[{"data":1,"prerenderedAt":842},["ShallowReactive",2],{"/en-us/blog/gitlab-duo-self-hosted-models-on-aws-bedrock":3,"navigation-en-us":40,"banner-en-us":461,"footer-en-us":471,"blog-post-authors-en-us-Chloe Cartron|Olivier Dupré":713,"blog-related-posts-en-us-gitlab-duo-self-hosted-models-on-aws-bedrock":741,"blog-promotions-en-us":780,"next-steps-en-us":832},{"id":4,"title":5,"authorSlugs":6,"authors":9,"body":12,"category":13,"categorySlug":13,"config":14,"content":18,"date":25,"description":19,"extension":26,"externalUrl":27,"featured":17,"heroImage":21,"isFeatured":17,"meta":28,"navigation":17,"path":29,"publishedDate":25,"rawbody":30,"seo":31,"slug":16,"stem":34,"tagSlugs":35,"tags":38,"template":15,"updatedDate":27,"__hash__":39},"blogPosts/en-us/blog/gitlab-duo-self-hosted-models-on-aws-bedrock.md","Own your AI: Self-Hosted GitLab Duo models with AWS Bedrock",[7,8],"chloe-cartron","olivier-dupr",[10,11],"Chloe Cartron","Olivier Dupré","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.","ai-ml",{"template":15,"slug":16,"featured":17},"BlogPost","gitlab-duo-self-hosted-models-on-aws-bedrock",true,{"title":5,"description":19,"authors":20,"heroImage":21,"tags":22,"category":13,"date":25,"body":12},"Discover how to leverage AI while maintaining control over your data, infrastructure, and security posture.",[10,11],"https://res.cloudinary.com/about-gitlab-com/image/upload/v1750098682/Blog/Hero%20Images/Blog/Hero%20Images/duo-blog-post_1Cy89R1pY8OMwyrgSB525O_1750098682075.png",[23,24],"AI/ML","AWS","2025-08-07","md",null,{},"/en-us/blog/gitlab-duo-self-hosted-models-on-aws-bedrock","---\nseo:\n  config:\n    noIndex: false\n  title: 'Own your AI: Self-Hosted GitLab Duo models with AWS Bedrock'\n  description: 'Discover how to leverage AI while maintaining control over your\n    data, infrastructure, and security posture.'\ntitle: 'Own your AI: Self-Hosted GitLab Duo models with AWS Bedrock'\ndescription: Discover how to leverage AI while maintaining control over your data, infrastructure, and security posture.\nauthors:\n  - Chloe Cartron\n  - Olivier Dupré\nheroImage: https://res.cloudinary.com/about-gitlab-com/image/upload/v1750098682/Blog/Hero%20Images/Blog/Hero%20Images/duo-blog-post_1Cy89R1pY8OMwyrgSB525O_1750098682075.png\ntags:\n  - AI/ML\n  - AWS\ncategory: ai-ml\ndate: '2025-08-07'\nslug: gitlab-duo-self-hosted-models-on-aws-bedrock\nfeatured: true\ntemplate: BlogPost\n---\n\nAs 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",{"config":32,"title":5,"description":19},{"noIndex":33},false,"en-us/blog/gitlab-duo-self-hosted-models-on-aws-bedrock",[36,37],"aiml","aws",[23,24],"TC_-Ark_sqNkkkP3CGHiaJkKtaakS4tHRXnMIK9vDCM",{"logo":41,"freeTrial":46,"sales":51,"login":56,"items":61,"search":381,"minimal":412,"duo":431,"switchNav":440,"pricingDeployment":451},{"config":42},{"href":43,"dataGaName":44,"dataGaLocation":45},"/","gitlab logo","header",{"text":47,"config":48},"Get free trial",{"href":49,"dataGaName":50,"dataGaLocation":45},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com&glm_content=default-saas-trial/","free trial",{"text":52,"config":53},"Talk to sales",{"href":54,"dataGaName":55,"dataGaLocation":45},"/sales/","sales",{"text":57,"config":58},"Sign in",{"href":59,"dataGaName":60,"dataGaLocation":45},"https://gitlab.com/users/sign_in/","sign in",[62,91,191,196,300,361],{"text":63,"config":64,"menu":66},"Platform",{"dataNavLevelOne":65},"platform",{"type":67,"columns":68},"cards",[69,75,83],{"title":63,"description":70,"link":71},"The intelligent orchestration platform for DevSecOps",{"text":72,"config":73},"Explore our Platform",{"href":74,"dataGaName":65,"dataGaLocation":45},"/platform/",{"title":76,"description":77,"link":78},"GitLab Duo Agent Platform","Agentic AI for the entire software lifecycle",{"text":79,"config":80},"Meet GitLab Duo",{"href":81,"dataGaName":82,"dataGaLocation":45},"/gitlab-duo-agent-platform/","gitlab duo agent platform",{"title":84,"description":85,"link":86},"Why GitLab","See the top reasons enterprises choose GitLab",{"text":87,"config":88},"Learn more",{"href":89,"dataGaName":90,"dataGaLocation":45},"/why-gitlab/","why gitlab",{"text":92,"left":17,"config":93,"menu":95},"Product",{"dataNavLevelOne":94},"solutions",{"type":96,"link":97,"columns":101,"feature":170},"lists",{"text":98,"config":99},"View all Solutions",{"href":100,"dataGaName":94,"dataGaLocation":45},"/solutions/",[102,126,149],{"title":103,"description":104,"link":105,"items":110},"Automation","CI/CD and automation to accelerate deployment",{"config":106},{"icon":107,"href":108,"dataGaName":109,"dataGaLocation":45},"AutomatedCodeAlt","/solutions/delivery-automation/","automated software delivery",[111,115,118,122],{"text":112,"config":113},"CI/CD",{"href":114,"dataGaLocation":45,"dataGaName":112},"/solutions/continuous-integration/",{"text":76,"config":116},{"href":81,"dataGaLocation":45,"dataGaName":117},"gitlab duo agent platform - product menu",{"text":119,"config":120},"Source Code Management",{"href":121,"dataGaLocation":45,"dataGaName":119},"/solutions/source-code-management/",{"text":123,"config":124},"Automated Software Delivery",{"href":108,"dataGaLocation":45,"dataGaName":125},"Automated software delivery",{"title":127,"description":128,"link":129,"items":134},"Security","Deliver code faster without compromising