--- title: What's new in GitLab 19.3: agentic tools for dedicated... description: GitLab 19.3 adds the ability to deploy the AI Gateway for GitLab Duo Agent Platform inside a self-managed GitLab Dedicated single-tenant environment, keeping... canonical: https://daily.dev/posts/what-s-new-in-gitlab-19-3-agentic-tools-for-dedicated-environments-custom-flows-and-bulk-vulnerab-pkkpfwcck twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: What's new in GitLab 19.3: agentic tools for dedicated environments, custom flows, and bulk vulnerability triage | daily.dev og:description: GitLab 19.3 adds the ability to deploy the AI Gateway for GitLab Duo Agent Platform inside a self-managed GitLab Dedicated single-tenant environment, keeping... og:url: https://daily.dev/posts/what-s-new-in-gitlab-19-3-agentic-tools-for-dedicated-environments-custom-flows-and-bulk-vulnerab-pkkpfwcck og:image: https://api.daily.dev/og/posts/pkkpfwcck.png og:image:alt: What's new in GitLab 19.3: agentic tools for dedicated environments, custom flows, and bulk vulnerability triage og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # What's new in GitLab 19.3: agentic tools for dedicated environments, custom flows, and bulk vulnerability triage **[Collections](https://daily.dev/sources/collections)** · 1 min read · 1 upvotes · 0 comments ## Summary GitLab 19.3 adds the ability to deploy the AI Gateway for GitLab Duo Agent Platform inside a self-managed GitLab Dedicated single-tenant environment, keeping AI-processed data within a chosen AWS region instead of routing through GitLab's shared infrastructure. The gateway connects to Amazon Bedrock or other model providers, letting code review, pipeline fixing, and security analysis run under an org's existing compliance and change-control policies. The release also introduces custom agentic flows and bulk vulnerability triage tooling aimed at managing security backlogs at scale. ## Content GitLab's 19.3 release focuses on a problem that shows up once you actually start using AI agents at scale: it's one thing to have agents write code or fix a pipeline, and another thing entirely to run them safely across a large org, keep secrets contained, and stop your security backlog from becoming unmanageable. This release tries to close some of those gaps. Here's what's actually in it. ## Agent Platform now runs inside GitLab Dedicated If you're on GitLab Dedicated, you can now deploy the AI Gateway for the GitLab Duo Agent Platform inside your own single-tenant environment. That means AI-processed data stays in the AWS region you've already chosen, rather than routing through GitLab's shared infrastructure. The gateway connects to Amazon Bedrock or other model providers you prefer, so code review, pipeline fixing, and security analysis can run under whatever compliance and change-control policies your org already has in place. Setup is straightforward: add a self-hosted model, test it in a non-production project first, then roll agentic workflows out from there. For regulated industries or anyone who's had to explain to a compliance team why their code is touching a third-party API, this is the difference between ## Questions this post answers ### Can I run GitLab's AI Gateway for the Duo Agent Platform inside my own single-tenant environment? Yes, as of GitLab 19.3 the AI Gateway for the GitLab Duo Agent Platform can be deployed inside GitLab Dedicated, a single-tenant environment. AI-processed data then stays within the AWS region already chosen for that Dedicated instance instead of routing through GitLab's shared infrastructure, and the gateway connects to Amazon Bedrock or other preferred model providers. _Track how daily.dev surfaces GitLab Duo Agent Platform updates for teams evaluating agentic AI compliance options._ ### How do I set up a self-hosted AI model for GitLab Duo Agent Platform on GitLab Dedicated? Add a self-hosted model to the AI Gateway, test it in a non-production project first, then roll the agentic workflows out from there. The gateway supports Amazon Bedrock or other model providers, letting code review, pipeline fixing, and security analysis run under an organization's existing compliance and change-control policies. _Compliance-focused teams rolling out agentic coding tools can follow daily.dev for GitLab Duo deployment updates._ ## Similar posts on daily.dev - [GitLab 19.0 Embeds Agentic AI in Secrets, Merge Requests, and Supply Chain Security](https://daily.dev/posts/gitlab-19-0-embeds-agentic-ai-in-secrets-merge-requests-and-supply-chain-security-ecao3bucp) · InfoQ · 8 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#ai-agents](https://daily.dev/tags/ai-agents), [#gitlab](https://daily.dev/tags/gitlab), [#devsecops](https://daily.dev/tags/devsecops), [#amazon-bedrock](https://daily.dev/tags/amazon-bedrock) [View this post on daily.dev](https://daily.dev/posts/what-s-new-in-gitlab-19-3-agentic-tools-for-dedicated-environments-custom-flows-and-bulk-vulnerab-pkkpfwcck) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"What's new in GitLab 19.3: agentic tools for dedicated environments, custom flows, and bulk vulnerability triage","url":"https://daily.dev/posts/what-s-new-in-gitlab-19-3-agentic-tools-for-dedicated-environments-custom-flows-and-bulk-vulnerab-pkkpfwcck","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/what-s-new-in-gitlab-19-3-agentic-tools-for-dedicated-environments-custom-flows-and-bulk-vulnerab-pkkpfwcck"},"datePublished":"2026-08-24T17:49:19.210Z","dateModified":"2026-08-24T17:49:55.960Z","description":"GitLab 19.3 adds the ability to deploy the AI Gateway for GitLab Duo Agent Platform inside a self-managed GitLab Dedicated single-tenant environment, keeping...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7f7298291f9fb5f467cdb932f70f731d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7f7298291f9fb5f467cdb932f70f731d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/what-s-new-in-gitlab-19-3-agentic-tools-for-dedicated-environments-custom-flows-and-bulk-vulnerab-pkkpfwcck","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,ai-agents,gitlab,devsecops,amazon-bedrock","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"What's new in GitLab 19.3: agentic tools for dedicated environments, custom flows, and bulk vulnerability triage"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/what-s-new-in-gitlab-19-3-agentic-tools-for-dedicated-environments-custom-flows-and-bulk-vulnerab-pkkpfwcck#faq","mainEntity":[{"@type":"Question","name":"Can I run GitLab's AI Gateway for the Duo Agent Platform inside my own single-tenant environment?","acceptedAnswer":{"@type":"Answer","text":"Yes, as of GitLab 19.3 the AI Gateway for the GitLab Duo Agent Platform can be deployed inside GitLab Dedicated, a single-tenant environment. AI-processed data then stays within the AWS region already chosen for that Dedicated instance instead of routing through GitLab's shared infrastructure, and the gateway connects to Amazon Bedrock or other preferred model providers. Track how daily.dev surfaces GitLab Duo Agent Platform updates for teams evaluating agentic AI compliance options."}},{"@type":"Question","name":"How do I set up a self-hosted AI model for GitLab Duo Agent Platform on GitLab Dedicated?","acceptedAnswer":{"@type":"Answer","text":"Add a self-hosted model to the AI Gateway, test it in a non-production project first, then roll the agentic workflows out from there. The gateway supports Amazon Bedrock or other model providers, letting code review, pipeline fixing, and security analysis run under an organization's existing compliance and change-control policies. Compliance-focused teams rolling out agentic coding tools can follow daily.dev for GitLab Duo deployment updates."}}]} ```