[{"data":1,"prerenderedAt":830},["ShallowReactive",2],{"/en-us/blog/gitlab-duo-self-hosted-models-on-aws-bedrock":3,"navigation-en-us":38,"banner-en-us":448,"footer-en-us":458,"blog-post-authors-en-us-Chloe Cartron|Olivier Dupré":700,"blog-related-posts-en-us-gitlab-duo-self-hosted-models-on-aws-bedrock":727,"blog-promotions-en-us":768,"next-steps-en-us":820},{"id":4,"title":5,"authorSlugs":6,"body":9,"categorySlug":10,"config":11,"content":15,"description":9,"extension":27,"isFeatured":12,"meta":28,"navigation":12,"path":29,"publishedDate":26,"seo":30,"stem":33,"tagSlugs":34,"__hash__":37},"blogPosts/en-us/blog/gitlab-duo-self-hosted-models-on-aws-bedrock.yml","Gitlab Duo Self Hosted Models On Aws Bedrock",[7,8],"chloe-cartron","olivier-dupr",null,"ai-ml",{"featured":12,"template":13,"slug":14},true,"BlogPost","gitlab-duo-self-hosted-models-on-aws-bedrock",{"title":16,"description":17,"authors":18,"heroImage":21,"body":22,"category":10,"tags":23,"date":26},"Own your AI: Self-Hosted GitLab Duo models with AWS Bedrock","Discover how to leverage AI while maintaining control over your data, infrastructure, and security posture.",[19,20],"Chloe Cartron","Olivier Dupré","https://res.cloudinary.com/about-gitlab-com/image/upload/v1750098682/Blog/Hero%20Images/Blog/Hero%20Images/duo-blog-post_1Cy89R1pY8OMwyrgSB525O_1750098682075.png","As organizations adopt AI capabilities to accelerate their software development lifecycle, they often face a critical challenge: how to leverage AI while maintaining control over their data, infrastructure, and security posture. This is where [GitLab Duo Self-Hosted](https://about.gitlab.com/gitlab-duo-agent-platform/) provides a compelling solution.\nIn this article, we'll walk through the implementation of GitLab Duo Self-Hosted models. This comprehensive guide helps organizations needing to meet strict data sovereignty requirements while still leveraging AI-powered development. The focus is on using models hosted on AWS Bedrock rather than setting up an [LLM](https://about.gitlab.com/blog/what-is-a-large-language-model-llm/) serving solution like vLLM. However, the methodology can be applied to models running in your own data center if you have the necessary capabilities.\n## Why GitLab Duo Self-Hosted?\nGitLab Duo Self-Hosted allows you to deploy GitLab's AI capabilities entirely within your own infrastructure, whether that's on-premises, in a private cloud, or within your secure environment.\n\nKey benefits include:\n* **Complete Data Privacy and Control:** Keep sensitive code and intellectual property within your security perimeter, ensuring no data leaves your environment.\n* **Model Flexibility:** Choose from a variety of models tailored to your specific performance needs and use cases, including Anthropic Claude, Meta Llama, Mistral families, and OpenAI GPT families.\n* **Compliance Adherence:** Meet regulatory requirements in highly regulated industries where data must remain within specific geographical boundaries.\n* **Customization:** Configure which GitLab Duo features use specific models to optimize performance and cost.\n* **Deployment Flexibility:** Deploy in fully air-gapped environments, on-premises, or in secure cloud environments.\n\n## Architecture overview\nThe GitLab Duo Self-Hosted solution consists of three core components:\n1. **Self-Managed GitLab instance**: Your existing GitLab instance where users interact with GitLab Duo features.\n2. **AI Gateway**: A service that routes requests between GitLab and your chosen LLM backend.\n3. **LLM backend**: The actual AI model service, which, in this article, will be AWS Bedrock.\n**Note:** You can use [another serving platform](https://docs.gitlab.com/administration/gitlab_duo_self_hosted/supported_llm_serving_platforms/) if you are running on-premises or using another cloud provider.\n\n![Air-gapped network flow chart](https://res.cloudinary.com/about-gitlab-com/image/upload/v1754422792/jws4h2kakflfrczftypj.png)\n\n## Prerequisites\nBefore we begin, you'll need:\n* A GitLab Premium or Ultimate instance (Version 17.10 or later)  \n\n  * We strongly recommend using the latest version of GitLab as we continuously deliver new features.\n\n* A GitLab Duo Enterprise add-on license  \n* AWS account with access to Bedrock models *or your API key and credentials needed to query your LLM Serving model*\n\n**Note:** If you aren't a GitLab customer yet, you can [sign up for a free trial of GitLab Ultimate](https://about.gitlab.com/free-trial/), which includes GitLab Duo Enterprise.\n## Implementation steps\n**1. Install the AI Gateway**\n\nThe AI Gateway is the component that routes requests between your GitLab instance and your LLM serving infrastructure — here that is AWS Bedrock. It can run in a Docker image. Follow the instructions from our [installation documentation](https://docs.gitlab.com/install/install_ai_gateway/) to get started. \n\nFor this example, using AWS Bedrock, you also must pass the AWS Key ID and Secret Access Key along with the AWS region.  \n\n```yaml\nAIGW_TAG=self-hosted-v18.1.2-ee`\ndocker run -d -p 5052:5052 \\\n\n  -e AIGW_GITLAB_URL=\u003Cyour_gitlab_instance> \\\n\n  -e AIGW_GITLAB_API_URL=https://\u003Cyour_gitlab_domain>/api/v4/ \\\n\n  -e AWS_ACCESS_KEY_ID=$AWS_KEY_ID\n\n  -e AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \\\n\n  -e AWS_REGION_NAME=$AWS_REGION_NAME \\\n\nregistry.gitlab.com/gitlab-org/modelops/applied-ml/code-suggestions/ai-assist/model-gateway:$AIGW_TAG \\\n```\nHere is the [`AIGW_TAG` list](https://gitlab.com/gitlab-org/modelops/applied-ml/code-suggestions/ai-assist/-/tags).\n\nIn this example we use Docker, but it is also possible to use the Helm chart. Refer to [the installation documentation](https://docs.gitlab.com/install/install_ai_gateway/#install-by-using-helm-chart) for more information.\n\n**2. Configure GitLab to access the AI Gateway**\n![Configure GitLab to access the AI Gateway](https://res.cloudinary.com/about-gitlab-com/image/upload/v1754422792/xj9kvljkqsacpsw41k4a.png)\nNow that the AI gateway is running, you need to configure your GitLab instance to use it.\n\n  - On the left sidebar, at the bottom, select **Admin**.  \n\n  - Select **GitLab Duo**.  \n\n  - In the GitLab Duo section, select **Change configuration**.  \n\n  - Under Local AI Gateway URL, enter the URL for your AI gateway and port for the container (e.g., `https://ai-gateway.example.com:5052`).\n  \n  - Select **Save changes**.\n\n\n**3. Access models from AWS Bedrock** \n\nNext, you will need to request access to the available models on AWS Bedrock. \n\n\n  - Navigate to your AWS account and Bedrock.  \n\n  - Under **Model access**, select the models you want to use and follow the instructions to gain access. \n\n\nYou can find more information in the [AWS Bedrock documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html).\n\n**4. Configure the self-hosted model**\nNow, let's configure a specific AWS Bedrock model for use with GitLab Duo.\n![Add the self-hosted model screen](https://res.cloudinary.com/about-gitlab-com/image/upload/v1754422792/chrlgdvxwdetcszptsav.png)\n\n  - On the left sidebar, at the bottom, select **Admin**.  \n\n  - Select **GitLab Duo Self-Hosted**.  \n\n  - Select **Add self-hosted model**.\n  \n  - Fill in the fields:  \n    * **Deployment name**: A name to identify this model configuration (e.g., \"Mixtral 8x7B\")  \n    * **Platform:** Choose AWS Bedrock  \n    * **Model family:** Select a model, for example here \"Mixtral\"  \n    * **Model identifier:** bedrock/`model-identifier` [from the supported list](https://docs.gitlab.com/administration/gitlab_duo_self_hosted/supported_models_and_hardware_requirements/).\n    \n  - Select **Create self-hosted model**.\n\n\n**5. Configure GitLab Duo features to use your self-hosted model**\n\nAfter configuring the model, assign it to specific GitLab Duo features.\n![Screen to configure self-hosted model features](https://res.cloudinary.com/about-gitlab-com/image/upload/v1754422793/an2i9s2p9cja2xx27g4z.png)\n\n  - On the left sidebar, at the bottom, select **Admin**.  \n\n  - Select **GitLab Duo Self-Hosted**.  \n\n  - Select the **AI-powered features** tab.  \n\n  - For each feature (e.g., Code Suggestions, GitLab Duo Chat) and sub-feature (e.g., Code Generation, Explain Code), select the model you just configured from the dropdown menu.\n\n\nFor example, you might assign Mixtral 8x7B to Code Generation tasks and Claude 3 Sonnet to the GitLab Duo Chat feature.\nCheck out the [requirements documentation](https://docs.gitlab.com/administration/gitlab_duo_self_hosted/supported_models_and_hardware_requirements/) to select the right model for the use case from the models compatibility list per Duo feature. \n## Verifying your setup\nTo ensure that your GitLab Duo Self-Hosted implementation with AWS Bedrock is working correctly, perform these verification steps:\n**1. Run the health check**\nAfter running the health check of your model to be sure that it’s up and running, Return to the GitLab Duo section from the Admin page and click on **Run health check**. This will verify if:   \n* The AI gateway URL is properly configured.  \n* Your instance can connect to the AI gateway.  \n* The Duo Licence is activated.   \n* A model is assigned to Code Suggestions — *as this is the model used to test the connection.*\n\n![Running the health check](https://res.cloudinary.com/about-gitlab-com/image/upload/v1754422793/yffw21yhjpwummw1ffsw.png)\n\nIf the health check reports issues, refer to the [troubleshooting guide](https://docs.gitlab.com/administration/gitlab_duo_self_hosted/troubleshooting/%20%20%20/) for common errors. \n\n**2. Test GitLab Duo features**\nTry out a few GitLab Duo features to ensure they're working:\n* In the UI, open GitLab Duo Chat and ask it a question.  \n* Open the web IDE  \n  * Create a new code file and see if Code Suggestions appears.  \n  * Select a code snippet and use the `/explain` command to receive an explanation from Duo Chat. \n\n**3. Check AI Gateway logs**\nReview the AI gateway logs to see the requests coming to the gateway from the selected model:\nIn your terminal, run:\n```yaml\ndocker logs \u003Cai-gateway-container-id>\n```\nOptional: In AWS, you can [activate CloudWatch and S3 as log destinations](https://docs.aws.amazon.com/bedrock/latest/userguide/model-invocation-logging.html). Doing so would enable you to see all your requests, prompts, and answers in CloudWatch.\n**Warning:** Keep in mind that activating these logs in AWS logs user data, which may not comply with privacy rules.\nAnd here you have full access to using GitLab Duo's AI features across the platform while retaining complete control over the data flow operating within the secure AWS cloud.\n## Next steps\n### Selecting the right model for each use case\nThe GitLab team actively tests each model's performance for each feature and provides [tier ranking of model's performance and suitability depending on the functionality:](https://docs.gitlab.com/administration/gitlab_duo_self_hosted/supported_models_and_hardware_requirements/#supported-models)\n- Fully compatible: The model can likely handle the feature without any loss of quality.  \n- Largely compatible: The model supports the feature, but there might be compromises or limitations.  \n- Not compatible: The model is unsuitable for the feature, likely resulting in significant quality loss or performance issues.\nAs of this writing, most GitLab Duo features can be configured with Self Hosted. The complete availability overview is available in the [documentation](https://docs.gitlab.com/administration/gitlab_duo_self_hosted/#supported-gitlab-duo-features). \n### Going beyond AWS Bedrock\nWhile this guide focuses on AWS Bedrock integration, GitLab Duo Self-Hosted supports multiple deployment options:\n1. [On-premises with vLLM](https://docs.gitlab.com/administration/gitlab_duo_self_hosted/supported_llm_serving_platforms/#vllm): Run models locally with vLLM for fully air-gapped environments.  \n2. [Azure OpenAI Service](https://docs.gitlab.com/administration/gitlab_duo_self_hosted/supported_llm_serving_platforms/#for-cloud-hosted-model-deployments): Similar to AWS Bedrock, you can use Azure OpenAI for models like GPT-4.\n## Summary\nGitLab Duo Self-Hosted provides a powerful solution for organizations that need AI-powered development tools while maintaining strict control over their data and infrastructure. By following this implementation guide, you can deploy a robust solution that meets security and compliance requirements without compromising on the advanced capabilities that AI brings to your software development lifecycle.