[{"data":1,"prerenderedAt":827},["ShallowReactive",2],{"/en-us/blog/gitlab-18-4-ai-native-development-with-automation-and-insight":3,"navigation-en-us":40,"banner-en-us":461,"footer-en-us":471,"blog-post-authors-en-us-Bill Staples":712,"blog-related-posts-en-us-gitlab-18-4-ai-native-development-with-automation-and-insight":727,"blog-promotions-en-us":765,"next-steps-en-us":817},{"id":4,"title":5,"authorSlugs":6,"authors":8,"body":10,"category":11,"categorySlug":11,"config":12,"content":16,"date":25,"description":17,"extension":26,"externalUrl":27,"featured":15,"heroImage":19,"isFeatured":15,"meta":28,"navigation":15,"path":29,"publishedDate":25,"rawbody":30,"seo":31,"slug":14,"stem":34,"tagSlugs":35,"tags":38,"template":13,"updatedDate":27,"__hash__":39},"blogPosts/en-us/blog/gitlab-18-4-ai-native-development-with-automation-and-insight.md","GitLab 18.4: AI-native development with automation and insight",[7],"bill-staples",[9],"Bill Staples","As a developer, you know modern development isn't just about writing code — it's about managing change across the entire software development lifecycle.\n\nIn [GitLab 18.3](https://about.gitlab.com/blog/gitlab-18-3-expanding-ai-orchestration-in-software-engineering/), we laid the groundwork for true human-AI collaboration. We introduced leading AI tools such as Claude Code, Codex CLI, Amazon Q CLI, and Gemini CLI as native integrations to GitLab, delivered our first preview of the GitLab Model Context Protocol ([MCP](https://about.gitlab.com/topics/ai/model-context-protocol/)) server in partnership with Cursor, and shipped two new flows, Issue to MR and Convert CI File for Jenkins Flows, to help teams tackle every day problems.\n\nWith [GitLab 18.4](https://docs.gitlab.com/releases/18/gitlab-18-4-released/) we are expanding your ability to build and share custom agents, collaborate more effectively through Agentic Chat, navigate codebases with the Knowledge Graph, and keep pipelines green with the Fix Failed Pipelines Flow, while also delivering greater security and governance over your AI usage.\n\n\u003Cdiv>\u003Ciframe src=\"https://player.vimeo.com/video/1120293274?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"18.4 Release video placeholder\">\u003C/iframe>\u003C/div>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n\n> Have questions on the latest features in the GitLab 18.4 release? [Join us for The Developer Show](https://www.linkedin.com/events/q-a-code-exploringgitlab18-4and7373772262312906753/theater/) live on LinkedIn on Sept. 23 at 10:00 am PT, or on-demand shortly after!\n\n## Build your experience\n\n*Start your day by pulling from the AI Catalog — a library of specialized agents that surface priorities, automate routine work, and keep you focused on building.*\n\n### AI Catalog as your library of specialized agents (Experimental)\n\nWith GitLab 18.4, we're introducing the GitLab Duo AI Catalog — a central library where teams can create, share, and collaborate with custom-built agents across their organization. Every team has ‘their way' of doing things. So creating a custom agent is just like training a fellow engineer on the ‘right way' to do things in your organization.\n\nFor example, a custom Product Planning agent can file bugs in the specific format, following your labeling standards, or a Technical Writer agent can draft concise documentation following your conventions, or a Security agent can make sure your security and compliance standards are met for every MR. Instead of functioning as disconnected tools, these agents become part of the natural stream of work inside GitLab — helping accelerate tasks without disrupting established processes.\n\n**Note:** This capability is currently only available on GitLab.com as an Experiment. We plan to deliver this to our self-managed customers next month in the 18.5 release.\n\n## Stay in your flow\n\n*GitLab Duo Agentic Chat makes collaboration with agents seamless.*\n\n### Smarter Agentic Chat to streamline collaboration with agents (Beta)\n\nAs the centerpiece of GitLab Duo Agent Platform (Beta), [Agentic Chat](https://docs.gitlab.com/user/gitlab_duo_chat/agentic_chat/) gives you a seamless way to collaborate with AI agents. The latest update to Agentic Chat with GitLab 18.4 improves the chat experience and expands how sessions are managed and surfaced.\n\n* **Chat with custom agent**\n\n  Let's start with your newly-created custom agent. Once designed, you can immediately put that agent to work through Agentic Chat. For example, you could ask your new agent “give me a list of assignments” to get started with your priorities for the day. Additionally, you now have the ability to start fresh conversations with new agents and resume previous conversations with agents without losing context.\n\n* [**User model selection**](https://docs.gitlab.com/user/gitlab_duo/model_selection/#select-a-model-to-use-in-gitlab-duo-agentic-chat)\n\n  With previous releases, you're able to select models at a namespace level, but in 18.4 you can now choose models at the user level for a given chat session. This empowers you to make the call on which LLM is right for the job, or experiment with different LLMs to see which delivers the best answer for your task.\n\n* **Improved formatting and visual design**\n\n  We hope you love the new visual design for GitLab Duo Agentic Chat, including improved handling of tool call approvals to ensure your experience is more enjoyable.