security",{"config":130},{"href":131,"dataGaName":132,"dataGaLocation":45,"icon":133},"/solutions/application-security-testing/","security and compliance","ShieldCheckLight",[135,139,144],{"text":136,"config":137},"Application Security Testing",{"href":131,"dataGaName":138,"dataGaLocation":45},"Application security testing",{"text":140,"config":141},"Software Supply Chain Security",{"href":142,"dataGaLocation":45,"dataGaName":143},"/solutions/supply-chain/","Software supply chain security",{"text":145,"config":146},"Software Compliance",{"href":147,"dataGaName":148,"dataGaLocation":45},"/solutions/software-compliance/","software compliance",{"title":150,"link":151,"items":156},"Measurement",{"config":152},{"icon":153,"href":154,"dataGaName":155,"dataGaLocation":45},"DigitalTransformation","/solutions/visibility-measurement/","visibility and measurement",[157,161,165],{"text":158,"config":159},"Visibility & Measurement",{"href":154,"dataGaLocation":45,"dataGaName":160},"Visibility and Measurement",{"text":162,"config":163},"Value Stream Management",{"href":164,"dataGaLocation":45,"dataGaName":162},"/solutions/value-stream-management/",{"text":166,"config":167},"Analytics & Insights",{"href":168,"dataGaLocation":45,"dataGaName":169},"/solutions/analytics-and-insights/","Analytics and insights",{"title":171,"type":96,"items":172},"GitLab for",[173,179,185],{"text":174,"config":175},"Enterprise",{"icon":176,"href":177,"dataGaLocation":45,"dataGaName":178},"Building","/enterprise/","enterprise",{"text":180,"config":181},"Small Business",{"icon":182,"href":183,"dataGaLocation":45,"dataGaName":184},"Work","/small-business/","small business",{"text":186,"config":187},"Public Sector",{"icon":188,"href":189,"dataGaLocation":45,"dataGaName":190},"Organization","/solutions/public-sector/","public sector",{"text":192,"config":193},"Pricing",{"href":194,"dataGaName":195,"dataGaLocation":45,"dataNavLevelOne":195},"/pricing/","pricing",{"text":197,"config":198,"menu":200},"Resources",{"dataNavLevelOne":199},"resources",{"type":96,"link":201,"columns":205,"feature":289},{"text":202,"config":203},"View all resources",{"href":204,"dataGaName":199,"dataGaLocation":45},"/resources/",[206,239,261],{"title":207,"items":208},"Getting started",[209,214,219,224,229,234],{"text":210,"config":211},"Install",{"href":212,"dataGaName":213,"dataGaLocation":45},"/install/","install",{"text":215,"config":216},"Quick start guides",{"href":217,"dataGaName":218,"dataGaLocation":45},"/get-started/","quick setup checklists",{"text":220,"config":221},"Learn",{"href":222,"dataGaLocation":45,"dataGaName":223},"https://university.gitlab.com/","learn",{"text":225,"config":226},"Product documentation",{"href":227,"dataGaName":228,"dataGaLocation":45},"https://docs.gitlab.com/","product documentation",{"text":230,"config":231},"Best practice videos",{"href":232,"dataGaName":233,"dataGaLocation":45},"/getting-started-videos/","best practice videos",{"text":235,"config":236},"Integrations",{"href":237,"dataGaName":238,"dataGaLocation":45},"/integrations/","integrations",{"title":240,"items":241},"Discover",[242,247,252,256],{"text":243,"config":244},"Customer success stories",{"href":245,"dataGaName":246,"dataGaLocation":45},"/customers/","customer success stories",{"text":248,"config":249},"Blog",{"href":250,"dataGaName":251,"dataGaLocation":45},"/blog/","blog",{"text":253,"config":254},"The Source",{"href":255,"dataGaName":251,"dataGaLocation":45},"/the-source/",{"text":257,"config":258},"Remote",{"href":259,"dataGaName":260,"dataGaLocation":45},"https://handbook.gitlab.com/handbook/company/culture/all-remote/","remote",{"title":262,"items":263},"Connect",[264,269,274,279,284],{"text":265,"config":266},"GitLab Services",{"href":267,"dataGaName":268,"dataGaLocation":45},"/services/","services",{"text":270,"config":271},"Community",{"href":272,"dataGaName":273,"dataGaLocation":45},"/community/","community",{"text":275,"config":276},"Forum",{"href":277,"dataGaName":278,"dataGaLocation":45},"https://forum.gitlab.com/","forum",{"text":280,"config":281},"Events",{"href":282,"dataGaName":283,"dataGaLocation":45},"/events/","events",{"text":285,"config":286},"Partners",{"href":287,"dataGaName":288,"dataGaLocation":45},"/partners/","partners",{"config":290,"title":293,"text":294,"link":295},{"background":291,"textColor":292},"url('https://res.cloudinary.com/about-gitlab-com/image/upload/v1777322348/qpq8yrgn8knii57omj0c.png')","#000","What’s new in GitLab","Stay updated with our latest features and improvements.",{"text":296,"config":297},"Read the latest",{"href":298,"dataGaName":299,"dataGaLocation":45},"/releases/whats-new/","whats new",{"text":301,"config":302,"menu":304},"Company",{"dataNavLevelOne":303},"company",{"type":96,"columns":305},[306],{"items":307},[308,313,319,321,326,331,336,341,346,351,356],{"text":309,"config":310},"About",{"href":311,"dataGaName":312,"dataGaLocation":45},"/company/","about",{"text":314,"config":315,"footerGa":318},"Jobs",{"href":316,"dataGaName":317,"dataGaLocation":45},"/jobs/","jobs",{"dataGaName":317},{"text":280,"config":320},{"href":282,"dataGaName":283,"dataGaLocation":45},{"text":322,"config":323},"Leadership",{"href":324,"dataGaName":325,"dataGaLocation":45},"/company/team/e-group/","leadership",{"text":327,"config":328},"Team",{"href":329,"dataGaName":330,"dataGaLocation":45},"/company/team/","team",{"text":332,"config":333},"Handbook",{"href":334,"dataGaName":335,"dataGaLocation":45},"https://handbook.gitlab.com/","handbook",{"text":337,"config":338},"Investor