"dataGaLocation":51,"dataGaName":145},"/solutions/supply-chain/","Software supply chain security",{"text":147,"config":148},"Software Compliance",{"href":149,"dataGaName":150,"dataGaLocation":51},"/solutions/software-compliance/","software compliance",{"title":152,"link":153,"items":158},"Measurement",{"config":154},{"icon":155,"href":156,"dataGaName":157,"dataGaLocation":51},"DigitalTransformation","/solutions/visibility-measurement/","visibility and measurement",[159,163,167],{"text":160,"config":161},"Visibility & Measurement",{"href":156,"dataGaLocation":51,"dataGaName":162},"Visibility and Measurement",{"text":164,"config":165},"Value Stream Management",{"href":166,"dataGaLocation":51,"dataGaName":164},"/solutions/value-stream-management/",{"text":168,"config":169},"Analytics & Insights",{"href":170,"dataGaLocation":51,"dataGaName":171},"/solutions/analytics-and-insights/","Analytics and insights",{"title":173,"items":174},"GitLab for",[175,180,185],{"text":176,"config":177},"Enterprise",{"href":178,"dataGaLocation":51,"dataGaName":179},"/enterprise/","enterprise",{"text":181,"config":182},"Small Business",{"href":183,"dataGaLocation":51,"dataGaName":184},"/small-business/","small business",{"text":186,"config":187},"Public Sector",{"href":188,"dataGaLocation":51,"dataGaName":189},"/solutions/public-sector/","public sector",{"text":191,"config":192},"Pricing",{"href":193,"dataGaName":194,"dataGaLocation":51,"dataNavLevelOne":194},"/pricing/","pricing",{"text":196,"config":197,"link":199,"lists":203,"feature":283},"Resources",{"dataNavLevelOne":198},"resources",{"text":200,"config":201},"View all resources",{"href":202,"dataGaName":198,"dataGaLocation":51},"/resources/",[204,237,255],{"title":205,"items":206},"Getting started",[207,212,217,222,227,232],{"text":208,"config":209},"Install",{"href":210,"dataGaName":211,"dataGaLocation":51},"/install/","install",{"text":213,"config":214},"Quick start guides",{"href":215,"dataGaName":216,"dataGaLocation":51},"/get-started/","quick setup checklists",{"text":218,"config":219},"Learn",{"href":220,"dataGaLocation":51,"dataGaName":221},"https://university.gitlab.com/","learn",{"text":223,"config":224},"Product documentation",{"href":225,"dataGaName":226,"dataGaLocation":51},"https://docs.gitlab.com/","product documentation",{"text":228,"config":229},"Best practice videos",{"href":230,"dataGaName":231,"dataGaLocation":51},"/getting-started-videos/","best practice videos",{"text":233,"config":234},"Integrations",{"href":235,"dataGaName":236,"dataGaLocation":51},"/integrations/","integrations",{"title":238,"items":239},"Discover",[240,245,250],{"text":241,"config":242},"Customer success stories",{"href":243,"dataGaName":244,"dataGaLocation":51},"/customers/","customer success stories",{"text":246,"config":247},"Blog",{"href":248,"dataGaName":249,"dataGaLocation":51},"/blog/","blog",{"text":251,"config":252},"Remote",{"href":253,"dataGaName":254,"dataGaLocation":51},"https://handbook.gitlab.com/handbook/company/culture/all-remote/","remote",{"title":256,"items":257},"Connect",[258,263,268,273,278],{"text":259,"config":260},"GitLab Services",{"href":261,"dataGaName":262,"dataGaLocation":51},"/services/","services",{"text":264,"config":265},"Community",{"href":266,"dataGaName":267,"dataGaLocation":51},"/community/","community",{"text":269,"config":270},"Forum",{"href":271,"dataGaName":272,"dataGaLocation":51},"https://forum.gitlab.com/","forum",{"text":274,"config":275},"Events",{"href":276,"dataGaName":277,"dataGaLocation":51},"/events/","events",{"text":279,"config":280},"Partners",{"href":281,"dataGaName":282,"dataGaLocation":51},"/partners/","partners",{"backgroundColor":284,"textColor":285,"text":286,"image":287,"link":291},"#2f2a6b","#fff","Insights for the future of software development",{"altText":288,"config":289},"the source promo card",{"src":290},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758208064/dzl0dbift9xdizyelkk4.svg",{"text":292,"config":293},"Read the latest",{"href":294,"dataGaName":295,"dataGaLocation":51},"/the-source/","the source",{"text":297,"config":298,"lists":300},"Company",{"dataNavLevelOne":299},"company",[301],{"items":302},[303,308,314,316,321,326,331,336,341,346,351],{"text":304,"config":305},"About",{"href":306,"dataGaName":307,"dataGaLocation":51},"/company/","about",{"text":309,"config":310,"footerGa":313},"Jobs",{"href":311,"dataGaName":312,"dataGaLocation":51},"/jobs/","jobs",{"dataGaName":312},{"text":274,"config":315},{"href":276,"dataGaName":277,"dataGaLocation":51},{"text":317,"config":318},"Leadership",{"href":319,"dataGaName":320,"dataGaLocation":51},"/company/team/e-group/","leadership",{"text":322,"config":323},"Team",{"href":324,"dataGaName":325,"dataGaLocation":51},"/company/team/","team",{"text":327,"config":328},"Handbook",{"href":329,"dataGaName":330,"dataGaLocation":51},"https://handbook.gitlab.com/","handbook",{"text":332,"config":333},"Investor relations",{"href":334,"dataGaName":335,"dataGaLocation":51},"https://ir.gitlab.com/","investor relations",{"text":337,"config":338},"Trust Center",{"href":339,"dataGaName":340,"dataGaLocation":51},"/security/","trust center",{"text":342,"config":343},"AI Transparency Center",{"href":344,"dataGaName":345,"dataGaLocation":51},"/ai-transparency-center/","ai transparency center",{"text":347,"config":348},"Newsletter",{"href":349,"dataGaName":350,"dataGaLocation":51},"/company/contact/#contact-forms","newsletter",{"text":352,"config":353},"Press",{"href":354,"dataGaName":355,"dataGaLocation":51},"/press/","press",{"text":357,"config":358,"lists":359},"Contact us",{"dataNavLevelOne":299},[360],{"items":361},[362,365,370],{"text":58,"config":363},{"href":60,"dataGaName":364,"dataGaLocation":51},"talk to sales",{"text":366,"config":367},"Support portal",{"href":368,"dataGaName":369,"dataGaLocation":51},"https://support.gitlab.com","support portal",{"text":371,"config":372},"Customer portal",{"href":373,"dataGaName":374,"dataGaLocation":51},"https://customers.gitlab.com/customers/sign_in/","customer portal",{"close":376,"login":377,"suggestions":384},"Close",{"text":378,"link":379},"To search repositories and projects, login to",{"text":380,"config":381},"gitlab.com",{"href":65,"dataGaName":382,"dataGaLocation":383},"search login","search",{"text":385,"default":386},"Suggestions",[387,389,393,395,399,403],{"text":80,"config":388},{"href":85,"dataGaName":80,"dataGaLocation":383},{"text":390,"config":391},"Code Suggestions (AI)",{"href":392,"dataGaName":390,"dataGaLocation":383},"/solutions/code-suggestions/",{"text":114,"config":394},{"href":116,"dataGaName":114,"dataGaLocation":383},{"text":396,"config":397},"GitLab on AWS",{"href":398,"dataGaName":396,"dataGaLocation":383},"/partners/technology-partners/aws/",{"text":400,"config":401},"GitLab on Google Cloud",{"href":402,"dataGaName":400,"dataGaLocation":383},"/partners/technology-partners/google-cloud-platform/",{"text":404,"config":405},"Why GitLab?",{"href":93,"dataGaName":404,"dataGaLocation":383},{"freeTrial":407,"mobileIcon":412,"desktopIcon":417,"secondaryButton":420},{"text":408,"config":409},"Start free trial",{"href":410,"dataGaName":56,"dataGaLocation":411},"https://gitlab.com/-/trials/new/","nav",{"altText":413,"config":414},"Gitlab Icon",{"src":415,"dataGaName":416,"dataGaLocation":411},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203874/jypbw1jx72aexsoohd7x.svg","gitlab icon",{"altText":413,"config":418},{"src":419,"dataGaName":416,"dataGaLocation":411},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203875/gs4c8p8opsgvflgkswz9.svg",{"text":421,"config":422},"Get Started",{"href":423,"dataGaName":424,"dataGaLocation":411},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com/get-started/","get started",{"freeTrial":426,"mobileIcon":430,"desktopIcon":432},{"text":427,"config":428},"Learn more about GitLab Duo",{"href":85,"dataGaName":429,"dataGaLocation":411},"gitlab duo",{"altText":413,"config":431},{"src":415,"dataGaName":416,"dataGaLocation":411},{"altText":413,"config":433},{"src":419,"dataGaName":416,"dataGaLocation":411},{"button":435,"mobileIcon":440,"desktopIcon":442},{"text":436,"config":437},"/switch",{"href":438,"dataGaName":439,"dataGaLocation":411},"#contact","switch",{"altText":413,"config":441},{"src":415,"dataGaName":416,"dataGaLocation":411},{"altText":413,"config":443},{"src":444,"dataGaName":416,"dataGaLocation":411},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1773335277/ohhpiuoxoldryzrnhfrh.png",{"freeTrial":446,"mobileIcon":451,"desktopIcon":453},{"text":447,"config":448},"Back to pricing",{"href":193,"dataGaName":449,"dataGaLocation":411,"icon":450},"back to pricing","GoBack",{"altText":413,"config":452},{"src":415,"dataGaName":416,"dataGaLocation":411},{"altText":413,"config":454},{"src":419,"dataGaName":416,"dataGaLocation":411},{"title":456,"button":457,"config":462},"See how agentic AI transforms software delivery",{"text":458,"config":459},"Watch GitLab Transcend now",{"href":460,"dataGaName":461,"dataGaLocation":51},"/events/transcend/virtual/","transcend event",{"layout":463,"icon":464,"disabled":13},"release","AiStar",{"data":466},{"text":467,"source":468,"edit":474,"contribute":479,"config":484,"items":489,"minimal":695},"Git is a trademark of Software Freedom Conservancy and our use of 'GitLab' is under license",{"text":469,"config":470},"View page source",{"href":471,"dataGaName":472,"dataGaLocation":473},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/","page source","footer",{"text":475,"config":476},"Edit this page",{"href":477,"dataGaName":478,"dataGaLocation":473},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/content/","web ide",{"text":480,"config":481},"Please contribute",{"href":482,"dataGaName":483,"dataGaLocation":473},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/CONTRIBUTING.md/","please contribute",{"twitter":485,"facebook":486,"youtube":487,"linkedin":488},"https://twitter.com/gitlab","https://www.facebook.com/gitlab","https://www.youtube.com/channel/UCnMGQ8QHMAnVIsI3xJrihhg","https://www.linkedin.com/company/gitlab-com",[490,537,590,634,661],{"title":191,"links":491,"subMenu":506},[492,496,501],{"text":493,"config":494},"View plans",{"href":193,"dataGaName":495,"dataGaLocation":473},"view plans",{"text":497,"config":498},"Why Premium?",{"href":499,"dataGaName":500,"dataGaLocation":473},"/pricing/premium/","why premium",{"text":502,"config":503},"Why Ultimate?",{"href":504,"dataGaName":505,"dataGaLocation":473},"/pricing/ultimate/","why ultimate",[507],{"title":508,"links":509},"Contact Us",[510,513,515,517,522,527,532],{"text":511,"config":512},"Contact sales",{"href":60,"dataGaName":61,"dataGaLocation":473},{"text":366,"config":514},{"href":368,"dataGaName":369,"dataGaLocation":473},{"text":371,"config":516},{"href":373,"dataGaName":374,"dataGaLocation":473},{"text":518,"config":519},"Status",{"href":520,"dataGaName":521,"dataGaLocation":473},"https://status.gitlab.com/","status",{"text":523,"config":524},"Terms of use",{"href":525,"dataGaName":526,"dataGaLocation":473},"/terms/","terms of use",{"text":528,"config":529},"Privacy statement",{"href":530,"dataGaName":531,"dataGaLocation":473},"/privacy/","privacy statement",{"text":533,"config":534},"Cookie preferences",{"dataGaName":535,"dataGaLocation":473,"id":536,"isOneTrustButton":13},"cookie preferences","ot-sdk-btn",{"title":96,"links":538,"subMenu":546},[539,542],{"text":27,"config":540},{"href":78,"dataGaName":541,"dataGaLocation":473},"devsecops platform",{"text":543,"config":544},"AI-Assisted Development",{"href":85,"dataGaName":545,"dataGaLocation":473},"ai-assisted development",[547],{"title":548,"links":549},"Topics",[550,555,560,565,570,575,580,585],{"text":551,"config":552},"CICD",{"href":553,"dataGaName":554,"dataGaLocation":473},"/topics/ci-cd/","cicd",{"text":556,"config":557},"GitOps",{"href":558,"dataGaName":559,"dataGaLocation":473},"/topics/gitops/","gitops",{"text":561,"config":562},"DevOps",{"href":563,"dataGaName":564,"dataGaLocation":473},"/topics/devops/","devops",{"text":566,"config":567},"Version Control",{"href":568,"dataGaName":569,"dataGaLocation":473},"/topics/version-control/","version control",{"text":571,"config":572},"DevSecOps",{"href":573,"dataGaName":574,"dataGaLocation":473},"/topics/devsecops/","devsecops",{"text":576,"config":577},"Cloud Native",{"href":578,"dataGaName":579,"dataGaLocation":473},"/topics/cloud-native/","cloud native",{"text":581,"config":582},"AI for Coding",{"href":583,"dataGaName":584,"dataGaLocation":473},"/topics/devops/ai-for-coding/","ai for coding",{"text":586,"config":587},"Agentic AI",{"href":588,"dataGaName":589,"dataGaLocation":473},"/topics/agentic-ai/","agentic ai",{"title":591,"links":592},"Solutions",[593,595,597,602,606,609,613,616,618,621,624,629],{"text":138,"config":594},{"href":133,"dataGaName":138,"dataGaLocation":473},{"text":127,"config":596},{"href":110,"dataGaName":111,"dataGaLocation":473},{"text":598,"config":599},"Agile