\nFor organizations with stringent security and compliance needs, GitLab Duo Self-Hosted strikes the perfect balance between innovation and control, allowing you to harness the power of AI while keeping your code and intellectual property secure within your boundaries.\nWould you like to learn more about implementing GitLab Duo Self-Hosted in your environment? Please [reach out to a GitLab representative](https://about.gitlab.com/sales/) or [visit our documentation](https://docs.gitlab.com/administration/gitlab_duo_self_hosted/) for more detailed information.\n",[24,25],"AI/ML","AWS","2025-08-07","yml",{},"/en-us/blog/gitlab-duo-self-hosted-models-on-aws-bedrock",{"config":31,"title":16,"description":17},{"noIndex":32},false,"en-us/blog/gitlab-duo-self-hosted-models-on-aws-bedrock",[35,36],"aiml","aws","dnncf-cZZ32YQVRuKWwcKC_A6DW1w6k2B37MzIxUImk",{"data":39},{"logo":40,"freeTrial":45,"sales":50,"login":55,"items":60,"search":368,"minimal":399,"duo":418,"switchNav":427,"pricingDeployment":438},{"config":41},{"href":42,"dataGaName":43,"dataGaLocation":44},"/","gitlab logo","header",{"text":46,"config":47},"Get free trial",{"href":48,"dataGaName":49,"dataGaLocation":44},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com&glm_content=default-saas-trial/","free trial",{"text":51,"config":52},"Talk to sales",{"href":53,"dataGaName":54,"dataGaLocation":44},"/sales/","sales",{"text":56,"config":57},"Sign in",{"href":58,"dataGaName":59,"dataGaLocation":44},"https://gitlab.com/users/sign_in/","sign in",[61,88,183,188,289,349],{"text":62,"config":63,"cards":65},"Platform",{"dataNavLevelOne":64},"platform",[66,72,80],{"title":62,"description":67,"link":68},"The intelligent orchestration platform for DevSecOps",{"text":69,"config":70},"Explore our Platform",{"href":71,"dataGaName":64,"dataGaLocation":44},"/platform/",{"title":73,"description":74,"link":75},"GitLab Duo Agent Platform","Agentic AI for the entire software lifecycle",{"text":76,"config":77},"Meet GitLab Duo",{"href":78,"dataGaName":79,"dataGaLocation":44},"/gitlab-duo-agent-platform/","gitlab duo agent platform",{"title":81,"description":82,"link":83},"Why GitLab","See the top reasons enterprises choose GitLab",{"text":84,"config":85},"Learn more",{"href":86,"dataGaName":87,"dataGaLocation":44},"/why-gitlab/","why gitlab",{"text":89,"left":12,"config":90,"link":92,"lists":96,"footer":165},"Product",{"dataNavLevelOne":91},"solutions",{"text":93,"config":94},"View all Solutions",{"href":95,"dataGaName":91,"dataGaLocation":44},"/solutions/",[97,121,144],{"title":98,"description":99,"link":100,"items":105},"Automation","CI/CD and automation to accelerate deployment",{"config":101},{"icon":102,"href":103,"dataGaName":104,"dataGaLocation":44},"AutomatedCodeAlt","/solutions/delivery-automation/","automated software delivery",[106,110,113,117],{"text":107,"config":108},"CI/CD",{"href":109,"dataGaLocation":44,"dataGaName":107},"/solutions/continuous-integration/",{"text":73,"config":111},{"href":78,"dataGaLocation":44,"dataGaName":112},"gitlab duo agent platform - product menu",{"text":114,"config":115},"Source Code Management",{"href":116,"dataGaLocation":44,"dataGaName":114},"/solutions/source-code-management/",{"text":118,"config":119},"Automated Software Delivery",{"href":103,"dataGaLocation":44,"dataGaName":120},"Automated software delivery",{"title":122,"description":123,"link":124,"items":129},"Security","Deliver code faster without compromising security",{"config":125},{"href":126,"dataGaName":127,"dataGaLocation":44,"icon":128},"/solutions/application-security-testing/","security and compliance","ShieldCheckLight",[130,134,139],{"text":131,"config":132},"Application Security Testing",{"href":126,"dataGaName":133,"dataGaLocation":44},"Application security testing",{"text":135,"config":136},"Software Supply Chain Security",{"href":137,"dataGaLocation":44,"dataGaName":138},"/solutions/supply-chain/","Software supply chain security",{"text":140,"config":141},"Software Compliance",{"href":142,"dataGaName":143,"dataGaLocation":44},"/solutions/software-compliance/","software compliance",{"title":145,"link":146,"items":151},"Measurement",{"config":147},{"icon":148,"href":149,"dataGaName":150,"dataGaLocation":44},"DigitalTransformation","/solutions/visibility-measurement/","visibility and measurement",[152,156,160],{"text":153,"config":154},"Visibility & Measurement",{"href":149,"dataGaLocation":44,"dataGaName":155},"Visibility and Measurement",{"text":157,"config":158},"Value Stream Management",{"href":159,"dataGaLocation":44,"dataGaName":157},"/solutions/value-stream-management/",{"text":161,"config":162},"Analytics & Insights",{"href":163,"dataGaLocation":44,"dataGaName":164},"/solutions/analytics-and-insights/","Analytics and insights",{"title":166,"items":167},"GitLab for",[168,173,178],{"text":169,"config":170},"Enterprise",{"href":171,"dataGaLocation":44,"dataGaName":172},"/enterprise/","enterprise",{"text":174,"config":175},"Small Business",{"href":176,"dataGaLocation":44,"dataGaName":177},"/small-business/","small business",{"text":179,"config":180},"Public Sector",{"href":181,"dataGaLocation":44,"dataGaName":182},"/solutions/public-sector/","public sector",{"text":184,"config":185},"Pricing",{"href":186,"dataGaName":187,"dataGaLocation":44,"dataNavLevelOne":187},"/pricing/","pricing",{"text":189,"config":190,"link":192,"lists":196,"feature":276},"Resources",{"dataNavLevelOne":191},"resources",{"text":193,"config":194},"View all resources",{"href":195,"dataGaName":191,"dataGaLocation":44},"/resources/",[197,230,248],{"title":198,"items":199},"Getting started",[200,205,210,215,220,225],{"text":201,"config":202},"Install",{"href":203,"dataGaName":204,"dataGaLocation":44},"/install/","install",{"text":206,"config":207},"Quick start guides",{"href":208,"dataGaName":209,"dataGaLocation":44},"/get-started/","quick setup checklists",{"text":211,"config":212},"Learn",{"href":213,"dataGaLocation":44,"dataGaName":214},"https://university.gitlab.com/","learn",{"text":216,"config":217},"Product documentation",{"href":218,"dataGaName":219,"dataGaLocation":44},"https://docs.gitlab.com/","product documentation",{"text":221,"config":222},"Best practice