[{"data":1,"prerenderedAt":796},["ShallowReactive",2],{"/en-us/blog/categories/ai-ml":3,"navigation-en-us":21,"banner-en-us":431,"footer-en-us":441,"ai-ml-category-page-total-items-en-us":683,"ai-ml-category-page-featured-en-us":684,"ai-ml-category-page-10-en-us":713},{"id":4,"title":5,"body":6,"category":6,"config":7,"content":11,"description":6,"extension":13,"meta":14,"navigation":15,"path":16,"seo":17,"slug":6,"stem":19,"testContent":6,"type":6,"__hash__":20},"blogCategories/en-us/blog/categories/ai-ml.yml","Ai Ml",null,{"template":8,"slug":9,"hide":10},"BlogCategory","ai-ml",false,{"name":12},"AI/ML","yml",{},true,"/en-us/blog/categories/ai-ml",{"title":12,"description":18},"Browse articles related to AI/ML on the GitLab Blog","en-us/blog/categories/ai-ml","rEmbrx2EiZNCvAIStbsvNZ9AHldybfSqbXcgAnBzrUY",{"data":22},{"logo":23,"freeTrial":28,"sales":33,"login":38,"items":43,"search":351,"minimal":382,"duo":401,"switchNav":410,"pricingDeployment":421},{"config":24},{"href":25,"dataGaName":26,"dataGaLocation":27},"/","gitlab logo","header",{"text":29,"config":30},"Get free trial",{"href":31,"dataGaName":32,"dataGaLocation":27},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com&glm_content=default-saas-trial/","free trial",{"text":34,"config":35},"Talk to sales",{"href":36,"dataGaName":37,"dataGaLocation":27},"/sales/","sales",{"text":39,"config":40},"Sign in",{"href":41,"dataGaName":42,"dataGaLocation":27},"https://gitlab.com/users/sign_in/","sign in",[44,71,166,171,272,332],{"text":45,"config":46,"cards":48},"Platform",{"dataNavLevelOne":47},"platform",[49,55,63],{"title":45,"description":50,"link":51},"The intelligent orchestration platform for DevSecOps",{"text":52,"config":53},"Explore our Platform",{"href":54,"dataGaName":47,"dataGaLocation":27},"/platform/",{"title":56,"description":57,"link":58},"GitLab Duo Agent Platform","Agentic AI for the entire software lifecycle",{"text":59,"config":60},"Meet GitLab Duo",{"href":61,"dataGaName":62,"dataGaLocation":27},"/gitlab-duo-agent-platform/","gitlab duo agent platform",{"title":64,"description":65,"link":66},"Why GitLab","See the top reasons enterprises choose GitLab",{"text":67,"config":68},"Learn more",{"href":69,"dataGaName":70,"dataGaLocation":27},"/why-gitlab/","why gitlab",{"text":72,"left":15,"config":73,"link":75,"lists":79,"footer":148},"Product",{"dataNavLevelOne":74},"solutions",{"text":76,"config":77},"View all Solutions",{"href":78,"dataGaName":74,"dataGaLocation":27},"/solutions/",[80,104,127],{"title":81,"description":82,"link":83,"items":88},"Automation","CI/CD and automation to accelerate deployment",{"config":84},{"icon":85,"href":86,"dataGaName":87,"dataGaLocation":27},"AutomatedCodeAlt","/solutions/delivery-automation/","automated software delivery",[89,93,96,100],{"text":90,"config":91},"CI/CD",{"href":92,"dataGaLocation":27,"dataGaName":90},"/solutions/continuous-integration/",{"text":56,"config":94},{"href":61,"dataGaLocation":27,"dataGaName":95},"gitlab duo agent platform - product menu",{"text":97,"config":98},"Source Code Management",{"href":99,"dataGaLocation":27,"dataGaName":97},"/solutions/source-code-management/",{"text":101,"config":102},"Automated Software Delivery",{"href":86,"dataGaLocation":27,"dataGaName":103},"Automated software delivery",{"title":105,"description":106,"link":107,"items":112},"Security","Deliver code faster without compromising