\n\n* **Agent Sessions available through Agentic Chat**\n\n  Sessions are expanding to become a core part of the Agentic Chat experience. Any agent run or flow now appears in the Sessions overview available from Agentic Chat. Within each session, you'll see rich details like job logs, user information, and tool metadata — providing critical transparency into how agents are working on your behalf.\n\n\n**Note:** Sessions in Agentic Chat is available on GitLab.com only, this enhancement is planned for self-managed customers next month in the 18.5 update.\n## Unlock your codebase\n\n*With agents, context is king. With Knowledge Graph, you can give your agents more context so they can reason faster and give you better results.*\n\n### Introducing the GitLab Knowledge Graph (Beta)\n\nThe [GitLab Knowledge Graph](https://gitlab-org.gitlab.io/rust/knowledge-graph/) in 18.4 transforms how developers and agents understand and navigate complex codebases. The Knowledge Graph provides a connected map of your entire project, linking files, routes, and references across the software development lifecycle. By leveraging tools such as go-to-definition, codebase search, and reference tracking through in-chat queries, developers gain the ability to ask precise questions like “show me all route files” or “what else does this change impact?”\nThis deeper context helps teams move faster and with more confidence — whether it's onboarding new contributors, conducting deep research across a project, or exploring how a modification impacts dependent code. The more of your ecosystem that lives in GitLab, the more powerful the Knowledge Graph becomes, giving both humans and AI agents the foundation to build with accuracy, speed, and full project awareness. In future releases, we'll be stitching all of your GitLab data into the Knowledge Graph, including plans, MRs, security vulnerabilities, and more.\nThis release of the Knowledge Graph focuses on local code indexing, where the `gkg` CLI turns your codebase into a live, embeddable graph database for RAG. You can install it with a simple one-line script, parse local repositories, and connect via MCP to query your workspace.\nOur vision for the Knowledge Graph project is twofold: building a vibrant community edition that developers can run locally today, which will serve as the foundation for a future, fully-integrated Knowledge Graph Service within GitLab.com and self-managed instances.\n\u003Cdiv>\u003Ciframe src=\"https://player.vimeo.com/video/1121017374?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"18.4 Knowledge Graph Demo\">\u003C/iframe>\u003C/div>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n## Automate your pipeline maintenance\n\n*Fix pipeline failures faster and stay in the flow with the Fixed Failed Pipelines Flow.*\n\n### Fix Failed Pipelines Flow with business awareness\n\nKeeping pipelines green is critical for your development velocity, but traditional approaches focus only on technical troubleshooting without considering the business impact. The **Fix Failed Pipelines Flow** addresses this challenge by combining technical analysis with strategic context. For example, it can automatically prioritize fixing a failed deployment pipeline for a customer-facing service ahead of a nightly test job, or flag build issues in a high-priority release branch differently than experimental feature branches.\n\n* **Business-aware failure detection** monitors pipeline executions while understanding the importance of different workflows and deployment targets.\n* **Contextual root cause analysis** analyzes failure logs alongside business requirements, recent changes, and cross-project dependencies to identify underlying causes.\n* **Strategic fix prioritization** generates appropriate fixes while considering business impact, deadlines, and resource allocation priorities.\n* **Workflow-integrated resolution** automatically creates merge requests with fixes that maintain proper review processes while providing business context for prioritization decisions.\n\nThis flow keeps pipelines green while maintaining strategic alignment, enabling automated fixes to support business objectives rather than just resolving technical issues in isolation.\n\n## Customize your AI environment\n\n*Automation only works if you trust the models behind it. That's why 18.4 delivers governance features like model selection and GitLab-managed keys.*\n\n### GitLab Duo model selection to optimize feature performance\n\n[Model selection](https://docs.gitlab.com/user/gitlab_duo/model_selection/) is now generally available, giving you direct control over which large language models ([LLMs](https://about.gitlab.com/blog/what-is-a-large-language-model-llm/)) power GitLab Duo. You and your team can select the models of your choice, apply them across the organization or tailor them per feature. You can set defaults to ensure consistency across namespaces and tools, with governance, compliance, and security requirements in mind.\n\nFor customers using GitLab Duo Self-Hosted, newly added support for GPT OSS and GPT-5 provides additional flexibility for AI-powered development workflows.\n\n**Note:** GitLab Duo Self-Hosted is not available to GitLab.com customers, and GPT models are not supported on GitLab.com.\n\n## Protect your sensitive context\n\n*Alongside governance comes data protection, giving you fine-grained control over what AI can and can't see.