videos",{"href":223,"dataGaName":224,"dataGaLocation":44},"/getting-started-videos/","best practice videos",{"text":226,"config":227},"Integrations",{"href":228,"dataGaName":229,"dataGaLocation":44},"/integrations/","integrations",{"title":231,"items":232},"Discover",[233,238,243],{"text":234,"config":235},"Customer success stories",{"href":236,"dataGaName":237,"dataGaLocation":44},"/customers/","customer success stories",{"text":239,"config":240},"Blog",{"href":241,"dataGaName":242,"dataGaLocation":44},"/blog/","blog",{"text":244,"config":245},"Remote",{"href":246,"dataGaName":247,"dataGaLocation":44},"https://handbook.gitlab.com/handbook/company/culture/all-remote/","remote",{"title":249,"items":250},"Connect",[251,256,261,266,271],{"text":252,"config":253},"GitLab Services",{"href":254,"dataGaName":255,"dataGaLocation":44},"/services/","services",{"text":257,"config":258},"Community",{"href":259,"dataGaName":260,"dataGaLocation":44},"/community/","community",{"text":262,"config":263},"Forum",{"href":264,"dataGaName":265,"dataGaLocation":44},"https://forum.gitlab.com/","forum",{"text":267,"config":268},"Events",{"href":269,"dataGaName":270,"dataGaLocation":44},"/events/","events",{"text":272,"config":273},"Partners",{"href":274,"dataGaName":275,"dataGaLocation":44},"/partners/","partners",{"backgroundColor":277,"textColor":278,"text":279,"image":280,"link":284},"#2f2a6b","#fff","Insights for the future of software development",{"altText":281,"config":282},"the source promo card",{"src":283},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758208064/dzl0dbift9xdizyelkk4.svg",{"text":285,"config":286},"Read the latest",{"href":287,"dataGaName":288,"dataGaLocation":44},"/the-source/","the source",{"text":290,"config":291,"lists":293},"Company",{"dataNavLevelOne":292},"company",[294],{"items":295},[296,301,307,309,314,319,324,329,334,339,344],{"text":297,"config":298},"About",{"href":299,"dataGaName":300,"dataGaLocation":44},"/company/","about",{"text":302,"config":303,"footerGa":306},"Jobs",{"href":304,"dataGaName":305,"dataGaLocation":44},"/jobs/","jobs",{"dataGaName":305},{"text":267,"config":308},{"href":269,"dataGaName":270,"dataGaLocation":44},{"text":310,"config":311},"Leadership",{"href":312,"dataGaName":313,"dataGaLocation":44},"/company/team/e-group/","leadership",{"text":315,"config":316},"Team",{"href":317,"dataGaName":318,"dataGaLocation":44},"/company/team/","team",{"text":320,"config":321},"Handbook",{"href":322,"dataGaName":323,"dataGaLocation":44},"https://handbook.gitlab.com/","handbook",{"text":325,"config":326},"Investor relations",{"href":327,"dataGaName":328,"dataGaLocation":44},"https://ir.gitlab.com/","investor relations",{"text":330,"config":331},"Trust Center",{"href":332,"dataGaName":333,"dataGaLocation":44},"/security/","trust center",{"text":335,"config":336},"AI Transparency Center",{"href":337,"dataGaName":338,"dataGaLocation":44},"/ai-transparency-center/","ai transparency center",{"text":340,"config":341},"Newsletter",{"href":342,"dataGaName":343,"dataGaLocation":44},"/company/contact/#contact-forms","newsletter",{"text":345,"config":346},"Press",{"href":347,"dataGaName":348,"dataGaLocation":44},"/press/","press",{"text":350,"config":351,"lists":352},"Contact us",{"dataNavLevelOne":292},[353],{"items":354},[355,358,363],{"text":51,"config":356},{"href":53,"dataGaName":357,"dataGaLocation":44},"talk to sales",{"text":359,"config":360},"Support portal",{"href":361,"dataGaName":362,"dataGaLocation":44},"https://support.gitlab.com","support portal",{"text":364,"config":365},"Customer portal",{"href":366,"dataGaName":367,"dataGaLocation":44},"https://customers.gitlab.com/customers/sign_in/","customer portal",{"close":369,"login":370,"suggestions":377},"Close",{"text":371,"link":372},"To search repositories and projects, login to",{"text":373,"config":374},"gitlab.com",{"href":58,"dataGaName":375,"dataGaLocation":376},"search login","search",{"text":378,"default":379},"Suggestions",[380,382,386,388,392,396],{"text":73,"config":381},{"href":78,"dataGaName":73,"dataGaLocation":376},{"text":383,"config":384},"Code Suggestions (AI)",{"href":385,"dataGaName":383,"dataGaLocation":376},"/solutions/code-suggestions/",{"text":107,"config":387},{"href":109,"dataGaName":107,"dataGaLocation":376},{"text":389,"config":390},"GitLab on AWS",{"href":391,"dataGaName":389,"dataGaLocation":376},"/partners/technology-partners/aws/",{"text":393,"config":394},"GitLab on Google Cloud",{"href":395,"dataGaName":393,"dataGaLocation":376},"/partners/technology-partners/google-cloud-platform/",{"text":397,"config":398},"Why GitLab?",{"href":86,"dataGaName":397,"dataGaLocation":376},{"freeTrial":400,"mobileIcon":405,"desktopIcon":410,"secondaryButton":413},{"text":401,"config":402},"Start free trial",{"href":403,"dataGaName":49,"dataGaLocation":404},"https://gitlab.com/-/trials/new/","nav",{"altText":406,"config":407},"Gitlab Icon",{"src":408,"dataGaName":409,"dataGaLocation":404},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203874/jypbw1jx72aexsoohd7x.svg","gitlab icon",{"altText":406,"config":411},{"src":412,"dataGaName":409,"dataGaLocation":404},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203875/gs4c8p8opsgvflgkswz9.svg",{"text":414,"config":415},"Get Started",{"href":416,"dataGaName":417,"dataGaLocation":404},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com/get-started/","get started",{"freeTrial":419,"mobileIcon":423,"desktopIcon":425},{"text":420,"config":421},"Learn more about GitLab Duo",{"href":78,"dataGaName":422,"dataGaLocation":404},"gitlab duo",{"altText":406,"config":424},{"src":408,"dataGaName":409,"dataGaLocation":404},{"altText":406,"config":426},{"src":412,"dataGaName":409,"dataGaLocation":404},{"button":428,"mobileIcon":433,"desktopIcon":435},{"text":429,"config":430},"/switch",{"href":431,"dataGaName":432,"dataGaLocation":404},"#contact","switch",{"altText":406,"config":434},{"src":408,"dataGaName":409,"dataGaLocation":404},{"altText":406,"config":436},{"src":437,"dataGaName":409,"dataGaLocation":404},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1773335277/ohhpiuoxoldryzrnhfrh.png",{"freeTrial":439,"mobileIcon":444,"desktopIcon":446},{"text":440,"config":441},"Back to pricing",{"href":186,"dataGaName":442,"dataGaLocation":404,"icon":443},"back to