security",{"config":108},{"href":109,"dataGaName":110,"dataGaLocation":27,"icon":111},"/solutions/application-security-testing/","security and compliance","ShieldCheckLight",[113,117,122],{"text":114,"config":115},"Application Security Testing",{"href":109,"dataGaName":116,"dataGaLocation":27},"Application security testing",{"text":118,"config":119},"Software Supply Chain Security",{"href":120,"dataGaLocation":27,"dataGaName":121},"/solutions/supply-chain/","Software supply chain security",{"text":123,"config":124},"Software Compliance",{"href":125,"dataGaName":126,"dataGaLocation":27},"/solutions/software-compliance/","software compliance",{"title":128,"link":129,"items":134},"Measurement",{"config":130},{"icon":131,"href":132,"dataGaName":133,"dataGaLocation":27},"DigitalTransformation","/solutions/visibility-measurement/","visibility and measurement",[135,139,143],{"text":136,"config":137},"Visibility & Measurement",{"href":132,"dataGaLocation":27,"dataGaName":138},"Visibility and Measurement",{"text":140,"config":141},"Value Stream Management",{"href":142,"dataGaLocation":27,"dataGaName":140},"/solutions/value-stream-management/",{"text":144,"config":145},"Analytics & Insights",{"href":146,"dataGaLocation":27,"dataGaName":147},"/solutions/analytics-and-insights/","Analytics and insights",{"title":149,"items":150},"GitLab for",[151,156,161],{"text":152,"config":153},"Enterprise",{"href":154,"dataGaLocation":27,"dataGaName":155},"/enterprise/","enterprise",{"text":157,"config":158},"Small Business",{"href":159,"dataGaLocation":27,"dataGaName":160},"/small-business/","small business",{"text":162,"config":163},"Public Sector",{"href":164,"dataGaLocation":27,"dataGaName":165},"/solutions/public-sector/","public sector",{"text":167,"config":168},"Pricing",{"href":169,"dataGaName":170,"dataGaLocation":27,"dataNavLevelOne":170},"/pricing/","pricing",{"text":172,"config":173,"link":175,"lists":179,"feature":259},"Resources",{"dataNavLevelOne":174},"resources",{"text":176,"config":177},"View all resources",{"href":178,"dataGaName":174,"dataGaLocation":27},"/resources/",[180,213,231],{"title":181,"items":182},"Getting started",[183,188,193,198,203,208],{"text":184,"config":185},"Install",{"href":186,"dataGaName":187,"dataGaLocation":27},"/install/","install",{"text":189,"config":190},"Quick start guides",{"href":191,"dataGaName":192,"dataGaLocation":27},"/get-started/","quick setup checklists",{"text":194,"config":195},"Learn",{"href":196,"dataGaLocation":27,"dataGaName":197},"https://university.gitlab.com/","learn",{"text":199,"config":200},"Product documentation",{"href":201,"dataGaName":202,"dataGaLocation":27},"https://docs.gitlab.com/","product documentation",{"text":204,"config":205},"Best practice videos",{"href":206,"dataGaName":207,"dataGaLocation":27},"/getting-started-videos/","best practice videos",{"text":209,"config":210},"Integrations",{"href":211,"dataGaName":212,"dataGaLocation":27},"/integrations/","integrations",{"title":214,"items":215},"Discover",[216,221,226],{"text":217,"config":218},"Customer success stories",{"href":219,"dataGaName":220,"dataGaLocation":27},"/customers/","customer success stories",{"text":222,"config":223},"Blog",{"href":224,"dataGaName":225,"dataGaLocation":27},"/blog/","blog",{"text":227,"config":228},"Remote",{"href":229,"dataGaName":230,"dataGaLocation":27},"https://handbook.gitlab.com/handbook/company/culture/all-remote/","remote",{"title":232,"items":233},"Connect",[234,239,244,249,254],{"text":235,"config":236},"GitLab