*\n\n### GitLab Duo Context Exclusion for granular data protection\n\nIt's no surprise — you need granular control over what information AI agents can access. **GitLab Duo Context Exclusion** in 18.4 provides project-level settings that let teams exclude specific files or file paths from AI access. Capabilities include:\n\n* **File-specific exclusions** to help protect sensitive files such as password configurations, secrets, and proprietary algorithms.\n* **Path-based rules** to create exclusion patterns based on directory structures or file naming conventions.\n* **Flexible configuration** to apply exclusions at the project level while maintaining development workflow efficiency.\n* **Audit visibility** to track what content is excluded to support compliance with data governance policies.\n\nGitLab Duo Context Exclusion helps you protect sensitive data while you accelerate development with agentic AI.\n\n## Extend your AI capabilities with new MCP tools\n\n*Expanded MCP tools extend those capabilities even further, connecting your GitLab environment with a broader ecosystem of intelligent agents.*\n\n### New tools for GitLab MCP server\n\nExpanding on the initial MCP server introduced in [18.3](https://about.gitlab.com/blog/gitlab-18-3-expanding-ai-orchestration-in-software-engineering/), GitLab 18.4 adds more MCP tools — capabilities that define how MCP clients interact with GitLab. These new tools extend integration possibilities, enabling both first-party and third-party AI agents to take on richer tasks such as accessing project data, performing code operations, or searching across repositories, all while respecting existing security and permissions models. For a full list of MCP tools, including the new additions in 18.4, visit our [MCP server documentation](https://docs.gitlab.com/user/gitlab_duo/model_context_protocol/mcp_server/).\n\n## Experience the future of intelligent software development\n\nWith [GitLab Duo Agent Platform](https://about.gitlab.com/gitlab-duo-agent-platform/), engineers can begin to move from working on one issue at a time in single threaded fashion, to multi-threaded collaboration with asynchronous agents that act like teammates to get work done, faster. We are bringing to market this unique vision with our customer's preferences for independence and choice: run in your preferred cloud environments using the LLMs and AI tools that work best for you, within the security and compliance guardrails you set.\n\nAs an integral part of this innovation, GitLab 18.4 is more than a software upgrade — it's about making the day-to-day experience of developers smoother, smarter, and more secure. From reusable agents to business-aware pipeline fixes, every feature is designed to keep teams in flow while balancing speed, security, and control. For a deeper look at how these capabilities come together in practice, check out our walkthrough video.\n\n\n\u003Cdiv>\u003Ciframe src=\"https://player.vimeo.com/video/1120288083?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"A day in the life with GitLab Duo Agent Platform\">\u003C/iframe>\u003C/div>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\u003Cp>\u003C/p>\n\nGitLab Premium and Ultimate users can start using these capabilities today on [GitLab.com](https://GitLab.com) and self-managed environments, with availability for [GitLab Dedicated](https://about.gitlab.com/dedicated/) customers coming next month.\n\n> **Enable beta and experimental features in GitLab Duo Agent Platform today** and experience how full-context AI can transform the way your teams build software. New to GitLab? [Start your free trial](https://about.gitlab.com/free-trial/devsecops/) and see why the future of development is AI-powered, secure, and orchestrated through the world's most comprehensive DevSecOps platform.\n\n## Stay up to date with GitLab\n\nTo make sure you're getting the latest features, security updates, and performance improvements, we recommend keeping your GitLab instance up to date. The following resources can help you plan and complete your upgrade:\n\n* [Upgrade Path Tool](https://gitlab-com.gitlab.io/support/toolbox/upgrade-path/) – enter your current version and see the exact upgrade steps for your instance\n* [Upgrade documentation](https://docs.gitlab.com/update/upgrade_paths/) – detailed guides for each supported version, including requirements, step-by-step instructions, and best practices\n\nBy upgrading regularly, you'll ensure your team benefits from the newest GitLab capabilities and remains secure and supported.\n\nFor organizations that want a hands-off approach, consider [GitLab's Managed Maintenance service](https://content.gitlab.com/viewer/d1fe944dddb06394e6187f0028f010ad#1). With Managed Maintenance, your team stays focused on innovation while GitLab experts keep your Self-Managed instance reliably upgraded, secure, and ready to lead in DevSecOps. Ask your account manager for more information.\n\n\n*This blog post contains \"forward-looking statements\" within the meaning of Section 27A of the Securities Act of 1933, as amended, and Section 21E of the Securities Exchange Act of 1934. Although we believe that the expectations reflected in these statements are reasonable, they are subject to known and unknown risks, uncertainties, assumptions and other factors that may cause actual results or outcomes to differ materially. Further information on these risks and other factors is included under the caption \"Risk Factors\" in our filings with the SEC. We do not undertake any obligation to update or revise these statements after the date of this blog post, except as required by law.