pricing","GoBack",{"altText":406,"config":445},{"src":408,"dataGaName":409,"dataGaLocation":404},{"altText":406,"config":447},{"src":412,"dataGaName":409,"dataGaLocation":404},{"title":449,"button":450,"config":455},"See how agentic AI transforms software delivery",{"text":451,"config":452},"Watch GitLab Transcend now",{"href":453,"dataGaName":454,"dataGaLocation":44},"/events/transcend/virtual/","transcend event",{"layout":456,"icon":457,"disabled":12},"release","AiStar",{"data":459},{"text":460,"source":461,"edit":467,"contribute":472,"config":477,"items":482,"minimal":689},"Git is a trademark of Software Freedom Conservancy and our use of 'GitLab' is under license",{"text":462,"config":463},"View page source",{"href":464,"dataGaName":465,"dataGaLocation":466},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/","page source","footer",{"text":468,"config":469},"Edit this page",{"href":470,"dataGaName":471,"dataGaLocation":466},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/content/","web ide",{"text":473,"config":474},"Please contribute",{"href":475,"dataGaName":476,"dataGaLocation":466},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/CONTRIBUTING.md/","please contribute",{"twitter":478,"facebook":479,"youtube":480,"linkedin":481},"https://twitter.com/gitlab","https://www.facebook.com/gitlab","https://www.youtube.com/channel/UCnMGQ8QHMAnVIsI3xJrihhg","https://www.linkedin.com/company/gitlab-com",[483,530,584,628,655],{"title":184,"links":484,"subMenu":499},[485,489,494],{"text":486,"config":487},"View plans",{"href":186,"dataGaName":488,"dataGaLocation":466},"view plans",{"text":490,"config":491},"Why Premium?",{"href":492,"dataGaName":493,"dataGaLocation":466},"/pricing/premium/","why premium",{"text":495,"config":496},"Why Ultimate?",{"href":497,"dataGaName":498,"dataGaLocation":466},"/pricing/ultimate/","why ultimate",[500],{"title":501,"links":502},"Contact Us",[503,506,508,510,515,520,525],{"text":504,"config":505},"Contact sales",{"href":53,"dataGaName":54,"dataGaLocation":466},{"text":359,"config":507},{"href":361,"dataGaName":362,"dataGaLocation":466},{"text":364,"config":509},{"href":366,"dataGaName":367,"dataGaLocation":466},{"text":511,"config":512},"Status",{"href":513,"dataGaName":514,"dataGaLocation":466},"https://status.gitlab.com/","status",{"text":516,"config":517},"Terms of use",{"href":518,"dataGaName":519,"dataGaLocation":466},"/terms/","terms of use",{"text":521,"config":522},"Privacy statement",{"href":523,"dataGaName":524,"dataGaLocation":466},"/privacy/","privacy statement",{"text":526,"config":527},"Cookie preferences",{"dataGaName":528,"dataGaLocation":466,"id":529,"isOneTrustButton":12},"cookie preferences","ot-sdk-btn",{"title":89,"links":531,"subMenu":540},[532,536],{"text":533,"config":534},"DevSecOps platform",{"href":71,"dataGaName":535,"dataGaLocation":466},"devsecops platform",{"text":537,"config":538},"AI-Assisted Development",{"href":78,"dataGaName":539,"dataGaLocation":466},"ai-assisted development",[541],{"title":542,"links":543},"Topics",[544,549,554,559,564,569,574,579],{"text":545,"config":546},"CICD",{"href":547,"dataGaName":548,"dataGaLocation":466},"/topics/ci-cd/","cicd",{"text":550,"config":551},"GitOps",{"href":552,"dataGaName":553,"dataGaLocation":466},"/topics/gitops/","gitops",{"text":555,"config":556},"DevOps",{"href":557,"dataGaName":558,"dataGaLocation":466},"/topics/devops/","devops",{"text":560,"config":561},"Version Control",{"href":562,"dataGaName":563,"dataGaLocation":466},"/topics/version-control/","version control",{"text":565,"config":566},"DevSecOps",{"href":567,"dataGaName":568,"dataGaLocation":466},"/topics/devsecops/","devsecops",{"text":570,"config":571},"Cloud Native",{"href":572,"dataGaName":573,"dataGaLocation":466},"/topics/cloud-native/","cloud native",{"text":575,"config":576},"AI for Coding",{"href":577,"dataGaName":578,"dataGaLocation":466},"/topics/devops/ai-for-coding/","ai for coding",{"text":580,"config":581},"Agentic AI",{"href":582,"dataGaName":583,"dataGaLocation":466},"/topics/agentic-ai/","agentic ai",{"title":585,"links":586},"Solutions",[587,589,591,596,600,603,607,610,612,615,618,623],{"text":131,"config":588},{"href":126,"dataGaName":131,"dataGaLocation":466},{"text":120,"config":590},{"href":103,"dataGaName":104,"dataGaLocation":466},{"text":592,"config":593},"Agile development",{"href":594,"dataGaName":595,"dataGaLocation":466},"/solutions/agile-delivery/","agile delivery",{"text":597,"config":598},"SCM",{"href":116,"dataGaName":599,"dataGaLocation":466},"source code management",{"text":545,"config":601},{"href":109,"dataGaName":602,"dataGaLocation":466},"continuous integration & delivery",{"text":604,"config":605},"Value stream management",{"href":159,"dataGaName":606,"dataGaLocation":466},"value stream management",{"text":550,"config":608},{"href":609,"dataGaName":553,"dataGaLocation":466},"/solutions/gitops/",{"text":169,"config":611},{"href":171,"dataGaName":172,"dataGaLocation":466},{"text":613,"config":614},"Small business",{"href":176,"dataGaName":177,"dataGaLocation":466},{"text":616,"config":617},"Public sector",{"href":181,"dataGaName":182,"dataGaLocation":466},{"text":619,"config":620},"Education",{"href":621,"dataGaName":622,"dataGaLocation":466},"/solutions/education/","education",{"text":624,"config":625},"Financial services",{"href":626,"dataGaName":627,"dataGaLocation":466},"/solutions/finance/","financial services",{"title":189,"links":629},[630,632,634,636,639,641,643,645,647,649,651,653],{"text":201,"config":631},{"href":203,"dataGaName":204,"dataGaLocation":466},{"text":206,"config":633},{"href":208,"dataGaName":209,"dataGaLocation":466},{"text":211,"config":635},{"href":213,"dataGaName":214,"dataGaLocation":466},{"text":216,"config":637},{"href":218,"dataGaName":638,"dataGaLocation":466},"docs",{"text":239,"config":640},{"href":241,"dataGaName":242,"dataGaLocation":466},{"text":234,"config":642},{"href":236,"dataGaName":237,"dataGaLocation":466},{"text":244,"config":644},{"href":246,"dataGaName":247,"dataGaLocation":466},{"text":252,"config":646},{"href":254,"dataGaName":255,"dataGaLocation":466},{"text":257,"config":648},{"href":259,"dataGaName":260,"dataGaLocation":466},{"text":262,"config":650},{"href":264,"dataGaName":265,"dataGaLocation":466},{"text":267,"config":652},{"href":269,"dataGaName":270,"dataGaLocation":466},{"text":272,"config":654},{"href":274,"dataGaName":275,"dataGaLocation":466},{"title":290,"links":656},[657,659,661,663,665,667,669,673,678,680,682,684],{"text":297,"config":658},{"href":299,"dataGaName":292,"dataGaLocation":466},{"text":302,"config":660},{"href":304,"dataGaName":305,"dataGaLocation":466},{"text":310,"config":662},{"href":312,"dataGaName":313,"dataGaLocation":466},{"text":315,"config":664},{"href":317,"dataGaName":318,"dataGaLocation":466},{"text":320,"config":666},{"href":322,"dataGaName":323,"dataGaLocation":466},{"text":325,"config":668},{"href":327,"dataGaName":328,"dataGaLocation":466},{"text":670,"config":671},"Sustainability",{"href":672,"dataGaName":670,"dataGaLocation":466},"/sustainability/",{"text":674,"config":675},"Diversity, inclusion