Services",{"href":237,"dataGaName":238,"dataGaLocation":27},"/services/","services",{"text":240,"config":241},"Community",{"href":242,"dataGaName":243,"dataGaLocation":27},"/community/","community",{"text":245,"config":246},"Forum",{"href":247,"dataGaName":248,"dataGaLocation":27},"https://forum.gitlab.com/","forum",{"text":250,"config":251},"Events",{"href":252,"dataGaName":253,"dataGaLocation":27},"/events/","events",{"text":255,"config":256},"Partners",{"href":257,"dataGaName":258,"dataGaLocation":27},"/partners/","partners",{"backgroundColor":260,"textColor":261,"text":262,"image":263,"link":267},"#2f2a6b","#fff","Insights for the future of software development",{"altText":264,"config":265},"the source promo card",{"src":266},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758208064/dzl0dbift9xdizyelkk4.svg",{"text":268,"config":269},"Read the latest",{"href":270,"dataGaName":271,"dataGaLocation":27},"/the-source/","the source",{"text":273,"config":274,"lists":276},"Company",{"dataNavLevelOne":275},"company",[277],{"items":278},[279,284,290,292,297,302,307,312,317,322,327],{"text":280,"config":281},"About",{"href":282,"dataGaName":283,"dataGaLocation":27},"/company/","about",{"text":285,"config":286,"footerGa":289},"Jobs",{"href":287,"dataGaName":288,"dataGaLocation":27},"/jobs/","jobs",{"dataGaName":288},{"text":250,"config":291},{"href":252,"dataGaName":253,"dataGaLocation":27},{"text":293,"config":294},"Leadership",{"href":295,"dataGaName":296,"dataGaLocation":27},"/company/team/e-group/","leadership",{"text":298,"config":299},"Team",{"href":300,"dataGaName":301,"dataGaLocation":27},"/company/team/","team",{"text":303,"config":304},"Handbook",{"href":305,"dataGaName":306,"dataGaLocation":27},"https://handbook.gitlab.com/","handbook",{"text":308,"config":309},"Investor relations",{"href":310,"dataGaName":311,"dataGaLocation":27},"https://ir.gitlab.com/","investor relations",{"text":313,"config":314},"Trust Center",{"href":315,"dataGaName":316,"dataGaLocation":27},"/security/","trust center",{"text":318,"config":319},"AI Transparency Center",{"href":320,"dataGaName":321,"dataGaLocation":27},"/ai-transparency-center/","ai transparency center",{"text":323,"config":324},"Newsletter",{"href":325,"dataGaName":326,"dataGaLocation":27},"/company/contact/#contact-forms","newsletter",{"text":328,"config":329},"Press",{"href":330,"dataGaName":331,"dataGaLocation":27},"/press/","press",{"text":333,"config":334,"lists":335},"Contact us",{"dataNavLevelOne":275},[336],{"items":337},[338,341,346],{"text":34,"config":339},{"href":36,"dataGaName":340,"dataGaLocation":27},"talk to sales",{"text":342,"config":343},"Support portal",{"href":344,"dataGaName":345,"dataGaLocation":27},"https://support.gitlab.com","support portal",{"text":347,"config":348},"Customer portal",{"href":349,"dataGaName":350,"dataGaLocation":27},"https://customers.gitlab.com/customers/sign_in/","customer portal",{"close":352,"login":353,"suggestions":360},"Close",{"text":354,"link":355},"To search repositories and projects, login to",{"text":356,"config":357},"gitlab.com",{"href":41,"dataGaName":358,"dataGaLocation":359},"search login","search",{"text":361,"default":362},"Suggestions",[363,365,369,371,375,379],{"text":56,"config":364},{"href":61,"dataGaName":56,"dataGaLocation":359},{"text":366,"config":367},"Code Suggestions (AI)",{"href":368,"dataGaName":366,"dataGaLocation":359},"/solutions/code-suggestions/",{"text":90,"config":370},{"href":92,"dataGaName":90,"dataGaLocation":359},{"text":372,"config":373},"GitLab on AWS",{"href":374,"dataGaName":372,"dataGaLocation":359},"/partners/technology-partners/aws/",{"text":376,"config":377},"GitLab on Google Cloud",{"href":378,"dataGaName":376,"dataGaLocation":359},"/partners/technology-partners/google-cloud-platform/",{"text":380,"config":381},"Why GitLab?",{"href":69,"dataGaName":380,"dataGaLocation":359},{"freeTrial":383,"mobileIcon":388,"desktopIcon":393,"secondaryButton":396},{"text":384,"config":385},"Start free trial",{"href":386,"dataGaName":32,"dataGaLocation":387},"https://gitlab.com/-/trials/new/","nav",{"altText":389,"config":390},"Gitlab Icon",{"src":391,"dataGaName":392,"dataGaLocation":387},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203874/jypbw1jx72aexsoohd7x.svg","gitlab icon",{"altText":389,"config":394},{"src":395,"dataGaName":392,"dataGaLocation":387},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203875/gs4c8p8opsgvflgkswz9.svg",{"text":397,"config":398},"Get Started",{"href":399,"dataGaName":400,"dataGaLocation":387},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com/get-started/","get started",{"freeTrial":402,"mobileIcon":406,"desktopIcon":408},{"text":403,"config":404},"Learn more about GitLab Duo",{"href":61,"dataGaName":405,"dataGaLocation":387},"gitlab duo",{"altText":389,"config":407},{"src":391,"dataGaName":392,"dataGaLocation":387},{"altText":389,"config":409},{"src":395,"dataGaName":392,"dataGaLocation":387},{"button":411,"mobileIcon":416,"desktopIcon":418},{"text":412,"config":413},"/switch",{"href":414,"dataGaName":415,"dataGaLocation":387},"#contact","switch",{"altText":389,"config":417},{"src":391,"dataGaName":392,"dataGaLocation":387},{"altText":389,"config":419},{"src":420,"dataGaName":392,"dataGaLocation":387},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1773335277/ohhpiuoxoldryzrnhfrh.png",{"freeTrial":422,"mobileIcon":427,"desktopIcon":429},{"text":423,"config":424},"Back to pricing",{"href":169,"dataGaName":425,"dataGaLocation":387,"icon":426},"back to pricing","GoBack",{"altText":389,"config":428},{"src":391,"dataGaName":392,"dataGaLocation":387},{"altText":389,"config":430},{"src":395,"dataGaName":392,"dataGaLocation":387},{"title":432,"button":433,"config":438},"See how agentic AI transforms software delivery",{"text":434,"config":435},"Watch GitLab Transcend now",{"href":436,"dataGaName":437,"dataGaLocation":27},"/events/transcend/virtual/","transcend event",{"layout":439,"icon":440,"disabled":15},"release","AiStar",{"data":442},{"text":443,"source":444,"edit":450,"contribute":455,"config":460,"items":465,"minimal":672},"Git is a trademark of Software Freedom Conservancy and our use of 'GitLab' is under license",{"text":445,"config":446},"View page source",{"href":447,"dataGaName":448,"dataGaLocation":449},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/","page source","footer",{"text":451,"config":452},"Edit this page",{"href":453,"dataGaName":454,"dataGaLocation":449},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/content/","web ide",{"text":456,"config":457},"Please contribute",{"href":458,"dataGaName":459,"dataGaLocation":449},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/CONTRIBUTING.md/","please