relations",{"href":339,"dataGaName":340,"dataGaLocation":45},"https://ir.gitlab.com/","investor relations",{"text":342,"config":343},"Trust Center",{"href":344,"dataGaName":345,"dataGaLocation":45},"/security/","trust center",{"text":347,"config":348},"AI Transparency Center",{"href":349,"dataGaName":350,"dataGaLocation":45},"/ai-transparency-center/","ai transparency center",{"text":352,"config":353},"Newsletter",{"href":354,"dataGaName":355,"dataGaLocation":45},"/company/contact/#contact-forms","newsletter",{"text":357,"config":358},"Press",{"href":359,"dataGaName":360,"dataGaLocation":45},"/press/","press",{"text":362,"config":363,"menu":364},"Contact us",{"dataNavLevelOne":303},{"type":96,"columns":365},[366],{"items":367},[368,371,376],{"text":52,"config":369},{"href":54,"dataGaName":370,"dataGaLocation":45},"talk to sales",{"text":372,"config":373},"Support portal",{"href":374,"dataGaName":375,"dataGaLocation":45},"https://support.gitlab.com","support portal",{"text":377,"config":378},"Customer portal",{"href":379,"dataGaName":380,"dataGaLocation":45},"https://customers.gitlab.com/customers/sign_in/","customer portal",{"close":382,"login":383,"suggestions":390},"Close",{"text":384,"link":385},"To search repositories and projects, login to",{"text":386,"config":387},"gitlab.com",{"href":59,"dataGaName":388,"dataGaLocation":389},"search login","search",{"text":391,"default":392},"Suggestions",[393,395,399,401,405,409],{"text":76,"config":394},{"href":81,"dataGaName":76,"dataGaLocation":389},{"text":396,"config":397},"Code Suggestions (AI)",{"href":398,"dataGaName":396,"dataGaLocation":389},"/solutions/code-suggestions/",{"text":112,"config":400},{"href":114,"dataGaName":112,"dataGaLocation":389},{"text":402,"config":403},"GitLab on AWS",{"href":404,"dataGaName":402,"dataGaLocation":389},"/partners/technology-partners/aws/",{"text":406,"config":407},"GitLab on Google Cloud",{"href":408,"dataGaName":406,"dataGaLocation":389},"/partners/technology-partners/google-cloud-platform/",{"text":410,"config":411},"Why GitLab?",{"href":89,"dataGaName":410,"dataGaLocation":389},{"freeTrial":413,"mobileIcon":418,"desktopIcon":423,"secondaryButton":426},{"text":414,"config":415},"Start free trial",{"href":416,"dataGaName":50,"dataGaLocation":417},"https://gitlab.com/-/trials/new/","nav",{"altText":419,"config":420},"Gitlab Icon",{"src":421,"dataGaName":422,"dataGaLocation":417},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203874/jypbw1jx72aexsoohd7x.svg","gitlab icon",{"altText":419,"config":424},{"src":425,"dataGaName":422,"dataGaLocation":417},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203875/gs4c8p8opsgvflgkswz9.svg",{"text":427,"config":428},"Get Started",{"href":429,"dataGaName":430,"dataGaLocation":417},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com/get-started/","get started",{"freeTrial":432,"mobileIcon":436,"desktopIcon":438},{"text":433,"config":434},"Learn more about GitLab Duo",{"href":81,"dataGaName":435,"dataGaLocation":417},"gitlab duo",{"altText":419,"config":437},{"src":421,"dataGaName":422,"dataGaLocation":417},{"altText":419,"config":439},{"src":425,"dataGaName":422,"dataGaLocation":417},{"button":441,"mobileIcon":446,"desktopIcon":448},{"text":442,"config":443},"/switch",{"href":444,"dataGaName":445,"dataGaLocation":417},"#contact","switch",{"altText":419,"config":447},{"src":421,"dataGaName":422,"dataGaLocation":417},{"altText":419,"config":449},{"src":450,"dataGaName":422,"dataGaLocation":417},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1773335277/ohhpiuoxoldryzrnhfrh.png",{"freeTrial":452,"mobileIcon":457,"desktopIcon":459},{"text":453,"config":454},"Back to pricing",{"href":194,"dataGaName":455,"dataGaLocation":417,"icon":456},"back to pricing","GoBack",{"altText":419,"config":458},{"src":421,"dataGaName":422,"dataGaLocation":417},{"altText":419,"config":460},{"src":425,"dataGaName":422,"dataGaLocation":417},{"title":462,"button":463,"config":468},"See how agentic AI transforms software delivery",{"text":464,"config":465},"Sign up for GitLab Transcend on June 10",{"href":466,"dataGaName":467,"dataGaLocation":45},"/releases/whats-new/#sign-up","transcend event",{"layout":469,"icon":470,"disabled":33},"release","AiStar",{"data":472},{"text":473,"source":474,"edit":480,"contribute":485,"config":490,"items":495,"minimal":702},"Git is a trademark of Software Freedom Conservancy and our use of 'GitLab' is under license",{"text":475,"config":476},"View page source",{"href":477,"dataGaName":478,"dataGaLocation":479},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/","page source","footer",{"text":481,"config":482},"Edit this page",{"href":483,"dataGaName":484,"dataGaLocation":479},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/content/","web ide",{"text":486,"config":487},"Please contribute",{"href":488,"dataGaName":489,"dataGaLocation":479},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/CONTRIBUTING.md/","please contribute",{"twitter":491,"facebook":492,"youtube":493,"linkedin":494},"https://twitter.com/gitlab","https://www.facebook.com/gitlab","https://www.youtube.com/channel/UCnMGQ8QHMAnVIsI3xJrihhg","https://www.linkedin.com/company/gitlab-com",[496,543,597,641,668],{"title":192,"links":497,"subMenu":512},[498,502,507],{"text":499,"config":500},"View