and belonging (DIB)",{"href":676,"dataGaName":677,"dataGaLocation":466},"/diversity-inclusion-belonging/","Diversity, inclusion and belonging",{"text":330,"config":679},{"href":332,"dataGaName":333,"dataGaLocation":466},{"text":340,"config":681},{"href":342,"dataGaName":343,"dataGaLocation":466},{"text":345,"config":683},{"href":347,"dataGaName":348,"dataGaLocation":466},{"text":685,"config":686},"Modern Slavery Transparency Statement",{"href":687,"dataGaName":688,"dataGaLocation":466},"https://handbook.gitlab.com/handbook/legal/modern-slavery-act-transparency-statement/","modern slavery transparency statement",{"items":690},[691,694,697],{"text":692,"config":693},"Terms",{"href":518,"dataGaName":519,"dataGaLocation":466},{"text":695,"config":696},"Cookies",{"dataGaName":528,"dataGaLocation":466,"id":529,"isOneTrustButton":12},{"text":698,"config":699},"Privacy",{"href":523,"dataGaName":524,"dataGaLocation":466},[701,714],{"id":702,"title":19,"body":9,"config":703,"content":706,"description":9,"extension":27,"meta":709,"navigation":12,"path":710,"seo":711,"stem":712,"__hash__":713},"blogAuthors/en-us/blog/authors/chloe-cartron.yml",{"template":704,"gitlabHandle":705},"BlogAuthor","ChloeCartron",{"name":19,"config":707},{"headshot":708},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1754425488/d0uiiypsxa5ajnbdm6jn.png",{},"/en-us/blog/authors/chloe-cartron",{},"en-us/blog/authors/chloe-cartron","iajOtLjpqijgC1moSkhZ-MHWUl_TorgFg8weCt-YqNQ",{"id":715,"title":716,"body":9,"config":717,"content":718,"description":9,"extension":27,"meta":722,"navigation":12,"path":723,"seo":724,"stem":725,"__hash__":726},"blogAuthors/en-us/blog/authors/olivier-dupr.yml","Olivier Dupr",{"template":704},{"name":20,"config":719},{"headshot":720,"ctfId":721},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1750713474/cj6odchlpoqxbibenvye.png","4VIckvQsyfNxEtz4pM42aP",{},"/en-us/blog/authors/olivier-dupr",{},"en-us/blog/authors/olivier-dupr","KYUHajPcOeVlPPyPD8D4H56u7iQpJSPInWLi38Y1NA0",[728,742,753],{"content":729,"config":740},{"title":730,"description":731,"authors":732,"heroImage":734,"date":735,"body":736,"category":10,"tags":737},"Give your AI agent direct, structured GitLab access with glab CLI","The GitLab CLI (glab) provides AI agents structured, reliable access to projects via the MCP, eliminating friction. This tutorial shows how you can speed up code review and issue triage.",[733],"Kai Armstrong","https://res.cloudinary.com/about-gitlab-com/image/upload/v1776347152/unw3mzatkd5xyfbzcnni.png","2026-04-27","\nWhen teams use GitLab Duo, Claude, Cursor, and other AI assistants, more of the development workflow runs through an AI agent acting on your behalf — reading issues, reviewing merge requests, running pipelines, and helping you ship faster. Most developers are already using the GitLab CLI (`glab`) from the terminal to interact with GitLab. Combining the two is a natural next step.\n\n\nThe problem is that without the right tools, AI agents are essentially guessing when it comes to your GitLab projects. They might hallucinate the details of an issue they've never seen, summarize a merge request based on stale training data rather than its actual state, or require you to manually copy context from a browser tab and paste it into a chat window just to get started. Every one of those workarounds is friction: it slows you down, introduces the possibility of error, and puts a hard ceiling on what your agent can actually do on your behalf. `glab` changes that by giving agents a direct, reliable interface to your projects.\n\n\nWith `glab`, your agent fetches what it needs directly from GitLab, acts on it, and reports back — so you spend less time relaying information and more time on the work that matters.\n\n\nIn this tutorial, you'll learn how to use `glab` to give AI agents structured, reliable access to your GitLab projects. You'll also discover how that unlocks a faster, more capable development workflow.\n\n\n## How to connect your AI agent to GitLab through MCP\n\n\nThe most direct way to supercharge your AI workflow is to give your AI agent native access to `glab` through Model Context Protocol ([MCP](https://about.gitlab.com/topics/ai/model-context-protocol/)).\n\n\n MCP is an open standard that lets AI tools discover and use external capabilities at runtime. Once connected, your AI assistant can read issues, comment on merge requests, check pipeline status, and write back to GitLab, all without copying anything from the UI or writing a single API call yourself.\n\n\n To get started, run:\n\n\n ```shell\n # Start the glab MCP server\n glab mcp serve\n ```\n\n\n Once your MCP client is configured, your AI can answer questions like *\"What's the status of my open MRs?\"* or *\"Are there any failing pipelines on main?\"* by querying GitLab directly, not scraping the web UI, not relying on stale training data. See the [full setup docs](https://docs.gitlab.com/cli/) for configuration steps for Claude Code, Cursor, and other editors.\n\n\n One detail worth knowing: `glab` automatically adds `--output json` when invoked through MCP, for any command that supports it. Your agent gets clean, structured data without you needing to think about output formats. And because `glab` uses the official MCP SDK, it stays compatible as the\n protocol evolves.\n\n\n We've also been deliberate about *which* commands are exposed through MCP. Commands that require interactive terminal input are intentionally\n excluded, so your agent never gets stuck waiting for input that will never come. What's exposed is what actually works reliably in an agent context.