contribute",{"twitter":461,"facebook":462,"youtube":463,"linkedin":464},"https://twitter.com/gitlab","https://www.facebook.com/gitlab","https://www.youtube.com/channel/UCnMGQ8QHMAnVIsI3xJrihhg","https://www.linkedin.com/company/gitlab-com",[466,513,567,611,638],{"title":167,"links":467,"subMenu":482},[468,472,477],{"text":469,"config":470},"View plans",{"href":169,"dataGaName":471,"dataGaLocation":449},"view plans",{"text":473,"config":474},"Why Premium?",{"href":475,"dataGaName":476,"dataGaLocation":449},"/pricing/premium/","why premium",{"text":478,"config":479},"Why Ultimate?",{"href":480,"dataGaName":481,"dataGaLocation":449},"/pricing/ultimate/","why ultimate",[483],{"title":484,"links":485},"Contact Us",[486,489,491,493,498,503,508],{"text":487,"config":488},"Contact sales",{"href":36,"dataGaName":37,"dataGaLocation":449},{"text":342,"config":490},{"href":344,"dataGaName":345,"dataGaLocation":449},{"text":347,"config":492},{"href":349,"dataGaName":350,"dataGaLocation":449},{"text":494,"config":495},"Status",{"href":496,"dataGaName":497,"dataGaLocation":449},"https://status.gitlab.com/","status",{"text":499,"config":500},"Terms of use",{"href":501,"dataGaName":502,"dataGaLocation":449},"/terms/","terms of use",{"text":504,"config":505},"Privacy statement",{"href":506,"dataGaName":507,"dataGaLocation":449},"/privacy/","privacy statement",{"text":509,"config":510},"Cookie preferences",{"dataGaName":511,"dataGaLocation":449,"id":512,"isOneTrustButton":15},"cookie preferences","ot-sdk-btn",{"title":72,"links":514,"subMenu":523},[515,519],{"text":516,"config":517},"DevSecOps platform",{"href":54,"dataGaName":518,"dataGaLocation":449},"devsecops platform",{"text":520,"config":521},"AI-Assisted Development",{"href":61,"dataGaName":522,"dataGaLocation":449},"ai-assisted development",[524],{"title":525,"links":526},"Topics",[527,532,537,542,547,552,557,562],{"text":528,"config":529},"CICD",{"href":530,"dataGaName":531,"dataGaLocation":449},"/topics/ci-cd/","cicd",{"text":533,"config":534},"GitOps",{"href":535,"dataGaName":536,"dataGaLocation":449},"/topics/gitops/","gitops",{"text":538,"config":539},"DevOps",{"href":540,"dataGaName":541,"dataGaLocation":449},"/topics/devops/","devops",{"text":543,"config":544},"Version Control",{"href":545,"dataGaName":546,"dataGaLocation":449},"/topics/version-control/","version control",{"text":548,"config":549},"DevSecOps",{"href":550,"dataGaName":551,"dataGaLocation":449},"/topics/devsecops/","devsecops",{"text":553,"config":554},"Cloud Native",{"href":555,"dataGaName":556,"dataGaLocation":449},"/topics/cloud-native/","cloud native",{"text":558,"config":559},"AI for Coding",{"href":560,"dataGaName":561,"dataGaLocation":449},"/topics/devops/ai-for-coding/","ai for coding",{"text":563,"config":564},"Agentic AI",{"href":565,"dataGaName":566,"dataGaLocation":449},"/topics/agentic-ai/","agentic ai",{"title":568,"links":569},"Solutions",[570,572,574,579,583,586,590,593,595,598,601,606],{"text":114,"config":571},{"href":109,"dataGaName":114,"dataGaLocation":449},{"text":103,"config":573},{"href":86,"dataGaName":87,"dataGaLocation":449},{"text":575,"config":576},"Agile development",{"href":577,"dataGaName":578,"dataGaLocation":449},"/solutions/agile-delivery/","agile delivery",{"text":580,"config":581},"SCM",{"href":99,"dataGaName":582,"dataGaLocation":449},"source code management",{"text":528,"config":584},{"href":92,"dataGaName":585,"dataGaLocation":449},"continuous integration & delivery",{"text":587,"config":588},"Value