plans",{"href":194,"dataGaName":501,"dataGaLocation":479},"view plans",{"text":503,"config":504},"Why Premium?",{"href":505,"dataGaName":506,"dataGaLocation":479},"/pricing/premium/","why premium",{"text":508,"config":509},"Why Ultimate?",{"href":510,"dataGaName":511,"dataGaLocation":479},"/pricing/ultimate/","why ultimate",[513],{"title":514,"links":515},"Contact Us",[516,519,521,523,528,533,538],{"text":517,"config":518},"Contact sales",{"href":54,"dataGaName":55,"dataGaLocation":479},{"text":372,"config":520},{"href":374,"dataGaName":375,"dataGaLocation":479},{"text":377,"config":522},{"href":379,"dataGaName":380,"dataGaLocation":479},{"text":524,"config":525},"Status",{"href":526,"dataGaName":527,"dataGaLocation":479},"https://status.gitlab.com/","status",{"text":529,"config":530},"Terms of use",{"href":531,"dataGaName":532,"dataGaLocation":479},"/terms/","terms of use",{"text":534,"config":535},"Privacy statement",{"href":536,"dataGaName":537,"dataGaLocation":479},"/privacy/","privacy statement",{"text":539,"config":540},"Cookie preferences",{"dataGaName":541,"dataGaLocation":479,"id":542,"isOneTrustButton":17},"cookie preferences","ot-sdk-btn",{"title":92,"links":544,"subMenu":553},[545,549],{"text":546,"config":547},"DevSecOps platform",{"href":74,"dataGaName":548,"dataGaLocation":479},"devsecops platform",{"text":550,"config":551},"AI-Assisted Development",{"href":81,"dataGaName":552,"dataGaLocation":479},"ai-assisted development",[554],{"title":555,"links":556},"Topics",[557,562,567,572,577,582,587,592],{"text":558,"config":559},"CICD",{"href":560,"dataGaName":561,"dataGaLocation":479},"/topics/ci-cd/","cicd",{"text":563,"config":564},"GitOps",{"href":565,"dataGaName":566,"dataGaLocation":479},"/topics/gitops/","gitops",{"text":568,"config":569},"DevOps",{"href":570,"dataGaName":571,"dataGaLocation":479},"/topics/devops/","devops",{"text":573,"config":574},"Version Control",{"href":575,"dataGaName":576,"dataGaLocation":479},"/topics/version-control/","version control",{"text":578,"config":579},"DevSecOps",{"href":580,"dataGaName":581,"dataGaLocation":479},"/topics/devsecops/","devsecops",{"text":583,"config":584},"Cloud Native",{"href":585,"dataGaName":586,"dataGaLocation":479},"/topics/cloud-native/","cloud native",{"text":588,"config":589},"AI for Coding",{"href":590,"dataGaName":591,"dataGaLocation":479},"/topics/devops/ai-for-coding/","ai for coding",{"text":593,"config":594},"Agentic AI",{"href":595,"dataGaName":596,"dataGaLocation":479},"/topics/agentic-ai/","agentic ai",{"title":598,"links":599},"Solutions",[600,602,604,609,613,616,620,623,625,628,631,636],{"text":136,"config":601},{"href":131,"dataGaName":136,"dataGaLocation":479},{"text":125,"config":603},{"href":108,"dataGaName":109,"dataGaLocation":479},{"text":605,"config":606},"Agile development",{"href":607,"dataGaName":608,"dataGaLocation":479},"/solutions/agile-delivery/","agile delivery",{"text":610,"config":611},"SCM",{"href":121,"dataGaName":612,"dataGaLocation":479},"source code management",{"text":558,"config":614},{"href":114,"dataGaName":615,"dataGaLocation":479},"continuous integration & delivery",{"text":617,"config":618},"Value stream management",{"href":164,"dataGaName":619,"dataGaLocation":479},"value stream management",{"text":563,"config":621},{"href":622,"dataGaName":566,"dataGaLocation":479},"/solutions/gitops/",{"text":174,"config":624},{"href":177,"dataGaName":178,"dataGaLocation":479},{"text":626,"config":627},"Small business",{"href":183,"dataGaName":184,"dataGaLocation":479},{"text":629,"config":630},"Public sector",{"href":189,"dataGaName":190,"dataGaLocation":479},{"text":632,"config":633},"Education",{"href":634,"dataGaName":635,"dataGaLocation":479},"/solutions/education/","education",{"text":637,"config":638},"Financial services",{"href":639,"dataGaName":640,"dataGaLocation":479},"/solutions/finance/","financial services",{"title":197,"links":642},[643,645,647,649,652,654,656,658,660,662,664,666],{"text":210,"config":644},{"href":212,"dataGaName":213,"dataGaLocation":479},{"text":215,"config":646},{"href":217,"dataGaName":218,"dataGaLocation":479},{"text":220,"config":648},{"href":222,"dataGaName":223,"dataGaLocation":479},{"text":225,"config":650},{"href":227,"dataGaName":651,"dataGaLocation":479},"docs",{"text":248,"config":653},{"href":250,"dataGaName":251,"dataGaLocation":479},{"text":243,"config":655},{"href":245,"dataGaName":246,"dataGaLocation":479},{"text":257,"config":657},{"href":259,"dataGaName":260,"dataGaLocation":479},{"text":265,"config":659},{"href":267,"dataGaName":268,"dataGaLocation":479},{"text":270,"config":661},{"href":272,"dataGaName":273,"dataGaLocation":479},{"text":275,"config":663},{"href":277,"dataGaName":278,"dataGaLocation":479},{"text":280,"config":665},{"href":282,"dataGaName":283,"dataGaLocation":479},{"text":285,"config":667},{"href":287,"dataGaName":288,"dataGaLocation":479},{"title":301,"links":669},[670,672,674,676,678,680,682,686,691,693,695,697],{"text":309,"config":671},{"href":311,"dataGaName":303,"dataGaLocation":479},{"text":314,"config":673},{"href":316,"dataGaName":317,"dataGaLocation":479},{"text":322,"config":675},{"href":324,"dataGaName":325,"dataGaLocation":479},{"text":327,"config":677},{"href":329,"dataGaName":330,"dataGaLocation":479},{"text":332,"config":679},{"href":334,"dataGaName":335,"dataGaLocation":479},{"text":337,"config":681},{"href":339,"dataGaName":340,"dataGaLocation":479},{"text":683,"config":684},"Sustainability",{"href":685,"dataGaName":683,"dataGaLocation":479},"/sustainability/",{"text":687,"config":688},"Diversity, inclusion