\n\n\n ## Let your AI participate in code review\n\n\n Most developers have a backlog of MRs waiting for review. It's one of the most time-consuming parts of the job and one of the best places to put\n AI to work. With `glab`, your agent doesn't just observe your review queue, it can work through it with you.\n\n\n ### See exactly what still needs addressing\n\n\n Start with this:\n\n\n ```shell\n glab mr view 2677 --comments --unresolved --output json\n ```\n\n\n This input returns the full MR: metadata, description, and every\n unresolved discussion, as a single structured JSON payload. Hand that to\n your AI and it has everything it needs: which threads are open, what the\n reviewer asked for, and in what context. No tab-switching, no copy-pasting\n individual comments.\n\n\n \n ```json\n {\n   \"id\": 2677,\n   \"title\": \"feat: add OAuth2 support\",\n   \"state\": \"opened\",\n   \"author\": { \"username\": \"jdwick\" },\n   \"labels\": [\"backend\", \"needs-review\"],\n   \"blocking_discussions_resolved\": false,\n   \"discussions\": [\n     {\n       \"id\": \"3107030349\",\n       \"resolved\": false,\n       \"notes\": [\n         {\n           \"author\": { \"username\": \"dmurphy\" },\n           \"body\": \"This error handling will swallow panics — consider wrapping with recover()\",\n           \"created_at\": \"2026-03-14T09:23:11.000Z\"\n         }\n       ]\n     },\n     {\n       \"id\": \"3107030412\",\n       \"resolved\": false,\n       \"notes\": [\n         {\n           \"author\": { \"username\": \"sreeves\" },\n           \"body\": \"Token refresh logic needs a test for the expired token case\",\n           \"created_at\": \"2026-03-14T10:05:44.000Z\"\n         }\n       ]\n     }\n   ]\n }\n ```\n\n\n Instead of reading through every thread yourself, you ask your agent  *\"what do I still need to fix in MR 2677?\"* and get back a prioritized summary with suggested changes. This all happens from a single command.\n\n\n ### Close the loop programmatically\n\n\n Once your AI has helped you address the feedback, it can resolve\n discussions:\n\n\n ```shell\n # List all discussions — structured, ready for the agent to process\n glab mr note list 456 --output json\n\n # Resolve a discussion once the feedback is addressed\n glab mr note resolve 456 3107030349\n\n # Reopen if something needs another look\n glab mr note reopen 456 3107030349\n ```\n\n\n\n ```json\n [\n   {\n     \"id\": 3107030349,\n     \"body\": \"This error handling will swallow panics — consider wrapping with recover()\",\n     \"author\": { \"username\": \"dmurphy\" },\n     \"resolved\": false,\n     \"resolvable\": true\n   },\n   {\n     \"id\": 3107030412,\n     \"body\": \"Token refresh logic needs a test for the expired token case\",\n     \"author\": { \"username\": \"sreeves\" },\n     \"resolved\": false,\n     \"resolvable\": true\n   }\n ]\n ```\n\n\n\n Note IDs are visible directly in the GitLab UI and API, no extra lookup needed. Your agent can work through the full list, verify each fix, and\n resolve as it goes.\n\n\n ## Talk to your AI about your code more effectively\n\n\n Even if you're not running an MCP server, there's a simpler shift that makes a huge difference: using `glab` to feed your AI better information.\n\n\n Think about the last time you asked an AI assistant to help triage issues or debug a failing pipeline. You probably copied some text from the GitLab UI and pasted it into the chat. Here's what your agent is actually\n working with when you do that:\n\n\n ```text\n open issues: 12 • milestone: 17.10 • label: bug, needs-triage ...\n ```\n\n\n Compare that to what it gets with `glab`:\n\n\n \n ```json\n [\n   {\n     \"iid\": 902,\n     \"title\": \"Pipeline fails on merge to main\",\n     \"labels\": [\"bug\", \"needs-triage\"],\n     \"milestone\": { \"title\": \"17.10\" },\n     \"assignees\": []\n   },\n   ...\n ]\n ```\n\n\n Structured, typed, complete; no ambiguity, no parsing guesswork. That's the difference between an agent that can act and one that has to ask\n follow-up questions.\n\n\n If you're using the MCP server, you get this automatically: `glab` adds `--output json` for any command that supports it. If you're working directly\n from the terminal, just add the flag yourself:\n\n\n ```shell\n # Pull open issues for triage\n glab issue list --label \"needs-triage\" --output json\n\n # Check pipeline status\n glab ci status --output json\n\n # Get full MR details\n glab mr view 456 --output json\n ```\n\n\n We've significantly expanded JSON output support in recent releases. It now covers CI status, milestones, labels, releases, schedules, cluster agents, work items, MR approvers, repo contributors, and more. If `glab` can\n retrieve it, your AI can consume it cleanly.\n\n\n ### A real workflow\n\n\n ```shell\n $ glab issue list --label \"needs-triage\" --milestone \"17.10\"\n --output json\n ```\n\n\n ```text\n Agent: I found 2 unassigned bugs in the 17.10 milestone that need triage:\n 1. #902 — Pipeline fails on merge to main (opened 5 days ago)\n 2. #903 — Auth token not refreshing on expiry (opened 4 days ago)\n Both are unassigned. Want me to draft triage notes and suggest assignees based on recent commit history?\n ```\n\n\n ## Your agent is never limited to built-in commands\n\n\n `glab`'s first-class commands cover the most common workflows, but your agent is never limited to them. Through `glab api`, it has authenticated access to the full GitLab REST and GraphQL API surface, using the same session, with no extra credentials or configuration required.\n\n\n This is a meaningful differentiator. Most CLI tools stop at what their commands expose. With `glab`, if GitLab's API supports it, your agent can do it. It's always working from a trusted, authenticated context.\n\n\n A practical example: fetching just the list of changed files in an MR before deciding which diffs to pull in full:\n\n\n ```shell\n # Get changed file paths — lightweight, no diff content yet\n glab api \"/projects/$CI_PROJECT_ID/merge_requests/$CI_MERGE_REQUEST_IID/diffs?per_page=100\" \\\n | jq '.[].new_path'\n\n# Then fetch only the specific file your agent needs\nglab api \"/projects/$CI_PROJECT_ID/merge_requests/$CI_MERGE_REQUEST_IID/diffs?per_page=100\" \\\n| jq '.