development",{"href":600,"dataGaName":601,"dataGaLocation":473},"/solutions/agile-delivery/","agile delivery",{"text":603,"config":604},"SCM",{"href":123,"dataGaName":605,"dataGaLocation":473},"source code management",{"text":551,"config":607},{"href":116,"dataGaName":608,"dataGaLocation":473},"continuous integration & delivery",{"text":610,"config":611},"Value stream management",{"href":166,"dataGaName":612,"dataGaLocation":473},"value stream management",{"text":556,"config":614},{"href":615,"dataGaName":559,"dataGaLocation":473},"/solutions/gitops/",{"text":176,"config":617},{"href":178,"dataGaName":179,"dataGaLocation":473},{"text":619,"config":620},"Small business",{"href":183,"dataGaName":184,"dataGaLocation":473},{"text":622,"config":623},"Public sector",{"href":188,"dataGaName":189,"dataGaLocation":473},{"text":625,"config":626},"Education",{"href":627,"dataGaName":628,"dataGaLocation":473},"/solutions/education/","education",{"text":630,"config":631},"Financial services",{"href":632,"dataGaName":633,"dataGaLocation":473},"/solutions/finance/","financial services",{"title":196,"links":635},[636,638,640,642,645,647,649,651,653,655,657,659],{"text":208,"config":637},{"href":210,"dataGaName":211,"dataGaLocation":473},{"text":213,"config":639},{"href":215,"dataGaName":216,"dataGaLocation":473},{"text":218,"config":641},{"href":220,"dataGaName":221,"dataGaLocation":473},{"text":223,"config":643},{"href":225,"dataGaName":644,"dataGaLocation":473},"docs",{"text":246,"config":646},{"href":248,"dataGaName":249,"dataGaLocation":473},{"text":241,"config":648},{"href":243,"dataGaName":244,"dataGaLocation":473},{"text":251,"config":650},{"href":253,"dataGaName":254,"dataGaLocation":473},{"text":259,"config":652},{"href":261,"dataGaName":262,"dataGaLocation":473},{"text":264,"config":654},{"href":266,"dataGaName":267,"dataGaLocation":473},{"text":269,"config":656},{"href":271,"dataGaName":272,"dataGaLocation":473},{"text":274,"config":658},{"href":276,"dataGaName":277,"dataGaLocation":473},{"text":279,"config":660},{"href":281,"dataGaName":282,"dataGaLocation":473},{"title":297,"links":662},[663,665,667,669,671,673,675,679,684,686,688,690],{"text":304,"config":664},{"href":306,"dataGaName":299,"dataGaLocation":473},{"text":309,"config":666},{"href":311,"dataGaName":312,"dataGaLocation":473},{"text":317,"config":668},{"href":319,"dataGaName":320,"dataGaLocation":473},{"text":322,"config":670},{"href":324,"dataGaName":325,"dataGaLocation":473},{"text":327,"config":672},{"href":329,"dataGaName":330,"dataGaLocation":473},{"text":332,"config":674},{"href":334,"dataGaName":335,"dataGaLocation":473},{"text":676,"config":677},"Sustainability",{"href":678,"dataGaName":676,"dataGaLocation":473},"/sustainability/",{"text":680,"config":681},"Diversity, inclusion and belonging (DIB)",{"href":682,"dataGaName":683,"dataGaLocation":473},"/diversity-inclusion-belonging/","Diversity, inclusion and belonging",{"text":337,"config":685},{"href":339,"dataGaName":340,"dataGaLocation":473},{"text":347,"config":687},{"href":349,"dataGaName":350,"dataGaLocation":473},{"text":352,"config":689},{"href":354,"dataGaName":355,"dataGaLocation":473},{"text":691,"config":692},"Modern Slavery Transparency Statement",{"href":693,"dataGaName":694,"dataGaLocation":473},"https://handbook.gitlab.com/handbook/legal/modern-slavery-act-transparency-statement/","modern slavery transparency statement",{"items":696},[697,700,703],{"text":698,"config":699},"Terms",{"href":525,"dataGaName":526,"dataGaLocation":473},{"text":701,"config":702},"Cookies",{"dataGaName":535,"dataGaLocation":473,"id":536,"isOneTrustButton":13},{"text":704,"config":705},"Privacy",{"href":530,"dataGaName":531,"dataGaLocation":473},[707,720],{"id":708,"title":19,"body":9,"config":709,"content":711,"description":9,"extension":31,"meta":715,"navigation":13,"path":716,"seo":717,"stem":718,"__hash__":719},"blogAuthors/en-us/blog/authors/mark-lapierre.yml",{"template":710},"BlogAuthor",{"name":19,"config":712},{"headshot":713,"ctfId":714},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1749669066/Blog/Author%20Headshots/mark_lapierre.png","2Fnsk5H33npbli2fy9kMqu",{},"/en-us/blog/authors/mark-lapierre",{},"en-us/blog/authors/mark-lapierre","0HzPTjvC6yQJRoZypDDz_Ow6FkOfcD8aea81kGSFg7o",{"id":721,"title":20,"body":9,"config":722,"content":723,"description":9,"extension":31,"meta":727,"navigation":13,"path":728,"seo":729,"stem":730,"__hash__":731},"blogAuthors/en-us/blog/authors/vincy-wilson.yml",{"template":710},{"name":20,"config":724},{"headshot":725,"ctfId":726},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1749669069/Blog/Author%20Headshots/vincy.jpg","1iyKndVlbE3dQnxOJoSY0q",{},"/en-us/blog/authors/vincy-wilson",{},"en-us/blog/authors/vincy-wilson","LvCuCwCbFKkkdcuAkl-tE7wn13eg9fSlEk_3q8yMPIg",[733,746,761],{"content":734,"config":744},{"title":735,"description":736,"authors":737,"heroImage":739,"date":740,"body":741,"category":10,"tags":742},"GitHub Copilot's new policy for AI training is a governance wake-up call","Learn what GitHub's Copilot policy change means for regulated industries, and why GitLab's commitment to customer data privacy matters.",[738],"Allie Holland","https://res.cloudinary.com/about-gitlab-com/image/upload/v1776347152/unw3mzatkd5xyfbzcnni.png","2026-04-20","GitHub recently [announced](https://github.blog/news-insights/company-news/updates-to-github-copilot-interaction-data-usage-policy/) a significant change to how it handles data from Copilot users. Starting April 24, 2026, interaction data from Copilot Free, Pro, and Pro+ users, including inputs, outputs, code snippets, and associated context, will be used to train AI models by default, unless users actively opt out. Copilot Business and Enterprise customers are exempt under existing contract terms.\n\nFor organizations in regulated industries, including finance, healthcare, defense, and public sector, the policy shift raises questions that go beyond individual developer preferences. It forces a harder look at a question that engineering and security leaders should be asking every AI vendor in their stack: Do you train on our code? \n\nGitLab's answer is no. GitLab does not train AI models on customer code at any tier, and AI vendors are contractually prohibited from using customer inputs or outputs for their own purposes. The [GitLab AI Transparency Center](https://about.gitlab.com/ai-transparency-center/) makes that commitment auditable: a single location documenting which models power which features, how data is handled, subprocessor relationships, and data retention periods. The GitLab AI Transparency Center also lists the compliance status of each feature, including confirmation that GitLab's current AI features do not qualify as high-risk systems under the EU AI Act. It's a standard GitLab CEO Bill Staples has consistently [reiterated](https://www.linkedin.com/posts/williamstaples_gitlab-1810-agentic-ai-now-open-to-even-activity-7443280763715985408-aHxf?utm_source=share&utm_medium=member_desktop&rcm=ACoAABsu7EUBcb_a1-JHKS9RC0B5rf8Ye-5XM60) and one reflected in GitLab's mission and [Trust Center](https://trust.gitlab.com/).