*","ai-ml",{"template":13,"slug":14,"featured":15},"BlogPost","gitlab-18-4-ai-native-development-with-automation-and-insight",true,{"title":5,"description":17,"authors":18,"heroImage":19,"tags":20,"category":11,"date":25,"body":10},"With GitLab 18.4, teams create custom agents, unlock Knowledge Graph context, and auto-fix pipelines so developers stay focused and in flow.",[9],"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758541195/kig7sww6jyvxzmkmimbv.png",[21,22,23,24],"AI/ML","product","features","DevSecOps platform","2025-09-23","md",null,{},"/en-us/blog/gitlab-18-4-ai-native-development-with-automation-and-insight","---\nseo:\n  config:\n    noIndex: false\n  title: 'GitLab 18.4: AI-native development with automation and insight'\n  description: With GitLab 18.4, teams create custom agents, unlock Knowledge\n    Graph context, and auto-fix pipelines so developers stay focused and in\n    flow.\ntitle: 'GitLab 18.4: AI-native development with automation and insight'\ndescription: With GitLab 18.4, teams create custom agents, unlock Knowledge Graph context, and auto-fix pipelines so developers stay focused and in flow.\nauthors:\n  - Bill Staples\nheroImage: https://res.cloudinary.com/about-gitlab-com/image/upload/v1758541195/kig7sww6jyvxzmkmimbv.png\ntags:\n  - AI/ML\n  - product\n  - features\n  - DevSecOps platform\ncategory: ai-ml\ndate: '2025-09-23'\nslug: gitlab-18-4-ai-native-development-with-automation-and-insight\nfeatured: true\ntemplate: BlogPost\n---\n\nAs a developer, you know modern development isn't just about writing code — it's about managing change across the entire software development lifecycle.\n\nIn [GitLab 18.3](https://about.gitlab.com/blog/gitlab-18-3-expanding-ai-orchestration-in-software-engineering/), we laid the groundwork for true human-AI collaboration. We introduced leading AI tools such as Claude Code, Codex CLI, Amazon Q CLI, and Gemini CLI as native integrations to GitLab, delivered our first preview of the GitLab Model Context Protocol ([MCP](https://about.gitlab.com/topics/ai/model-context-protocol/)) server in partnership with Cursor, and shipped two new flows, Issue to MR and Convert CI File for Jenkins Flows, to help teams tackle every day problems.\n\nWith [GitLab 18.4](https://docs.gitlab.com/releases/18/gitlab-18-4-released/) we are expanding your ability to build and share custom agents, collaborate more effectively through Agentic Chat, navigate codebases with the Knowledge Graph, and keep pipelines green with the Fix Failed Pipelines Flow, while also delivering greater security and governance over your AI usage.\n\n\u003Cdiv>\u003Ciframe src=\"https://player.vimeo.com/video/1120293274?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"18.4 Release video placeholder\">\u003C/iframe>\u003C/div>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n\n> Have questions on the latest features in the GitLab 18.4 release? [Join us for The Developer Show](https://www.linkedin.com/events/q-a-code-exploringgitlab18-4and7373772262312906753/theater/) live on LinkedIn on Sept. 23 at 10:00 am PT, or on-demand shortly after!\n\n## Build your experience\n\n*Start your day by pulling from the AI Catalog — a library of specialized agents that surface priorities, automate routine work, and keep you focused on building.*\n\n### AI Catalog as your library of specialized agents (Experimental)\n\nWith GitLab 18.4, we're introducing the GitLab Duo AI Catalog — a central library where teams can create, share, and collaborate with custom-built agents across their organization. Every team has ‘their way' of doing things. So creating a custom agent is just like training a fellow engineer on the ‘right way' to do things in your organization.\n\nFor example, a custom Product Planning agent can file bugs in the specific format, following your labeling standards, or a Technical Writer agent can draft concise documentation following your conventions, or a Security agent can make sure your security and compliance standards are met for every MR. Instead of functioning as disconnected tools, these agents become part of the natural stream of work inside GitLab — helping accelerate tasks without disrupting established processes.\n\n**Note:** This capability is currently only available on GitLab.com as an Experiment. We plan to deliver this to our self-managed customers next month in the 18.5 release.\n\n## Stay in your flow\n\n*GitLab Duo Agentic Chat makes collaboration with agents seamless.*\n\n### Smarter Agentic Chat to streamline collaboration with agents (Beta)\n\nAs the centerpiece of GitLab Duo Agent Platform (Beta), [Agentic Chat](https://docs.gitlab.com/user/gitlab_duo_chat/agentic_chat/) gives you a seamless way to collaborate with AI agents. The latest update to Agentic Chat with GitLab 18.4 improves the chat experience and expands how sessions are managed and surfaced.\n\n* **Chat with custom agent**\n\n  Let's start with your newly-created custom agent. Once designed, you can immediately put that agent to work through Agentic Chat. For example, you could ask your new agent “give me a list of assignments” to get started with your priorities for the day. Additionally, you now have the ability to start fresh conversations with new agents and resume previous conversations with agents without losing context.