and belonging (DIB)",{"href":689,"dataGaName":690,"dataGaLocation":479},"/diversity-inclusion-belonging/","Diversity, inclusion and belonging",{"text":342,"config":692},{"href":344,"dataGaName":345,"dataGaLocation":479},{"text":352,"config":694},{"href":354,"dataGaName":355,"dataGaLocation":479},{"text":357,"config":696},{"href":359,"dataGaName":360,"dataGaLocation":479},{"text":698,"config":699},"Modern Slavery Transparency Statement",{"href":700,"dataGaName":701,"dataGaLocation":479},"https://handbook.gitlab.com/handbook/legal/modern-slavery-act-transparency-statement/","modern slavery transparency statement",{"items":703},[704,707,710],{"text":705,"config":706},"Terms",{"href":531,"dataGaName":532,"dataGaLocation":479},{"text":708,"config":709},"Cookies",{"dataGaName":541,"dataGaLocation":479,"id":542,"isOneTrustButton":17},{"text":711,"config":712},"Privacy",{"href":536,"dataGaName":537,"dataGaLocation":479},[714,728],{"id":715,"title":10,"body":27,"config":716,"content":719,"description":27,"extension":722,"meta":723,"navigation":17,"path":724,"seo":725,"stem":726,"__hash__":727},"blogAuthors/en-us/blog/authors/chloe-cartron.yml",{"template":717,"gitlabHandle":718},"BlogAuthor","ChloeCartron",{"name":10,"config":720},{"headshot":721},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1754425488/d0uiiypsxa5ajnbdm6jn.png","yml",{},"/en-us/blog/authors/chloe-cartron",{},"en-us/blog/authors/chloe-cartron","iajOtLjpqijgC1moSkhZ-MHWUl_TorgFg8weCt-YqNQ",{"id":729,"title":730,"body":27,"config":731,"content":732,"description":27,"extension":722,"meta":736,"navigation":17,"path":737,"seo":738,"stem":739,"__hash__":740},"blogAuthors/en-us/blog/authors/olivier-dupr.yml","Olivier Dupr",{"template":717},{"name":11,"config":733},{"headshot":734,"ctfId":735},"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",[742,755,767],{"content":743,"config":753},{"title":744,"description":745,"authors":746,"date":748,"heroImage":749,"body":750,"category":13,"tags":751},"Atlassian will train on your data: Opt out with GitLab","Learn why Atlassian's latest move is a threat to data governance and how GitLab's approach helps ensure your customers' data stays private and protected.",[747],"Jessica Hurwitz","2026-05-04","https://res.cloudinary.com/about-gitlab-com/image/upload/v1773866173/vte9qh8rriznvyclhkes.png","Starting August 17, 2026, Atlassian will begin collecting customer metadata and in-app content from Jira, Confluence, and other cloud products to train its AI offerings, including Rovo and Rovo Dev. This announcement comes after [GitHub recently changed its Copilot data usage policy](https://about.gitlab.com/blog/github-copilots-new-policy-for-ai-training-is-a-governance-wake-up-call/). **Taken together, these changes suggest opt-out-by-default is becoming the industry norm. GitLab takes the opposite position: no data collection, no AI training on customer data, no matter what tier you're on.**\n\n[Atlassian's change](https://www.atlassian.com/trust/ai/data-contribution) is enabled by default for all cloud customers and affects roughly 300,000 organizations. For customers on the Free, Standard, and Premium tiers, metadata collection is mandatory and cannot be turned off. Only Enterprise-tier customers have the option to opt out. This policy change deserves a close read if your engineering, IT, and program management teams run on Atlassian because they are most exposed by this change — and least likely to have been consulted before it happened.\n\nAlthough the underlying governance questions are the same for both Atlassian and GitHub's changes, the data at risk is different. Where GitHub's change concerned source code and developer interactions, Atlassian's reaches into project plans, internal documentation, workflow configurations, and operational metadata across Jira, Confluence, and the broader Atlassian stack. **For organizations that rely on these tools as their system of record for how work gets planned and delivered, the implications run deep.**\n\n## What changed and what it means for your data\n\nAtlassian will collect two categories of information: \n\n- **Metadata:** de-identified operational signals like story points, sprint dates, and SLA values, including data from its Teamwork Graph and connected third-party apps  \n- **In-app content:** user-generated material such as Confluence page content, Jira issue titles, descriptions, and comments\n\nAtlassian says it will apply de-identification and aggregation before training. Collected data may be retained for up to seven years, with in-app data removed within 30 days of opt-out and models retrained within 90 days.\n\nThere are some exclusions: Customers using customer-managed encryption keys, Atlassian Government Cloud, Isolated Cloud, or those with HIPAA requirements are carved out from collection. But for the vast majority of Atlassian's cloud customer base, data collection will start unless you pay for the Enterprise tier and actively flip the switch.\n\nThis reverses Atlassian's prior stated position that customer data would not be used to train or improve AI services. Organizations that adopted Jira and Confluence to manage their most sensitive planning workflows, sprint boards, security tickets, incident postmortems, and internal documentation will soon be contributing that content to Atlassian's AI training pipeline, without ever being asked.