\n\n## What the policy change actually means\n\nGitHub's announcement also specifies that the data may be shared with GitHub affiliates, including Microsoft, for AI development purposes.\n\nA policy change of this nature forces organizations to re-examine their AI governance posture, audit their Copilot license tiers, and confirm that the right controls are configured across their teams.\n\n## Why AI governance matters in regulated environments\n\nSource code is often among an organization's most sensitive intellectual property. It may contain references to internal systems, reflect proprietary business logic, or touch data flows governed by strict retention and access policies. When that code passes through an AI assistant, questions about training data usage, model vendor relationships, and data residency become compliance concerns.\n\nThe exposure is particularly acute for financial services firms that have invested in proprietary algorithms, fraud detection logic, credit risk models, underwriting rules, trading strategies. When AI tooling processes that code and uses it to train models serving competitors, vendor data practices become an IP concern.\n\nFinancial institutions operating under [the Federal Reserve's Supervisory Guidance on Model Risk Management (SR 11-7) and the](https://www.federalreserve.gov/supervisionreg/srletters/sr1107.htm) [Digital Operational Resilience Act (DORA)](https://eur-lex.europa.eu/eli/reg/2022/2554/oj/eng) are required to maintain documented, auditable oversight of third-party technology providers, including understanding how those providers handle data. Third-party AI tools used in development workflows increasingly fall within the scope of model risk oversight, and material changes to vendor data practices require updated documentation. \n\nIn the public sector, [the National Institute of Standards and Technology Special Publication 800-53 (NIST 800-53)](https://csrc.nist.gov/publications/detail/sp/800-53/rev-5/final) and the [Federal Information Security Modernization Act (FISMA)](https://www.cisa.gov/topics/cyber-threats-and-advisories/federal-information-security-modernization-act) establish that sensitive or classified code must never leave a controlled boundary. For U.S. Department of Defense and intelligence community environments in particular, a vendor's default data posture is an operational concern. In healthcare, [the Health Insurance Portability and Accountability Act (HIPAA)](https://www.hhs.gov/hipaa/index.html) governs how patient-adjacent data is handled by third parties, and development environments that touch clinical systems increasingly fall within that scope.\n\nAcross all of these contexts, the common thread is the same: A vendor policy that changes data usage defaults, requires individual opt-out, and offers different protections depending on account tier introduces exactly the kind of uncontrolled variable that compliance teams cannot afford.\n\n## What regulated industries actually need from AI vendors\n\nRegulated organizations have largely moved past debating whether to adopt AI in development workflows. The focus now is on doing so in a way they can defend to regulators, boards, and customers. That shift has surfaced a consistent set of requirements regardless of sector.\n\n**Contractual certainty.** Regulated firms need to know, with specificity, what happens to their data. A clear, documented, unconditional commitment is what's required, not something that varies by plan or requires action before a deadline.\n\n**Auditability.** Model risk management frameworks require organizations to understand and validate the AI systems they deploy, including the training data behind those models and the third parties involved in their development. Vendors who cannot answer these questions create documentation risk for the organizations relying on them.\n\n**Separation from vendor incentives.** When an AI vendor trains models on customer usage data, code and workflows become inputs to a system that also serves competitors. For institutions with proprietary trading logic, underwriting models, or fraud detection systems, that's a genuine IP exposure.\n\n## GitLab's position on AI data governance\n\nGitLab does not use customer code to train AI models. This commitment applies at every tier, and AI vendors are contractually prohibited from using inputs or outputs associated with GitLab customers for their own purposes.\n\nThis is a deliberate architectural and policy choice, not a feature of a particular pricing tier. As GitLab's [post on enterprise independence](https://about.gitlab.com/blog/why-enterprise-independence-matters-more-than-ever-in-devsecops/) notes, data governance has become \"an increasingly critical factor in enterprise technology decisions, driven by a complex web of national and regional data protection laws and growing concern about control over sensitive intellectual property.\"\n\nGitLab is also cloud-neutral and model-neutral while supporting self-hosted deployments, not commercially tied to any single cloud provider or large language model (LLM). That i[ndependence matters](https://about.gitlab.com/blog/why-enterprise-independence-matters-more-than-ever-in-devsecops/) for regulated organizations evaluating vendor concentration risk. The [AI Continuity Plan](https://handbook.gitlab.com/handbook/product/ai/continuity-plan/) documents how vendor changes are managed, including material changes to how AI vendors treat customer data, a direct response to the governance requirements under frameworks like [DORA](https://handbook.gitlab.com/handbook/legal/dora/). \n\n## The governance gap AI teams need to close\n\nGitHub's policy update is a reminder that for organizations in regulated industries, understanding exactly how an AI tool handles data is a prerequisite for using it at all. That means asking vendors for clear, documented answers: Is our data used for model training? Who are your AI model subprocessors? What happens if a vendor changes its data practices? Can we deploy in a way that keeps all AI processing within our own infrastructure? What indemnification do you offer for AI-generated output?