\n\n* [**User model selection**](https://docs.gitlab.com/user/gitlab_duo/model_selection/#select-a-model-to-use-in-gitlab-duo-agentic-chat)\n\n  With previous releases, you're able to select models at a namespace level, but in 18.4 you can now choose models at the user level for a given chat session. This empowers you to make the call on which LLM is right for the job, or experiment with different LLMs to see which delivers the best answer for your task.\n\n* **Improved formatting and visual design**\n\n  We hope you love the new visual design for GitLab Duo Agentic Chat, including improved handling of tool call approvals to ensure your experience is more enjoyable.\n\n* **Agent Sessions available through Agentic Chat**\n\n  Sessions are expanding to become a core part of the Agentic Chat experience. Any agent run or flow now appears in the Sessions overview available from Agentic Chat. Within each session, you'll see rich details like job logs, user information, and tool metadata — providing critical transparency into how agents are working on your behalf.\n\n\n**Note:** Sessions in Agentic Chat is available on GitLab.com only, this enhancement is planned for self-managed customers next month in the 18.5 update.\n## Unlock your codebase\n\n*With agents, context is king. With Knowledge Graph, you can give your agents more context so they can reason faster and give you better results.*\n\n### Introducing the GitLab Knowledge Graph (Beta)\n\nThe [GitLab Knowledge Graph](https://gitlab-org.gitlab.io/rust/knowledge-graph/) in 18.4 transforms how developers and agents understand and navigate complex codebases. The Knowledge Graph provides a connected map of your entire project, linking files, routes, and references across the software development lifecycle. By leveraging tools such as go-to-definition, codebase search, and reference tracking through in-chat queries, developers gain the ability to ask precise questions like “show me all route files” or “what else does this change impact?”\nThis deeper context helps teams move faster and with more confidence — whether it's onboarding new contributors, conducting deep research across a project, or exploring how a modification impacts dependent code. The more of your ecosystem that lives in GitLab, the more powerful the Knowledge Graph becomes, giving both humans and AI agents the foundation to build with accuracy, speed, and full project awareness. In future releases, we'll be stitching all of your GitLab data into the Knowledge Graph, including plans, MRs, security vulnerabilities, and more.\nThis release of the Knowledge Graph focuses on local code indexing, where the `gkg` CLI turns your codebase into a live, embeddable graph database for RAG. You can install it with a simple one-line script, parse local repositories, and connect via MCP to query your workspace.\nOur vision for the Knowledge Graph project is twofold: building a vibrant community edition that developers can run locally today, which will serve as the foundation for a future, fully-integrated Knowledge Graph Service within GitLab.com and self-managed instances.\n\u003Cdiv>\u003Ciframe src=\"https://player.vimeo.com/video/1121017374?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"18.4 Knowledge Graph Demo\">\u003C/iframe>\u003C/div>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n## Automate your pipeline maintenance\n\n*Fix pipeline failures faster and stay in the flow with the Fixed Failed Pipelines Flow.*\n\n### Fix Failed Pipelines Flow with business awareness\n\nKeeping pipelines green is critical for your development velocity, but traditional approaches focus only on technical troubleshooting without considering the business impact. The **Fix Failed Pipelines Flow** addresses this challenge by combining technical analysis with strategic context. For example, it can automatically prioritize fixing a failed deployment pipeline for a customer-facing service ahead of a nightly test job, or flag build issues in a high-priority release branch differently than experimental feature branches.\n\n* **Business-aware failure detection** monitors pipeline executions while understanding the importance of different workflows and deployment targets.\n* **Contextual root cause analysis** analyzes failure logs alongside business requirements, recent changes, and cross-project dependencies to identify underlying causes.\n* **Strategic fix prioritization** generates appropriate fixes while considering business impact, deadlines, and resource allocation priorities.\n* **Workflow-integrated resolution** automatically creates merge requests with fixes that maintain proper review processes while providing business context for prioritization decisions.\n\nThis flow keeps pipelines green while maintaining strategic alignment, enabling automated fixes to support business objectives rather than just resolving technical issues in isolation.\n\n## Customize your AI environment\n\n*Automation only works if you trust the models behind it. That's why 18.4 delivers governance features like model selection and GitLab-managed keys.