\n\n## The governance gap in \"opt-out by default\"\n\nOpt-out-by-default data collection for AI training is an emerging pattern across the software industry. It raises the same set of questions every time: How does this interact with existing data processing agreements? Does the vendor's definition of \"metadata\" match what your legal and security teams would consider non-sensitive data?\n\n**For many organizations, the answer to these questions is \"we don't know.\"** \n\nWhen a vendor changes its data practices through a terms-of-service update, the burden falls on the customer to notice, evaluate the implications, and act within the window the vendor provides. \n\nThe mandatory nature of metadata collection on Free, Standard, and Premium tiers makes this more acute. The only exit is upgrading to Enterprise, which requires a minimum of 801 users and custom pricing that would represent a significant cost jump for teams that aren't there yet. Data protection, in other words, is now a purchasing decision.\n\nThe tiered structure also introduces a subtler problem. Metadata like story points, sprint velocity, SLA metrics, and task classifications may seem innocuous in isolation, but in aggregate they reveal project structure, team performance patterns, and delivery cadence. For organizations in competitive industries, that operational intelligence has real value, and \"de-identified\" does not necessarily mean \"non-sensitive\" once patterns are reconstructable at scale.\n\n## Why this matters more for Atlassian-stack organizations\n\nIn Atlassian-based organizations, Jira has been the center how teams plan, track, and deliver work. It’s the source of truth for sprint planning, bug tracking, release management, portfolio coordination, and cross-functional project execution. \n\nIn regulated industries like financial services, public sector and manufacturing, Jira and Confluence together hold sensitive operational data that may be subject to compliance requirements. The risk compounds for organizations that have expanded beyond Jira into the broader Atlassian ecosystem.\n\nWhen you run Jira, Confluence, Bitbucket, and Bamboo together, the surface area of data now feeding into AI training spans your project plans, internal documentation, source code metadata, and CI/CD configurations — each of which security and compliance teams would want to review before sharing with a vendor's training pipeline.\n\nAtlassian’s Teamwork Graph connectors add another dimension for customers who have integrated third-party tools, such as Slack, Figma, Google Drive, Salesforce, and ServiceNow, into their environment. Teamwork Graph connectors index relationship and activity signals from these connected apps, which means the metadata Atlassian collects will not be limited to what lives inside Atlassian products. For security and compliance teams accustomed to evaluating data flows on a per-vendor basis, this cross-platform reach complicates the assessment considerably.\n\nOrganizations that are already navigating [Atlassian's push from Data Center](https://about.gitlab.com/blog/atlassian-ending-data-center-as-gitlab-maintains-deployment-choice/) and Server editions to the cloud face a compounding challenge. Adding default AI data collection to that migration path raises the stakes further: **The question is no longer just \"do we move to Atlassian Cloud?\" but \"do we move to Atlassian Cloud knowing our data will feed AI training unless we're on the most expensive tier?\"**\n\n## What regulated industries should be evaluating now\n\nThe compliance implications vary by sector, but the obligation to reassess is consistent.\n\nIn financial services, frameworks like [SR 11-7](https://www.federalreserve.gov/supervisionreg/srletters/sr1107.htm) and [DORA](https://eur-lex.europa.eu/eli/reg/2022/2554/oj/eng) require documented, auditable oversight of third-party technology providers, including how those providers handle data. In the public sector, [NIST 800-53](https://csrc.nist.gov/publications/detail/sp/800-53/rev-5/final) and [FISMA](https://www.cisa.gov/topics/cyber-threats-and-advisories/federal-information-security-modernization-act) make controlling where sensitive data flows a foundational requirement. In healthcare, [HIPAA](https://www.hhs.gov/hipaa/index.html) governs how patient-adjacent data is handled by third parties. \n\nAcross the board, a material change in a vendor's data practices, such as Atlassian moving from \"we don't train on your data\" to \"we do, by default,\" triggers a documentation and risk reassessment obligation. \n\nInstitutions operating under the [EU AI Act](https://eur-lex.europa.eu/eli/reg/2024/1689/oj/eng) face an additional dimension: opt-out framing aligns with U.S. norms, while European regulators generally expect opt-in consent for data processing of this nature.\n\nIf your model risk or vendor management team documented Atlassian's data handling controls before this announcement, the question isn't whether this change triggers a reassessment obligation. It does. The question is whether your team can take action before August 17.