\n\nVendors who can answer those questions clearly, and document those answers in an auditable form, are vendors you can build on. **Those who cannot will create compliance debt every time they ship a policy update.** And when a vendor can change its data practices with 30 days notice, that's not a partnership built for regulated industries. That's a liability.\n\n> Learn more about GitLab's approach to AI governance at the [GitLab AI Transparency Center](https://about.gitlab.com/ai-transparency-center/).",[25,743],"product",{"featured":35,"template":14,"slug":745},"github-copilots-new-policy-for-ai-training-is-a-governance-wake-up-call",{"content":747,"config":759},{"title":748,"description":749,"authors":750,"body":753,"heroImage":754,"date":755,"category":10,"tags":756},"GitLab and Vertex AI on Google Cloud: Advancing agentic software development","Learn how Google Cloud customers are standardizing on GitLab and Vertex AI for foundation models, enterprise controls, and Model Garden breadth.\n",[751,752],"Regnard Raquedan","Rajesh Agadi","GitLab Duo Agent Platform is helping redefine how organizations build, secure, and deliver software. Since its general availability in January 2026, the platform is bringing agentic AI to every phase of the software development lifecycle. Duo Agent Platform is an intelligent orchestration layer where software teams, and their specialized agents plan, code, review, and remediate security vulnerabilities together.\n\nThrough this exciting partnership, [GitLab Duo Agent Platform](https://about.gitlab.com/gitlab-duo-agent-platform/) automates software development orchestration and lifecycle context via its integration with Vertex AI on Google Cloud, which powers the model tier for agent calls. Software teams keep working on issues, merge requests, pipelines, and security workflows while inference follows the Google Cloud posture they already defined. \n\nAdvances in Google Cloud’s Vertex AI models expand how Google Cloud customers can use GitLab Duo Agent Platform in their environment. Customers get an AI-powered DevSecOps control plane in GitLab, backed by a rapidly advancing AI infrastructure foundation in Vertex AI and Duo Agent Platform’s flexible deployment and integration options. The combination enables more capable, governed agentic workflows that operate at enterprise scale.\n\n![Conceptual illustration of the GitLab Duo Agent Platform integrated with Google Cloud's Vertex AI to power agentic software development and governed AI workflows](https://res.cloudinary.com/about-gitlab-com/image/upload/v1776165990/b7jlux9kydafncwy8spc.png)\n\n## Agents that work across the full lifecycle\n\nMany AI tools focus on a single task: generating code faster. GitLab Duo Agent Platform goes further. It orchestrates AI agents across the entire software development lifecycle (SDLC), from planning through security review to delivery, across many teams with many projects and releases. At this scale, AI coding assistants are necessary for continuous innovation but not sufficient. \n\nSingle-purpose coding assistants rarely see the full state of a project. Backlog shape, open merge requests, failing jobs, and security findings live in GitLab, but a separate chat window in a coding assistant does not inherit that full picture of the SDLC. The gap shows up as manual handoffs, duplicate explanations to an AI that lacks context, and governance teams trying to map data flows across tools that were never designed as one system.\n\nGitLab Duo Agent Platform helps close that gap by running agents and flows on the same objects engineers use every day. Vertex AI then supplies the models and services those agents call when Google Cloud is your chosen inference home, with GitLab’s AI Gateway mediating access so administrators keep a clear map of what connects to what. For instance, GitLab Duo Planner Agent analyzes backlogs, breaks epics into structured tasks, and applies prioritization frameworks to help teams decide what to build next. Security Analyst Agent triages vulnerabilities, details risks in plain language, and recommends remediation in priority order. Built-in flows connect these agents into end-to-end processes, without requiring developers to manage every handoff manually.\n\nAgentic Chat in GitLab Duo Agent Platform ties the experience together for developers. They query in natural language to get context-aware responses with multi-step reasoning that draws on the full state of a project: its issues, merge requests, pipelines, security findings, and codebase. Because GitLab serves as the system of record for the SDLC with a unified data model, GitLab Duo agents operate with lifecycle context that falls outside the reach of standalone, tool-specific AI assistants.\n\n### Amplified by Vertex AI\n\nGitLab Duo Agent Platform is designed to be model-flexible, routing different capabilities to different models based on what performs best for a given task. That architectural choice pays off on Google Cloud, where Vertex AI acts as the managed environment for foundation models and related services, providing a broad model ecosystem and managed infrastructure that helps push the platform's capabilities further.\n\nThe latest generations of AI models available through Vertex AI bring significant improvements in reasoning, tool use, and long-context understanding compared to previous iterations — the same properties that GitLab's agents rely on across many projects and teams with large, complex codebases. Longer context windows and richer tool integration in the underlying models expand what agents can accomplish in a single pass, which is especially important for workloads like deep backlog analysis or monorepo security review.\n\n[Vertex AI Model Garden](https://cloud.google.com/model-garden), with access to a wide range of foundation models, gives customers the breadth to make these choices based on performance, cost, and regulatory requirements rather than vendor lock-in.