stream management",{"href":142,"dataGaName":589,"dataGaLocation":449},"value stream management",{"text":533,"config":591},{"href":592,"dataGaName":536,"dataGaLocation":449},"/solutions/gitops/",{"text":152,"config":594},{"href":154,"dataGaName":155,"dataGaLocation":449},{"text":596,"config":597},"Small business",{"href":159,"dataGaName":160,"dataGaLocation":449},{"text":599,"config":600},"Public sector",{"href":164,"dataGaName":165,"dataGaLocation":449},{"text":602,"config":603},"Education",{"href":604,"dataGaName":605,"dataGaLocation":449},"/solutions/education/","education",{"text":607,"config":608},"Financial services",{"href":609,"dataGaName":610,"dataGaLocation":449},"/solutions/finance/","financial services",{"title":172,"links":612},[613,615,617,619,622,624,626,628,630,632,634,636],{"text":184,"config":614},{"href":186,"dataGaName":187,"dataGaLocation":449},{"text":189,"config":616},{"href":191,"dataGaName":192,"dataGaLocation":449},{"text":194,"config":618},{"href":196,"dataGaName":197,"dataGaLocation":449},{"text":199,"config":620},{"href":201,"dataGaName":621,"dataGaLocation":449},"docs",{"text":222,"config":623},{"href":224,"dataGaName":225,"dataGaLocation":449},{"text":217,"config":625},{"href":219,"dataGaName":220,"dataGaLocation":449},{"text":227,"config":627},{"href":229,"dataGaName":230,"dataGaLocation":449},{"text":235,"config":629},{"href":237,"dataGaName":238,"dataGaLocation":449},{"text":240,"config":631},{"href":242,"dataGaName":243,"dataGaLocation":449},{"text":245,"config":633},{"href":247,"dataGaName":248,"dataGaLocation":449},{"text":250,"config":635},{"href":252,"dataGaName":253,"dataGaLocation":449},{"text":255,"config":637},{"href":257,"dataGaName":258,"dataGaLocation":449},{"title":273,"links":639},[640,642,644,646,648,650,652,656,661,663,665,667],{"text":280,"config":641},{"href":282,"dataGaName":275,"dataGaLocation":449},{"text":285,"config":643},{"href":287,"dataGaName":288,"dataGaLocation":449},{"text":293,"config":645},{"href":295,"dataGaName":296,"dataGaLocation":449},{"text":298,"config":647},{"href":300,"dataGaName":301,"dataGaLocation":449},{"text":303,"config":649},{"href":305,"dataGaName":306,"dataGaLocation":449},{"text":308,"config":651},{"href":310,"dataGaName":311,"dataGaLocation":449},{"text":653,"config":654},"Sustainability",{"href":655,"dataGaName":653,"dataGaLocation":449},"/sustainability/",{"text":657,"config":658},"Diversity, inclusion and belonging (DIB)",{"href":659,"dataGaName":660,"dataGaLocation":449},"/diversity-inclusion-belonging/","Diversity, inclusion and belonging",{"text":313,"config":662},{"href":315,"dataGaName":316,"dataGaLocation":449},{"text":323,"config":664},{"href":325,"dataGaName":326,"dataGaLocation":449},{"text":328,"config":666},{"href":330,"dataGaName":331,"dataGaLocation":449},{"text":668,"config":669},"Modern Slavery Transparency Statement",{"href":670,"dataGaName":671,"dataGaLocation":449},"https://handbook.gitlab.com/handbook/legal/modern-slavery-act-transparency-statement/","modern slavery transparency statement",{"items":673},[674,677,680],{"text":675,"config":676},"Terms",{"href":501,"dataGaName":502,"dataGaLocation":449},{"text":678,"config":679},"Cookies",{"dataGaName":511,"dataGaLocation":449,"id":512,"isOneTrustButton":15},{"text":681,"config":682},"Privacy",{"href":506,"dataGaName":507,"dataGaLocation":449},145,{"id":685,"title":686,"authorSlugs":687,"body":6,"categorySlug":9,"config":689,"content":692,"description":6,"extension":13,"isFeatured":15,"meta":703,"navigation":15,"path":704,"publishedDate":698,"seo":705,"stem":709,"tagSlugs":710,"__hash__":712},"blogPosts/en-us/blog/give-your-ai-agent-direct-structured-gitlab-access-with-glab-cli.yml","Give