*\n\n### GitLab Duo model selection to optimize feature performance\n\n[Model selection](https://docs.gitlab.com/user/gitlab_duo/model_selection/) is now generally available, giving you direct control over which large language models ([LLMs](https://about.gitlab.com/blog/what-is-a-large-language-model-llm/)) power GitLab Duo. You and your team can select the models of your choice, apply them across the organization or tailor them per feature. You can set defaults to ensure consistency across namespaces and tools, with governance, compliance, and security requirements in mind.\n\nFor customers using GitLab Duo Self-Hosted, newly added support for GPT OSS and GPT-5 provides additional flexibility for AI-powered development workflows.\n\n**Note:** GitLab Duo Self-Hosted is not available to GitLab.com customers, and GPT models are not supported on GitLab.com.\n\n## Protect your sensitive context\n\n*Alongside governance comes data protection, giving you fine-grained control over what AI can and can't see.*\n\n### GitLab Duo Context Exclusion for granular data protection\n\nIt's no surprise — you need granular control over what information AI agents can access. **GitLab Duo Context Exclusion** in 18.4 provides project-level settings that let teams exclude specific files or file paths from AI access. Capabilities include:\n\n* **File-specific exclusions** to help protect sensitive files such as password configurations, secrets, and proprietary algorithms.\n* **Path-based rules** to create exclusion patterns based on directory structures or file naming conventions.\n* **Flexible configuration** to apply exclusions at the project level while maintaining development workflow efficiency.\n* **Audit visibility** to track what content is excluded to support compliance with data governance policies.\n\nGitLab Duo Context Exclusion helps you protect sensitive data while you accelerate development with agentic AI.\n\n## Extend your AI capabilities with new MCP tools\n\n*Expanded MCP tools extend those capabilities even further, connecting your GitLab environment with a broader ecosystem of intelligent agents.*\n\n### New tools for GitLab MCP server\n\nExpanding on the initial MCP server introduced in [18.3](https://about.gitlab.com/blog/gitlab-18-3-expanding-ai-orchestration-in-software-engineering/), GitLab 18.4 adds more MCP tools — capabilities that define how MCP clients interact with GitLab. These new tools extend integration possibilities, enabling both first-party and third-party AI agents to take on richer tasks such as accessing project data, performing code operations, or searching across repositories, all while respecting existing security and permissions models. For a full list of MCP tools, including the new additions in 18.4, visit our [MCP server documentation](https://docs.gitlab.com/user/gitlab_duo/model_context_protocol/mcp_server/).\n\n## Experience the future of intelligent software development\n\nWith [GitLab Duo Agent Platform](https://about.gitlab.com/gitlab-duo-agent-platform/), engineers can begin to move from working on one issue at a time in single threaded fashion, to multi-threaded collaboration with asynchronous agents that act like teammates to get work done, faster. We are bringing to market this unique vision with our customer's preferences for independence and choice: run in your preferred cloud environments using the LLMs and AI tools that work best for you, within the security and compliance guardrails you set.\n\nAs an integral part of this innovation, GitLab 18.4 is more than a software upgrade — it's about making the day-to-day experience of developers smoother, smarter, and more secure. From reusable agents to business-aware pipeline fixes, every feature is designed to keep teams in flow while balancing speed, security, and control. For a deeper look at how these capabilities come together in practice, check out our walkthrough video.\n\n\n\u003Cdiv>\u003Ciframe src=\"https://player.vimeo.com/video/1120288083?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"A day in the life with GitLab Duo Agent Platform\">\u003C/iframe>\u003C/div>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\u003Cp>\u003C/p>\n\nGitLab Premium and Ultimate users can start using these capabilities today on [GitLab.com](https://GitLab.com) and self-managed environments, with availability for [GitLab Dedicated](https://about.gitlab.com/dedicated/) customers coming next month.\n\n> **Enable beta and experimental features in GitLab Duo Agent Platform today** and experience how full-context AI can transform the way your teams build software. New to GitLab? [Start your free trial](https://about.gitlab.com/free-trial/devsecops/) and see why the future of development is AI-powered, secure, and orchestrated through the world's most comprehensive DevSecOps platform.\n\n## Stay up to date with GitLab\n\nTo make sure you're getting the latest features, security updates, and performance improvements, we recommend keeping your GitLab instance up to date. The following resources can help you plan and complete your upgrade:\n\n* [Upgrade Path Tool](https://gitlab-com.gitlab.io/support/toolbox/upgrade-path/) – enter your current version and see the exact upgrade steps for your instance\n* [Upgrade documentation](https://docs.gitlab.com/update/upgrade_paths/) – detailed guides for each supported version, including requirements, step-by-step instructions, and best practices\n\nBy upgrading regularly, you'll ensure your team benefits from the newest GitLab capabilities and remains secure and supported.