\n\nMoreover, GitLab customers can use Bring Your Own Model (BYOM) for Duo Agent Platform so approved providers and gateways land where your security model expects them. GitLab’s [18.9 launch coverage of self-hosted Duo Agent Platform and BYOM](https://about.gitlab.com/blog/agentic-ai-enterprise-control-self-hosted-duo-agent-platform-and-byom/) describes how that wiring works. With this deployment option, customers gain access to a wider set of model options they can tailor to their software development process: the right model for the right workflow, with the right guardrails.\n\nFor GitLab, the decision to build on Vertex AI was driven by the need for enterprise-grade reliability and unparalleled model breadth. Vertex AI and Model Garden completely abstract the heavy lifting of LLM hosting — meaning rapid version delivery, robust security, and strict governance are seamlessly built into the integration. Beyond offering Gemini models, Vertex AI provides global, low-latency access to a vast catalog of third-party and open-source models. \n\nCombined with Google Cloud's industry-leading approach to data privacy and model protection, Vertex AI emerged as the clear choice to power GitLab's next-generation developer experience. \n\nBy integrating Vertex AI Model Garden into its backend, GitLab supercharges its DevSecOps platform without passing any complexity on to users. Development teams are not burdened with evaluating or managing underlying LLMs; instead, they experience a streamlined, AI-assisted workflow for building their applications. \n\nGitLab completely abstracts cloud orchestration, enabling developers to focus entirely on writing great code, while Vertex AI powers the features and functionality that assist them.\n\n## What this means for customers on Google Cloud\n\nGitLab Duo Agent Platform already delivers AI agents that operate across the full software lifecycle within a single, governed system of record. On Google Cloud, it enables rapid innovation as Vertex AI continues to advance the model and infrastructure layers. \n\nFor Google Cloud customers, this integration means streamlined software delivery while maintaining strict enterprise governance. For platform engineering groups, it means normalizing which Vertex-backed models power suggestions, analysis, and remediation inside GitLab instead of cataloging dozens of client-side tools. Security programs benefit when agents propose and validate fixes in the same place developers already triage findings, cutting context switching and reducing work that would otherwise spill into unmanaged channels.\n\nFrom a cloud economics and policy angle, drawing agent inference toward Vertex from within GitLab keeps usage nearer to the agreements and controls you already run on Google Cloud, which helps avoid duplicate spend and shadow paths that bypass procurement.\n\nBecause Vertex AI is an underlying infrastructure provider for GitLab Duo Agent Platform, organizations are enabled to dramatically lift developer productivity without the overhead and risk of managing fragmented AI toolchains. Teams stay aligned within a single, secure system of record, helping them build applications faster and ship with confidence.\n\nThe GitLab and Google Cloud collaboration has been building since 2018. Today, it represents one of the most comprehensive paths for organizations moving from AI experiments to fully governed, agentic software development on Google Cloud. As both platforms continue to advance — GitLab expanding its agent orchestration and developer context, and Vertex AI pushing the boundaries of model capability and agent infrastructure — the value for joint customers will continue to grow.\n\n> [Start a free trial of GitLab Duo Agent Platform](https://about.gitlab.com/free-trial/) to experience the power of GitLab and Vertex AI on Google Cloud.","https://res.cloudinary.com/about-gitlab-com/image/upload/v1749663121/Blog/Hero%20Images/LogoLockupPlusLight.png","2026-04-14",[25,282,757,758,743],"google","news",{"featured":13,"template":14,"slug":760},"gitlab-and-vertex-ai-on-google-cloud",{"content":762,"config":772},{"heroImage":763,"title":764,"description":765,"authors":766,"date":768,"category":10,"tags":769,"body":771},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643639/sapu29gmlgtwvhggmj6k.png","Extend GitLab Duo Agent Platform: Connect any tool with MCP","Learn how to connect external tools to GitLab Duo Agent Platform using MCP. Step-by-step setup with three practical workflow demos.",[767],"Albert Rabassa","2026-03-05",[10,743,770],"tutorial","Managing software development often means juggling multiple tools: tracking issues in Jira, writing code in your IDE, and collaborating through GitLab. Context switching between these platforms disrupts focus and slows down delivery.\n\nWith GitLab Duo Agent Platform's [MCP](https://about.gitlab.com/topics/ai/model-context-protocol/) support, you can now connect Jira or any tool that supports MCP directly to your AI-powered development environment. Query issues, update tickets, and sync your workflow — all through natural language, without ever leaving your IDE.\n\n## What you'll learn\n\nIn this tutorial, we'll walk you through:\n\n* **Setting up the Jira/Atlassian OAuth application** for secure authentication\n* **Configuring GitLab Duo Agent Platform** as an MCP client\n* **Three practical use cases** demonstrating real-world workflows\n\n## Prerequisites\n\nBefore getting started, ensure you have the following:\n\n| Requirement | Details |\n| ---- | ----- |\n| **GitLab instance** | GitLab 18.8+ with Duo Agent Platform enabled |\n| **Jira account** | Jira Cloud instance with admin access to create OAuth applications |\n| **IDE** | Visual Studio Code with GitLab Workflow extension installed |\n| **MCP support** | MCP support enabled in GitLab |\n\n\n## Understanding the architecture\n\nGitLab Duo Agent Platform acts as an **MCP client**, connecting to the Atlassian MCP server to access your Jira project management data. Atlassian  MCP server handles authentication, translates natural language requests into API calls, and returns structured data back to GitLab Duo Agent Platform — all while maintaining security and audit controls.\n\n## Part 1: Configure Jira OAuth application\n\nTo securely connect GitLab Duo Agent Platform to your Jira instance, you'll need to create an OAuth 2.0 application in the Atlassian Developer Console. This grants to GitLab the MCP server authorized access to your Jira data.