Your Ai Agent Direct Structured Gitlab Access With Glab Cli",[688],"kai-armstrong",{"featured":15,"template":690,"slug":691},"BlogPost","give-your-ai-agent-direct-structured-gitlab-access-with-glab-cli",{"title":693,"description":694,"authors":695,"heroImage":697,"date":698,"body":699,"category":9,"tags":700},"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.",[696],"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",[12,701,702],"product","tutorial",{},"/en-us/blog/give-your-ai-agent-direct-structured-gitlab-access-with-glab-cli",{"config":706,"title":707,"description":708},{"noIndex":10},"Give your AI agent direct GitLab access with glab CLI","This tutorial shows how GitLab CLI (glab) provides AI agents structured, reliable access to projects via the MCP, eliminating friction.","en-us/blog/give-your-ai-agent-direct-structured-gitlab-access-with-glab-cli",[711,701,702],"aiml","UU4cHjm3jVa6RcTLVG2hTy3r28PO_iEIRS-hNGsHpuE",[714,723,733,743,752,760,769,779,788],{"content":715,"config":721},{"title":716,"heroImage":717,"category":9,"description":718,"authors":719},"Use GitLab AI features out-of-the-box in a GitLab Workspace","https://res.cloudinary.com/about-gitlab-com/image/upload/v1750098843/Blog/Hero%20Images/Blog/Hero%20Images/securitylifecycle-light_securitylifecycle-light.png_1750098843047.png","GitLab Workspaces now ships with the GitLab workflow extension preinstalled, providing access to powerful AI features like GitLab Duo Chat and Code Suggestions for increased productivity.",[720],"Safwan Ahmed",{"externalUrl":-1,"slug":722},"use-gitlab-ai-features-out-of-the-box-in-a-gitlab-workspace",{"content":724,"config":731},{"title":725,"heroImage":726,"category":9,"description":727,"authors":728},"Developing GitLab Duo: Use AI to remediate security vulnerabilities ","https://res.cloudinary.com/about-gitlab-com/image/upload/v1750098106/Blog/Hero%20Images/Blog/Hero%20Images/blog-hero-banner-1-0178-820x470-fy25_7JlF3WlEkswGQbcTe8DOTB_1750098106040.png","This tutorial shows how GitLab Duo Vulnerability Explanation and GitLab Duo Vulnerability Resolution, along with our other AI-powered features, can help to address vulnerabilities quickly.",[729,730],"Michael Friedrich","Alana Bellucci",{"externalUrl":-1,"slug":732},"developing-gitlab-duo-use-ai-to-remediate-security-vulnerabilities",{"content":734,"config":741},{"title":735,"heroImage":736,"category":9,"description":737,"authors":738},"Developing GitLab Duo: A roundup of recent Chat enhancements","https://res.cloudinary.com/about-gitlab-com/image/upload/v1750098374/Blog/Hero%20Images/Blog/Hero%20Images/blog-hero-banner-1-0178-820x470-fy25_7JlF3WlEkswGQbcTe8DOTB_1750098374059.png","Discover the latest improvements to GitLab Duo Chat, including a new integration, prompt cancellation, and architectural upgrades.",[739,740],"Jannik Lehmann","David O'Regan",{"externalUrl":-1,"slug":742},"developing-gitlab-duo-a-roundup-of-recent-chat-enhancements",{"content":744,"config":750},{"title":745,"heroImage":746,"category":9,"description":747,"authors":748},"Meet GitLab Duo Workflow - the future of AI-driven