\n\n## What to look for in your platform vendors\n\nCTOs and CISOs across regulated industries need to adopt AI in a way they can explain to regulators, boards, and customers. Because of this, GitLab operates within the following set of principles:\n\n**Unconditional data commitments, not tier-dependent protections.** Regulated organizations need to know, with specificity, what happens to their data. A commitment that varies by plan tier, or that requires action before a deadline, introduces exactly the kind of uncontrolled variable that keeps CISOs up at night.\n\n**Transparency and auditability.** Model risk management frameworks require organizations to understand the AI systems they deploy, including the training data and third parties involved. Vendors who cannot answer these questions clearly create documentation risk.\n\n**Separation between customer data and vendor AI training.** When a platform vendor trains models on customer usage data, workflows and operational patterns become inputs to a system that also serves competitors. For organizations where project structure or delivery cadence represents competitive advantage, that exposure matters.\n\n## How GitLab's approach differs\n\nGitLab doesn't train on customer data — at any tier, full stop. AI vendors powering GitLab Duo features are contractually prohibited from using customer inputs or outputs for their own purposes, [a commitment GitLab CEO Bill Staples](https://www.linkedin.com/posts/williamstaples_gitlab-1810-agentic-ai-now-open-to-even-activity-7443280763715985408-aHxf) has consistently reiterated.\n\n[GitLab's AI Transparency Center](https://about.gitlab.com/ai-transparency-center/) documents exactly which models power which features, how data is handled, and what vendor commitments are in place. [GitLab's AI Continuity Plan](https://handbook.gitlab.com/handbook/product/ai/continuity-plan/) documents how vendor changes are managed, including any material changes to how AI vendors treat customer data. For institutions managing third-party AI risk under DORA or similar frameworks, vendor continuity and concentration are active governance concerns, and having a documented plan for both is part of what responsible AI tooling looks like.\n\nFor organizations that require AI processing to stay within their own infrastructure, [GitLab Duo Agent Platform](https://about.gitlab.com/gitlab-duo/) is available with GitLab Self-Managed deployments, including support for integration with self-hosted AI models. This means prompts and code never leave the customer's environment. GitLab also provides IP indemnification for Duo-generated output, with no filters required and no activation steps needed. Where your data lives remains your choice, no matter your deployment model or subscription tier.\n\n> Whether your organization stays on Atlassian or begins evaluating alternatives, the conversation about who controls your data and how it gets used should be happening now. **The August 17 deadline is approaching, but you still have time to [try GitLab Ultimate with Duo Agent Platform for free today](https://gitlab.com/-/trials/new).**",[23,752],"product",{"featured":17,"template":15,"slug":754},"atlassian-will-train-on-your-data-opt-out-with-gitlab",{"content":756,"config":765},{"title":757,"description":758,"authors":759,"heroImage":761,"date":762,"body":763,"category":13,"tags":764},"GitLab and Anthropic: Governed AI for enterprise development","GitLab deepens its Anthropic Claude integration, bringing governed AI, access to new models, and cloud flexibility to enterprise software development.",[760],"Stuart Moncada","https://res.cloudinary.com/about-gitlab-com/image/upload/v1776457632/llddiylsgwuze0u1rjks.png","2026-04-28","For enterprise and public sector leaders, the tension is familiar: Software teams need to move faster with AI, while security, compliance, and regulatory expectations only get more stringent. GitLab deepens its Anthropic Claude integration so organizations get access to newly released Claude models inside GitLab’s intelligent orchestration platform where governance, compliance, and auditability already run.\n\nClaude powers capabilities across GitLab Duo Agent Platform as the default model out of the box, across a variety of use cases from code generation and review to agentic chat and vulnerability resolution. If you've used GitLab Duo, you've already experienced how Duo agents automate workflows across the entire software development lifecycle (SDLC).\n\nThis accelerates the integration of Claude’s capabilities into GitLab, broadens how enterprises can deploy them, and reinforces what makes GitLab fundamentally different as a platform for software development and engineering: governance, compliance, and auditability built into every AI interaction.\n\n> \"GitLab Duo has accelerated how our teams plan, build, and ship software. The combination of Anthropic's Claude and GitLab's platform means we're getting more capable AI without changing how we work or how it is governed.\"\n>\n> – Mans Booijink, Operations Manager, Cube\n\n## The real differentiator: Governed AI\n\nWith GitLab, governance controls and auditing are built into the SDLC. When Claude suggests a code change through the GitLab Duo Agent Platform, that suggestion flows through the same merge request process, the same approval rules, the same security scanning, and the same audit trail as every other change. AI doesn't get a shortcut around your controls. It operates within them.