\n\n### Setup steps\n\nIf you prefer to configure manually, follow these steps:\n\n1. **Navigate to the Atlassian Developer Console**\n\n   * Go to [developer.atlassian.com/console/myapps](https://developer.atlassian.com/console/myapps)\n\n   * Sign in with your Atlassian account\n\n2. **Create a new OAuth 2.0 app**\n\n   * Click **Create** → **OAuth 2.0 integration**\n\n   * Enter a name (e.g., \"gitlab-dap-mcp\")\n\n   * Accept the terms and click **Create**\n\n3. **Configure permissions**\n\n   * Navigate to **Permissions** in the left sidebar.\n\n   * Add **Jira API** and configure the following scopes:\n\n     * `read:jira-work` — Read issues, projects, and boards\n\n     * `write:jira-work` — Create and update issues\n\n     * `read:jira-user` — Read user information\n\n4. **Set up authorization**\n\n   * Go to **Authorization** in the left sidebar\n\n   * Add a callback URL for your environment (`https://gitlab.com/oauth/callback`)\n\n   * Save your changes\n\n5. **Retrieve credentials**\n\n   * Navigate to **Settings**\n\n   * Copy your **Client ID** and **Client Secret**\n\n   * Store these securely — you'll need them for the MCP configuration\n\n\n### Interactive walkthrough: Jira OAuth setup\n\nClick on the image below to get started.\n\n\n[![Jira OAuth setup tour](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772644850/wnzfoq43nkkfmgdqldmr.png)](https://gitlab.navattic.com/jira-oauth-setup)\n\n\n## Part 2: Configure GitLab Duo Agent Platform MCP client\n\nWith your OAuth credentials ready, you can now configure GitLab Duo Agent Platform to connect to the Atlassian MCP server.\n\n### Create your MCP configuration file\n\nCreate the MCP configuration file in your GitLab project at `.gitlab/duo/mcp.json`:\n\n\n```json\n{\n  \"mcpServers\": {\n    \"atlassian\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.atlassian.com/v1/mcp\",\n      \"auth\": {\n        \"type\": \"oauth2\",\n        \"clientId\": \"YOUR_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_CLIENT_SECRET\",\n        \"authorizationUrl\": \"https://auth.atlassian.com/oauth/authorize\",\n        \"tokenUrl\": \"https://auth.atlassian.com/oauth/token\"\n      },\n      \"approvedTools\": true\n    }\n  }\n}\n```\n\nReplace `YOUR_CLIENT_ID` and `YOUR_CLIENT_SECRET` with the credentials you generated in Part 1.\n\n### Enable MCP in GitLab\n\n1. Navigate to your **Group Settings** → **GitLab Duo** → **Configuration**\n2. Make sure “Allow external MCP tools” is checked\n\n### Verify the connection\n\nOpen your project in VS Code and ask in GitLab Duo Agent Platform chat:\n\n```text\nWhat MCP tools do you have access to?\n```\n\nThen\n\n```text\nTest the MCP JIRA configuration in this project\n```\n\nAt this point you'll be redirected from the IDE to the MCP Atlassian website to approve access:\n\n![Redirect to MCP Atlassian website](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643461/z5acqjgguh0damnnde9g.png \"Redirect to MCP Atlassian website\")\n\n\u003Cbr>\u003C/br>\n\n![Approve access](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643461/rwowamm8nsubhpixtn3i.png \"Approve access\")\n\n\u003Cbr>\u003C/br>\n\n![Select your JIRA instance and approve](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643461/chuzqd0jeptfwvoj7wjr.png \"Select your JIRA instance and approve\")\n\n\u003Cbr>\u003C/br>\n\n![Success!](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643462/bsgti5iste2bzck19o5y.png \"Success!\")\n\n\u003Cbr>\u003C/br>\n\n### Verify with the MCP Dashboard\n\nGitLab also provides a built-in **MCP Dashboard** directly in your IDE for this.\n\nIn VS Code or VSCodium, open the Command Palette (`Cmd+Shift+P` on macOS, `Ctrl+Shift+P` on Windows/Linux) and search for **\"GitLab: Show MCP Dashboard\"**. The dashboard opens in a new editor tab and gives you:\n\n* **Connection status** for each configured MCP server\n* **Available tools** exposed by the server (e.g., `jira_get_issue`, `jira_create_issue`)\n* **Server logs** so you can see exactly which tools are being called in real time\n\n![MCP servers dashboard and status](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643462/mmvdfchucacsydivowvn.png \"MCP servers dashboard and status\")\n\n\u003Cbr>\u003C/br>\n\n![Server details and permissions](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643462/tcocgdvovp2dl42pvfn8.png \"Server details and permissions\")\n\n\u003Cbr>\u003C/br>\n\n\n![MCP Server logs](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643466/mougvqqk1bozchaufsci.png \"MCP Server logs\")\n\n\u003Cbr>\u003C/br>\n\n### Interactive walkthrough: Testing MCP\n\n\u003Ciframe src=\"https://player.vimeo.com/video/1170005495?badge=0&autopause=0& player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"Testing MCP\">\u003C/iframe>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n## Part 3: Use cases in action\n\nNow that your integration is configured, let's explore three practical workflows that demonstrate the power of connecting Jira to GitLab Duo Agent Platform.\n\n### Planning assistant\n\n**Scenario:** You're preparing for sprint planning and need to quickly assess the backlog, understand priorities, and identify blockers.\n\nThis demo shows you how to:\n\n* Query the backlog\n* Identify unassigned high-priority issues\n* Get AI-powered sprint recommendations\n\n#### Example prompts\n\nTry these prompts in GitLab Duo Agent Platform Chat:\n\n```text\nList all the unassigned issues in JIRA for project GITLAB\n```\n\n```text\nSuggest the two top issues to prioritize and summarize them. Assign them to me.\n```\n\n### Interactive walkthrough: Project planning\n\n\u003Ciframe src=\"https://player.vimeo.com/video/1170005462?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"Project Planning\">\u003C/iframe>\u003Cscript src=\"https://player.vimeo.com/api/player. js\">\u003C/script>\n\n### Issue triage and creation from code\n\n**Scenario:** While reviewing code, you discover a bug and want to create a Jira issue with relevant context — without leaving your IDE.\n\nThis demo walks you through:\n\n* Identifying a bug while coding\n* Creating a detailed Jira issue via natural language\n* Auto-populating issue fields with code context\n* Linking the issue to your current branch\n\n#### Example prompts\n\n```text\nSearch in JIRA for a bug related to: Null pointer exception in PaymentService.processRefund().\nIf it does not exist create it with all the context needed from the code. Find possible blockers that this bug may cause.\n```\n\n```text\nCreate a new branch called issue-gitlab-18, checkout, and link it to the issue we just created. Assign the JIRA issue to me and mark it as in-progress.