[] | select(.new_path == \"path/to/file.go\")'\n ```\n\n\n ```text\n \"internal/auth/token.go\"\n \"internal/auth/token_test.go\"\n \"internal/oauth/refresh.go\"\n ```\n\n\n For anything the REST API doesn't cover (epics, certain work item queries, complex cross-project data),  `glab api graphql` gives you the full\n GraphQL interface:\n\n\n ```shell\n   glab api graphql -f query='\n {\n   project(fullPath: \"gitlab-org/gitlab\") {\n     mergeRequest(iid: \"12345\") {\n       title\n       reviewers { nodes { username } }\n     }\n   }\n }'\n ```\n\n ```json\n{\n   \"data\": {\n     \"project\": {\n       \"mergeRequest\": {\n         \"title\": \"feat: add OAuth2 support\",\n         \"reviewers\": {\n           \"nodes\": [\n             { \"username\": \"dmurphy\" },\n             { \"username\": \"sreeves\" }\n           ]\n         }\n       }\n     }\n   }\n }\n\n ```\n\n\n Your agent has a single, authenticated entry point to everything GitLab exposes without the token juggling, separate API clients, or configuration\n overhead.\n\n\n ## What's coming and your feedback\n\n\n Two improvements we're actively working on will make `glab` even more useful for agent workflows:\n\n\n **Agent-aware help text.** Today, `--help` output is written for humansvat a terminal. We're updating it to surface the non-interactive alternative\n for every interactive command, flag which commands support `--output json`, and generally make help a useful resource for agents discovering\n capabilities at runtime — not just humans.\n\n\n **Better machine-readable errors.** When something goes wrong today, agents get the same human-readable error messages as terminal users. We're\n changing that so errors in JSON mode return structured output, giving your agent the information it needs to handle failures gracefully, retry intelligently, or surface the right context back to you.\n\n\n Both of these are in active development. If you're already using `glab` with an AI tool, you're exactly the audience we want feedback from.\n\n\n * **What friction are you hitting?** Commands that don't behave well in agent contexts, error messages that aren't actionable, gaps in JSON output\n coverage. We want to know.\n\n * **What workflows have you unlocked?** Real usage patterns help us prioritize what to build next.\n\n\n Join the discussion in [our feedback issue](https://gitlab.com/gitlab-org/cli/-/issues/8177) — that's where we're shaping the roadmap for agent-friendliness, and where your input will have the most direct impact. If you've found a specific gap, [open an issue](https://gitlab.com/gitlab-org/cli/-/issues/new). If you've got a fix in mind, contributions are welcome. Visit [CONTRIBUTING.md](https://gitlab.com/gitlab-org/cli/-/blob/main/CONTRIBUTING.md) to get started.\n\n\n The GitLab CLI has always been about giving developers more control over their workflow. As AI becomes a bigger part of how we all work, that means making `glab` the best possible interface between your AI tools and your GitLab projects. We're just getting started and we'd love to build the next part with you.\n",[24,738,739],"product","tutorial",{"featured":12,"template":13,"slug":741},"give-your-ai-agent-direct-structured-gitlab-access-with-glab-cli",{"content":743,"config":751},{"title":744,"description":745,"authors":746,"heroImage":734,"date":748,"body":749,"category":10,"tags":750},"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.",[747],"Allie Holland","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/).",[24,738],{"featured":32,"template":13,"slug":752},"github-copilots-new-policy-for-ai-training-is-a-governance-wake-up-call",{"content":754,"config":766},{"title":755,"description":756,"authors":757,"body":760,"heroImage":761,"date":762,"category":10,"tags":763},"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",[758,759],"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",[24,275,764,765,738],"google","news",{"featured":12,"template":13,"slug":767},"gitlab-and-vertex-ai-on-google-cloud",{"promotions":769},[770,783,794,806],{"id":771,"categories":772,"header":773,"text":774,"button":775,"image":780},"ai-modernization",[10],"Is AI achieving its promise at scale?","Quiz will take 5 minutes or less",{"text":776,"config":777},"Get your AI maturity score",{"href":778,"dataGaName":779,"dataGaLocation":242},"/assessments/ai-modernization-assessment/","modernization assessment",{"config":781},{"src":782},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/qix0m7kwnd8x2fh1zq49.png",{"id":784,"categories":785,"header":786,"text":774,"button":787,"image":791},"devops-modernization",[738,568],"Are you just managing tools or shipping innovation?",{"text":788,"config":789},"Get your DevOps maturity score",{"href":790,"dataGaName":779,"dataGaLocation":242},"/assessments/devops-modernization-assessment/",{"config":792},{"src":793},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138785/eg818fmakweyuznttgid.png",{"id":795,"categories":796,"header":798,"text":774,"button":799,"image":803},"security-modernization",[797],"security","Are you trading speed for security?",{"text":800,"config":801},"Get your security maturity score",{"href":802,"dataGaName":779,"dataGaLocation":242},"/assessments/security-modernization-assessment/",{"config":804},{"src":805},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/p4pbqd9nnjejg5ds6mdk.png",{"id":807,"paths":808,"header":811,"text":812,"button":813,"image":818},"github-azure-migration",[809,810],"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":814,"config":815},"See how GitLab compares to GitHub",{"href":816,"dataGaName":817,"dataGaLocation":242},"/compare/gitlab-vs-github/github-azure-migration/","github azure migration",{"config":819},{"src":793},{"header":821,"blurb":822,"button":823,"secondaryButton":828},"Start building faster today","See what your team can do with the intelligent orchestration platform for DevSecOps.\n",{"text":824,"config":825},"Get your free trial",{"href":826,"dataGaName":49,"dataGaLocation":827},"https://gitlab.com/-/trial_registrations/new?glm_content=default-saas-trial&glm_source=about.gitlab.com/","feature",{"text":504,"config":829},{"href":53,"dataGaName":54,"dataGaLocation":827},1777475762032]