\n\nFor organizations that want a hands-off approach, consider [GitLab's Managed Maintenance service](https://content.gitlab.com/viewer/d1fe944dddb06394e6187f0028f010ad#1). With Managed Maintenance, your team stays focused on innovation while GitLab experts keep your Self-Managed instance reliably upgraded, secure, and ready to lead in DevSecOps. Ask your account manager for more information.\n\n\n*This blog post contains \"forward-looking statements\" within the meaning of Section 27A of the Securities Act of 1933, as amended, and Section 21E of the Securities Exchange Act of 1934. Although we believe that the expectations reflected in these statements are reasonable, they are subject to known and unknown risks, uncertainties, assumptions and other factors that may cause actual results or outcomes to differ materially. Further information on these risks and other factors is included under the caption \"Risk Factors\" in our filings with the SEC. We do not undertake any obligation to update or revise these statements after the date of this blog post, except as required by law.*\n",{"config":32,"title":5,"description":17},{"noIndex":33},false,"en-us/blog/gitlab-18-4-ai-native-development-with-automation-and-insight",[36,22,23,37],"aiml","devsecops-platform",[21,22,23,24],"119fbDyBEEkPvtFabkOSbCDimrglTOitujqqf5FSFoc",{"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":15,"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":701},"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",[496,543,596,640,667],{"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":15},"cookie preferences","ot-sdk-btn",{"title":92,"links":544,"subMenu":552},[545,548],{"text":24,"config":546},{"href":74,"dataGaName":547,"dataGaLocation":479},"devsecops platform",{"text":549,"config":550},"AI-Assisted Development",{"href":81,"dataGaName":551,"dataGaLocation":479},"ai-assisted development",[553],{"title":554,"links":555},"Topics",[556,561,566,571,576,581,586,591],{"text":557,"config":558},"CICD",{"href":559,"dataGaName":560,"dataGaLocation":479},"/topics/ci-cd/","cicd",{"text":562,"config":563},"GitOps",{"href":564,"dataGaName":565,"dataGaLocation":479},"/topics/gitops/","gitops",{"text":567,"config":568},"DevOps",{"href":569,"dataGaName":570,"dataGaLocation":479},"/topics/devops/","devops",{"text":572,"config":573},"Version Control",{"href":574,"dataGaName":575,"dataGaLocation":479},"/topics/version-control/","version control",{"text":577,"config":578},"DevSecOps",{"href":579,"dataGaName":580,"dataGaLocation":479},"/topics/devsecops/","devsecops",{"text":582,"config":583},"Cloud Native",{"href":584,"dataGaName":585,"dataGaLocation":479},"/topics/cloud-native/","cloud native",{"text":587,"config":588},"AI for Coding",{"href":589,"dataGaName":590,"dataGaLocation":479},"/topics/devops/ai-for-coding/","ai for coding",{"text":592,"config":593},"Agentic AI",{"href":594,"dataGaName":595,"dataGaLocation":479},"/topics/agentic-ai/","agentic ai",{"title":597,"links":598},"Solutions",[599,601,603,608,612,615,619,622,624,627,630,635],{"text":136,"config":600},{"href":131,"dataGaName":136,"dataGaLocation":479},{"text":125,"config":602},{"href":108,"dataGaName":109,"dataGaLocation":479},{"text":604,"config":605},"Agile development",{"href":606,"dataGaName":607,"dataGaLocation":479},"/solutions/agile-delivery/","agile delivery",{"text":609,"config":610},"SCM",{"href":121,"dataGaName":611,"dataGaLocation":479},"source code management",{"text":557,"config":613},{"href":114,"dataGaName":614,"dataGaLocation":479},"continuous integration & delivery",{"text":616,"config":617},"Value stream management",{"href":164,"dataGaName":618,"dataGaLocation":479},"value stream management",{"text":562,"config":620},{"href":621,"dataGaName":565,"dataGaLocation":479},"/solutions/gitops/",{"text":174,"config":623},{"href":177,"dataGaName":178,"dataGaLocation":479},{"text":625,"config":626},"Small business",{"href":183,"dataGaName":184,"dataGaLocation":479},{"text":628,"config":629},"Public sector",{"href":189,"dataGaName":190,"dataGaLocation":479},{"text":631,"config":632},"Education",{"href":633,"dataGaName":634,"dataGaLocation":479},"/solutions/education/","education",{"text":636,"config":637},"Financial services",{"href":638,"dataGaName":639,"dataGaLocation":479},"/solutions/finance/","financial services",{"title":197,"links":641},[642,644,646,648,651,653,655,657,659,661,663,665],{"text":210,"config":643},{"href":212,"dataGaName":213,"dataGaLocation":479},{"text":215,"config":645},{"href":217,"dataGaName":218,"dataGaLocation":479},{"text":220,"config":647},{"href":222,"dataGaName":223,"dataGaLocation":479},{"text":225,"config":649},{"href":227,"dataGaName":650,"dataGaLocation":479},"docs",{"text":248,"config":652},{"href":250,"dataGaName":251,"dataGaLocation":479},{"text":243,"config":654},{"href":245,"dataGaName":246,"dataGaLocation":479},{"text":257,"config":656},{"href":259,"dataGaName":260,"dataGaLocation":479},{"text":265,"config":658},{"href":267,"dataGaName":268,"dataGaLocation":479},{"text":270,"config":660},{"href":272,"dataGaName":273,"dataGaLocation":479},{"text":275,"config":662},{"href":277,"dataGaName":278,"dataGaLocation":479},{"text":280,"config":664},{"href":282,"dataGaName":283,"dataGaLocation":479},{"text":285,"config":666},{"href":287,"dataGaName":288,"dataGaLocation":479},{"title":301,"links":668},[669,671,673,675,677,679,681,685,690,692,694,696],{"text":309,"config":670},{"href":311,"dataGaName":303,"dataGaLocation":479},{"text":314,"config":672},{"href":316,"dataGaName":317,"dataGaLocation":479},{"text":322,"config":674},{"href":324,"dataGaName":325,"dataGaLocation":479},{"text":327,"config":676},{"href":329,"dataGaName":330,"dataGaLocation":479},{"text":332,"config":678},{"href":334,"dataGaName":335,"dataGaLocation":479},{"text":337,"config":680},{"href":339,"dataGaName":340,"dataGaLocation":479},{"text":682,"config":683},"Sustainability",{"href":684,"dataGaName":682,"dataGaLocation":479},"/sustainability/",{"text":686,"config":687},"Diversity, inclusion