\n\nAs GitLab moves deeper into agentic software development, where AI autonomously handles well-defined tasks, the governance layer becomes more important. An AI agent that can open a merge request, help resolve a vulnerability, or refactor a service needs to be auditable, attributable, and subject to the same policy enforcement as a human developer. That requirement is an architectural decision GitLab made from the start, and one that grows more consequential as AI agents take on broader responsibilities.\n\n## Enterprise deployment flexibility\n\nThis also expands how organizations access the latest Claude models through GitLab. Claude is available within GitLab through Google Cloud's Vertex AI and Amazon Bedrock, which means enterprises can route AI workloads through the hyperscaler commitments and cloud governance frameworks they already have in place. No separate vendor contract. No new data residency questions. Your existing Google Cloud or AWS relationship is the on-ramp. \n\nGitLab is now also available in the [Claude Marketplace](https://claude.com/platform/marketplace), allowing customers to purchase GitLab Credits and apply them toward existing Anthropic spending commitments – consolidating AI spend and simplifying how teams discover and procure GitLab alongside their Anthropic investments.\n\n## Advancing an agentic future\n\nGitLab's vision for agentic software development, where AI handles defined tasks autonomously across planning, coding, testing, securing, and deploying, requires models with strong reasoning, reliability, and safety characteristics. It also requires a platform where those autonomous actions are fully governed.\n\nAgentic workflows demand models with strong reasoning, reliability, and safety characteristics, criteria that guide how GitLab selects and integrates AI model partners. And GitLab's governance framework helps ensure that as AI agents assume more advanced development work, enterprises maintain full visibility and control over what those agents do, when they do it, and how changes are tracked.\n\n## What this means for GitLab customers\n\nIf you're already using GitLab Duo Agent Platform, you'll get access to Claude models and deeper AI assistance across your software development lifecycle, all within the governance framework you already rely on.\n\nIf you're evaluating AI-powered software development platforms, you shouldn't have to choose between advanced AI capabilities and enterprise control. This strategic integration is built to deliver both.\n\n> Want to learn more about GitLab Duo Agent Platform? [Get a demo or start a free trial today](https://about.gitlab.com/gitlab-duo-agent-platform/).",[23,752,288],{"featured":17,"template":15,"slug":766},"gitlab-and-anthropic-governed-ai-for-enterprise-development",{"content":768,"config":778},{"title":769,"description":770,"authors":771,"heroImage":773,"date":774,"body":775,"category":13,"tags":776},"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.",[772],"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",[23,752,777],"tutorial",{"featured":17,"template":15,"slug":779},"give-your-ai-agent-direct-structured-gitlab-access-with-glab-cli",{"promotions":781},[782,795,806,818],{"id":783,"categories":784,"header":785,"text":786,"button":787,"image":792},"ai-modernization",[13],"Is AI achieving its promise at scale?","Quiz will take 5 minutes or less",{"text":788,"config":789},"Get your AI maturity score",{"href":790,"dataGaName":791,"dataGaLocation":251},"/assessments/ai-modernization-assessment/","modernization assessment",{"config":793},{"src":794},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/qix0m7kwnd8x2fh1zq49.png",{"id":796,"categories":797,"header":798,"text":786,"button":799,"image":803},"devops-modernization",[752,581],"Are you just managing tools or shipping innovation?",{"text":800,"config":801},"Get your DevOps maturity score",{"href":802,"dataGaName":791,"dataGaLocation":251},"/assessments/devops-modernization-assessment/",{"config":804},{"src":805},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138785/eg818fmakweyuznttgid.png",{"id":807,"categories":808,"header":810,"text":786,"button":811,"image":815},"security-modernization",[809],"security","Are you trading speed for security?",{"text":812,"config":813},"Get your security maturity score",{"href":814,"dataGaName":791,"dataGaLocation":251},"/assessments/security-modernization-assessment/",{"config":816},{"src":817},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/p4pbqd9nnjejg5ds6mdk.png",{"id":819,"paths":820,"header":823,"text":824,"button":825,"image":830},"github-azure-migration",[821,822],"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":826,"config":827},"See how GitLab compares to GitHub",{"href":828,"dataGaName":829,"dataGaLocation":251},"/compare/gitlab-vs-github/github-azure-migration/","github azure migration",{"config":831},{"src":805},{"header":833,"blurb":834,"button":835,"secondaryButton":840},"Start building faster today","See what your team can do with the intelligent orchestration platform for DevSecOps.\n",{"text":836,"config":837},"Get your free trial",{"href":838,"dataGaName":50,"dataGaLocation":839},"https://gitlab.com/-/trial_registrations/new?glm_content=default-saas-trial&glm_source=about.gitlab.com/","feature",{"text":517,"config":841},{"href":54,"dataGaName":55,"dataGaLocation":839},1777934806725]