development","https://res.cloudinary.com/about-gitlab-com/image/upload/v1749658912/Blog/Hero%20Images/blog-image-template-1800x945__20_.png","Workflow, our autonomous AI agent, will transform the way teams build and ship software – our first bold step towards AI-driven DevSecOps.",[749],"David DeSanto, Chief Product Officer, GitLab",{"externalUrl":-1,"slug":751},"meet-gitlab-duo-workflow-the-future-of-ai-driven-development",{"content":753,"config":758},{"title":754,"heroImage":755,"category":9,"description":756,"authors":757},"Top tips for efficient AI-powered Code Suggestions with GitLab Duo","https://res.cloudinary.com/about-gitlab-com/image/upload/v1749669095/Blog/Hero%20Images/gitlabduo.png","Explore best practices  for using Code Suggestions and how to combine it with our other AI features to greatly improve the developer experience (includes real-world exercises).",[729],{"externalUrl":-1,"slug":759},"top-tips-for-efficient-ai-powered-code-suggestions-with-gitlab-duo",{"content":761,"config":767},{"title":762,"heroImage":763,"category":9,"description":764,"authors":765},"Developing GitLab Duo: Blending AI and Root Cause Analysis to fix CI/CD pipelines","https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097321/Blog/Hero%20Images/Blog/Hero%20Images/blog-hero-banner-1-0178-820x470-fy25_7JlF3WlEkswGQbcTe8DOTB_1750097321081.png","Discover how we've infused Root Cause Analysis with AI to help remedy broken CI/CD pipelines, including example scenarios and take-away exercises.",[766,729],"Rutvik Shah",{"externalUrl":-1,"slug":768},"developing-gitlab-duo-blending-ai-and-root-cause-analysis-to-fix-ci-cd",{"content":770,"config":777},{"title":771,"heroImage":772,"category":9,"description":773,"authors":774},"Inside look: How GitLab's Test Platform team validates AI features","https://res.cloudinary.com/about-gitlab-com/image/upload/v1750099033/Blog/Hero%20Images/Blog/Hero%20Images/blog-image-template-1800x945%20%2811%29_78Dav6FR9EGjhebHWuBVan_1750099033422.png","Learn how we continuously analyze AI feature performance, including testing latency worldwide, and get to know our new AI continuous analysis tool.",[775,776],"Mark Lapierre","Vincy Wilson",{"externalUrl":-1,"slug":778},"inside-look-how-gitlabs-test-platform-team-validates-ai-features",{"content":780,"config":786},{"title":781,"heroImage":782,"category":9,"description":783,"authors":784},"Developing GitLab Duo series","https://res.cloudinary.com/about-gitlab-com/image/upload/v1749659856/Blog/Hero%20Images/blog-hero-banner-1-0178-820x470-fy25.png","Our unique blog series, written by our Product and Engineering teams, takes you behind the scenes of our AI innovation and guides you through our newest AI features powering your DevSecOps workflow.",[785],"GitLab Team",{"externalUrl":-1,"slug":787},"developing-gitlab-duo-series",{"content":789,"config":794},{"title":790,"heroImage":791,"category":9,"description":792,"authors":793},"Developing GitLab Duo: Secure and thoroughly test AI-generated code","https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097183/Blog/Hero%20Images/Blog/Hero%20Images/blog-hero-banner-1-0178-820x470-fy25_7JlF3WlEkswGQbcTe8DOTB_1750097183481.png","Learn step-by-step how to enhance AI-generated code reliability and security using GitLab Duo and GitLab Pages (includes code samples and prompts).",[740],{"externalUrl":-1,"slug":795},"how-gitlab-duo-helps-secure-and-thoroughly-test-ai-generated-code",1777475902341]