and belonging (DIB)",{"href":688,"dataGaName":689,"dataGaLocation":479},"/diversity-inclusion-belonging/","Diversity, inclusion and belonging",{"text":342,"config":691},{"href":344,"dataGaName":345,"dataGaLocation":479},{"text":352,"config":693},{"href":354,"dataGaName":355,"dataGaLocation":479},{"text":357,"config":695},{"href":359,"dataGaName":360,"dataGaLocation":479},{"text":697,"config":698},"Modern Slavery Transparency Statement",{"href":699,"dataGaName":700,"dataGaLocation":479},"https://handbook.gitlab.com/handbook/legal/modern-slavery-act-transparency-statement/","modern slavery transparency statement",{"items":702},[703,706,709],{"text":704,"config":705},"Terms",{"href":531,"dataGaName":532,"dataGaLocation":479},{"text":707,"config":708},"Cookies",{"dataGaName":541,"dataGaLocation":479,"id":542,"isOneTrustButton":15},{"text":710,"config":711},"Privacy",{"href":536,"dataGaName":537,"dataGaLocation":479},[713],{"id":714,"title":9,"body":27,"config":715,"content":717,"description":27,"extension":721,"meta":722,"navigation":15,"path":723,"seo":724,"stem":725,"__hash__":726},"blogAuthors/en-us/blog/authors/bill-staples.yml",{"template":716},"BlogAuthor",{"name":9,"config":718,"role":720},{"headshot":719},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1750434080/glxv59lh9qftpdbsb4ph.png","CEO","yml",{},"/en-us/blog/authors/bill-staples",{},"en-us/blog/authors/bill-staples","K-ulWVa7KOFAxgiGSmeiIjz3KeQyIkhm95lIRX_r6Zc",[728,740,752],{"content":729,"config":738},{"title":730,"description":731,"authors":732,"date":734,"heroImage":735,"body":736,"category":11,"tags":737},"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.",[733],"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).**",[21,22],{"featured":15,"template":13,"slug":739},"atlassian-will-train-on-your-data-opt-out-with-gitlab",{"content":741,"config":750},{"title":742,"description":743,"authors":744,"heroImage":746,"date":747,"body":748,"category":11,"tags":749},"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.",[745],"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/).",[21,22,288],{"featured":15,"template":13,"slug":751},"gitlab-and-anthropic-governed-ai-for-enterprise-development",{"content":753,"config":763},{"title":754,"description":755,"authors":756,"heroImage":758,"date":759,"body":760,"category":11,"tags":761},"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.",[757],"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",[21,22,762],"tutorial",{"featured":15,"template":13,"slug":764},"give-your-ai-agent-direct-structured-gitlab-access-with-glab-cli",{"promotions":766},[767,780,791,803],{"id":768,"categories":769,"header":770,"text":771,"button":772,"image":777},"ai-modernization",[11],"Is AI achieving its promise at scale?","Quiz will take 5 minutes or less",{"text":773,"config":774},"Get your AI maturity score",{"href":775,"dataGaName":776,"dataGaLocation":251},"/assessments/ai-modernization-assessment/","modernization assessment",{"config":778},{"src":779},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/qix0m7kwnd8x2fh1zq49.png",{"id":781,"categories":782,"header":783,"text":771,"button":784,"image":788},"devops-modernization",[22,580],"Are you just managing tools or shipping innovation?",{"text":785,"config":786},"Get your DevOps maturity score",{"href":787,"dataGaName":776,"dataGaLocation":251},"/assessments/devops-modernization-assessment/",{"config":789},{"src":790},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138785/eg818fmakweyuznttgid.png",{"id":792,"categories":793,"header":795,"text":771,"button":796,"image":800},"security-modernization",[794],"security","Are you trading speed for security?",{"text":797,"config":798},"Get your security maturity score",{"href":799,"dataGaName":776,"dataGaLocation":251},"/assessments/security-modernization-assessment/",{"config":801},{"src":802},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/p4pbqd9nnjejg5ds6mdk.png",{"id":804,"paths":805,"header":808,"text":809,"button":810,"image":815},"github-azure-migration",[806,807],"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":811,"config":812},"See how GitLab compares to GitHub",{"href":813,"dataGaName":814,"dataGaLocation":251},"/compare/gitlab-vs-github/github-azure-migration/","github azure migration",{"config":816},{"src":790},{"header":818,"blurb":819,"button":820,"secondaryButton":825},"Start building faster today","See what your team can do with the intelligent orchestration platform for DevSecOps.\n",{"text":821,"config":822},"Get your free trial",{"href":823,"dataGaName":50,"dataGaLocation":824},"https://gitlab.com/-/trial_registrations/new?glm_content=default-saas-trial&glm_source=about.gitlab.com/","feature",{"text":517,"config":826},{"href":54,"dataGaName":55,"dataGaLocation":824},1777934933091]