\n```\n\n### Interactive walkthrough: Bug review and task automation\n\n\u003Ciframe src=\"https://player.vimeo.com/video/1170005368?badge=0&autopause=0& player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"Bug Review\">\u003C/iframe>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n### Cross-system incident investigation\n\n**Scenario:** A production incident occurs, and you need to correlate information from Jira (incident ticket), GitLab Project Management, your codebase, and merge requests to identify the root cause.\n\nThis demo demonstrates:\n\n* Fetching incident details from Jira\n* Correlating with recent merge requests in GitLab\n* Identifying potentially related code changes\n* Generating an incident timeline\n* Design a remediation plan and create it as a work item in GitLab\n\n#### Example prompts\n\n```text\n\"We have a production incident INC-1 about checkout failures. Can you help me investigate with all available context?\"\n```\n\n```text\nCreate a timeline of events for incident INC-1 including related Jira issues and recent deployments\n```\n\n```text\nPropose a remediation plan\n```\n\n### Interactive walkthrough: Cross-system troubleshooting and remediation\n\n\u003Ciframe src=\"https://player.vimeo.com/video/1170005413?badge=0&autopause=0& player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"Cross System Investigation\">\u003C/iframe>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n## Troubleshooting\n\nThese are some common setup issues and quick fixes:\n\n| Issue | Solution |\n| ----- | ----- |\n| \"MCP server not found\" | Verify the `mcp.json` file is in the correct location and properly formatted |\n| \"Authentication failed\" | Re-check your OAuth credentials and ensure scopes are correctly configured in Atlassian |\n| \"No Jira tools available\" | Restart VS Code after updating `mcp.json` and ensure MCP is enabled in GitLab |\n| \"Connection timeout\" | Check your network connectivity to `mcp.atlassian.com` |\n\n\u003Cbr/> For detailed troubleshooting, see the [GitLab MCP clients documentation](https://docs.gitlab.com/user/gitlab_duo/model_context_protocol/mcp_clients/).\n\n\n## Security considerations\n\nWhen integrating Jira with GitLab Duo Agent Platform:\n\n* **OAuth tokens** — Make sure credentials remain secure\n* **Principle of least privilege** — Only grant the minimum required Jira scopes\n* **Token rotation** — Regularly rotate your OAuth credentials as part of security hygiene\n\n\n## Summary\n\nConnecting GitLab Duo Agent Platform to different tools through MCP transforms how you interact with your development lifecycle. In this article, you have learned how to:\n\n* **Query issues naturally** — Ask questions about your backlog, sprints, and incidents in natural language.\n* **Create and update issues on all your DevSecOps environment** — File bugs and update tickets without leaving your IDE.\n* **Correlate across systems** — Combine Jira data with GitLab project management, merge requests, and pipelines for complete visibility.\n* **Reduce context switching** — Keep your focus on code while staying connected to project management.\n\nThis integration exemplifies the power of MCP: standardized, secure access to your tools through AI, enabling developers to work more efficiently without sacrificing governance or security.\n\n\n## Read more\n\n* [GitLab Duo Agent Platform adds support for Model Context Protocol](https://about.gitlab.com/blog/duo-agent-platform-with-mcp/)\n\n* [What is Model Context Protocol?](https://about.gitlab.com/topics/ai/model-context-protocol/)\n\n* [Agentic AI guides and resources](https://about.gitlab.com/blog/agentic-ai-guides-and-resources/)\n\n* [GitLab MCP clients documentation](https://docs.gitlab.com/user/gitlab_duo/model_context_protocol/mcp_clients/)\n\n* [Get started with GitLab Duo Agent Platform: The complete guide](https://about.gitlab.com/blog/gitlab-duo-agent-platform-complete-getting-started-guide/)",{"featured":35,"template":14,"slug":773},"extend-gitlab-duo-agent-platform-connect-any-tool-with-mcp",{"promotions":775},[776,789,800,812],{"id":777,"categories":778,"header":779,"text":780,"button":781,"image":786},"ai-modernization",[10],"Is AI achieving its promise at scale?","Quiz will take 5 minutes or less",{"text":782,"config":783},"Get your AI maturity score",{"href":784,"dataGaName":785,"dataGaLocation":249},"/assessments/ai-modernization-assessment/","modernization assessment",{"config":787},{"src":788},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/qix0m7kwnd8x2fh1zq49.png",{"id":790,"categories":791,"header":792,"text":780,"button":793,"image":797},"devops-modernization",[743,574],"Are you just managing tools or shipping innovation?",{"text":794,"config":795},"Get your DevOps maturity score",{"href":796,"dataGaName":785,"dataGaLocation":249},"/assessments/devops-modernization-assessment/",{"config":798},{"src":799},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138785/eg818fmakweyuznttgid.png",{"id":801,"categories":802,"header":804,"text":780,"button":805,"image":809},"security-modernization",[803],"security","Are you trading speed for security?",{"text":806,"config":807},"Get your security maturity score",{"href":808,"dataGaName":785,"dataGaLocation":249},"/assessments/security-modernization-assessment/",{"config":810},{"src":811},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/p4pbqd9nnjejg5ds6mdk.png",{"id":813,"paths":814,"header":817,"text":818,"button":819,"image":824},"github-azure-migration",[815,816],"migration-from-azure-devops-to-gitlab","integrating-azure-devops-scm-and-gitlab","Is your team ready for GitHub's Azure move?","GitHub is already rebuilding around Azure. Find out what it means for you.",{"text":820,"config":821},"See how GitLab compares to GitHub",{"href":822,"dataGaName":823,"dataGaLocation":249},"/compare/gitlab-vs-github/github-azure-migration/","github azure migration",{"config":825},{"src":799},{"header":827,"blurb":828,"button":829,"secondaryButton":834},"Start building faster today","See what your team can do with the intelligent orchestration platform for DevSecOps.\n",{"text":830,"config":831},"Get your free trial",{"href":832,"dataGaName":56,"dataGaLocation":833},"https://gitlab.com/-/trial_registrations/new?glm_content=default-saas-trial&glm_source=about.gitlab.com/","feature",{"text":511,"config":835},{"href":60,"dataGaName":61,"dataGaLocation":833},1777302640662]