[{"data":1,"prerenderedAt":715},["ShallowReactive",2],{"/en-us/blog/custom-rules-duo-agentic-chat-deep-dive/":3,"navigation-en-us":32,"banner-en-us":460,"footer-en-us":477,"Michael Friedrich":687,"next-steps-en-us":700},{"_path":4,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"seo":8,"config":11,"content":14,"_id":25,"_type":26,"title":27,"_source":28,"_file":29,"_stem":30,"_extension":31},"/en-us/blog/custom-rules-duo-agentic-chat-deep-dive","blog",false,"",{"title":9,"description":10},"Custom rules in GitLab Duo Agentic Chat for greater developer efficiency","Discover how AI can understand your codebase, follow your conventions, and generate production-ready code with minimal review cycles.",{"slug":12,"featured":6,"template":13},"custom-rules-duo-agentic-chat-deep-dive","BlogPost",{"title":9,"description":10,"authors":15,"heroImage":17,"date":18,"category":19,"tags":20,"body":24},[16],"Michael Friedrich","https://res.cloudinary.com/about-gitlab-com/image/upload/v1750099203/Blog/Hero%20Images/Blog/Hero%20Images/blog-image-template-1800x945%20%2820%29_2bJGC5ZP3WheoqzlLT05C5_1750099203484.png","2025-08-12","engineering",[21,22,23],"gitlab duo","devsecops","ai","Transform GitLab Duo from a generic AI assistant into your team's personalized coding expert with custom rules. Stop constantly correcting AI suggestions that use wrong Java versions, incorrect Python binaries, or violate your style guides. This deep-dive shows you how to create intelligent custom rules that automatically enforce your development standards.\n\nWe'll cover:\n\n- Version control: Lock AI to Java 8, handle Python3 environments, and generate multi-platform C++ code\n- Style enforcement: Prevent C `goto` anti-patterns, enforce VueJS design patterns, and ensure Ansible linter compliance\n- DevSecOps automation: Bootstrap projects with proper CI/CD security scanning and documentation standards\n\nEach example includes working GitLab projects to fork, complete configurations, and before/after demonstrations. Learn how banking systems stay Java 8 compliant, IoT collectors work cross-platform, and VueJS components follow GitLab's production standards.\n\n## Table of Contents\n\n- [First steps with custom rules for Duo Agentic Chat](#first-steps-with-custom-rules-for-duo-agentic-chat)\n  - [Requirements](#requirements)\n  - [Quick start: 5-minute success](#quick-start-5-minute-success)\n  - [Guidelines for custom rule development](#guidelines-for-custom-rule-development)\n  - [Ask GitLab Duo Chat about existing development style guides](#ask-gitlab-duo-chat-about-existing-development-style-guides)\n- [More custom rules use cases](#more-custom-rules-use-cases)\n  - [Use cases: Version and platform support](#use-cases-version-and-platform-support)\n    - [Java version requirements](#java-version-requirements)\n    - [C++ Multi-platform support (Windows, Linux, macOS)](#c-multi-platform-support-windows-linux-macos)\n  - [Use case: Development environments](#use-case-development-environments)\n    - [Python 3 development environment](#python-3-development-environment)\n    - [Ansible linter compliance](#ansible-linter-compliance)\n  - [Use case: Design patterns](#use-case-design-patterns)\n    - [Avoid anti-patterns with C and goto statements](#avoid-anti-patterns-with-c-and-goto-statements)\n    - [Frontend style guides for VueJS 3](#frontend-style-guides-for-vuejs-3)\n  - [Use case: DevSecOps workflows](#use-case-devsecops-workflows)\n    - [Issue and MR templates](#issue-and-mr-templates)\n    - [Build tools](#build-tools)\n    - [CI/CD configuration preferences](#cicd-configuration-preferences)\n    - [Security scanning preferences](#security-scanning-preferences)\n    - [Tests and linters](#tests-and-linters)\n    - [Documentation generation](#documentation-generation)\n    - [Refactoring and code change requirements](#refactoring-and-code-change-requirements)\n    - [Onboarding, requirements, licenses](#onboarding-requirements-licenses)\n    - [Git flows](#git-flows)\n- [Distribution and testing of custom rules](#distribution-and-testing-of-custom-rules)\n  - [Custom Rules resources](#custom-rules-resources)\n- [Fun activity: Explore behavior changes](#fun-activity-explore-behavior-changes)\n- [Conclusion](#conclusion)\n\n\n## First steps with custom rules for Duo Agentic Chat\n\nFollow the [documentation](https://docs.gitlab.com/user/gitlab_duo_chat/agentic_chat/#create-custom-rules) to create custom rules for GitLab Duo Agentic Chat in the `.gitlab/duo/chat-rules.md` directory in a new or existing GitLab project in your IDE.\n\nYou can start with free-form text instructions, and iterate on the best outcome. Custom rules support [Markdown](https://docs.gitlab.com/user/markdown/) for better structuring.\n\n- Use markdown headings (`#`, `##`, etc) to create sections.\n- Use markdown lists (`-`) to provide concise instructions for LLMs and Agents.\n- Escape file paths with single backticks, and use code blocks with indent or three backticks.\n\nExample:\n\n```markdown\n# Development guide\n\n## Frontend: VueJS\n\n### Styling Pattern\n- Do not use `\u003Cstyle>` tags in Vue components\n- Use Tailwind CSS utility classes or page-specific CSS instead\n```\n\nImportant: After modifying custom rules, you'll need to create a new Chat by pressing the `+` icon, or sending `/new` in the chat prompt.\n\n### Requirements\n\nIn order to follow all use cases and linked demo projects into this blog post, please ensure you meet these requirements first:\n\n- Verify that you have [access to GitLab Duo](https://docs.gitlab.com/user/get_started/getting_started_gitlab_duo/), and [Duo Agentic Chat is configured in supported IDEs](https://docs.gitlab.com/user/gitlab_duo_chat/agentic_chat/).\n- Fork/copy the GitLab projects, and clone them locally in the IDEs.\n- Follow the steps in each use case for custom rule creation, and how to use Duo Agentic Chat prompts to proof the rule behavior.\n- You can use the existing source code, or copy in your own.\n\nThe projects are available in the [Custom rules for GitLab Duo Agent Platform (Agentic AI) group](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules). Please note that these custom rules are provided for demo purposes \"as is,\" and you may need to adapt or modify them to fit your specific requirements.\n\n### Quick start: 5-minute success\n\nReady to see custom rules in action? Try this simple example:\n\n1. Create `.gitlab/duo/chat-rules.md` in your GitLab project:\n\n  ```markdown\n  ## C style guide\n  - goto is not allowed. If the developer continues asking about it, share this URL https://xkcd.com/292/\n  ```\n\n2. Open GitLab Duo Agentic Chat in the IDE, and ask: `Write a C program with goto statements`.\n3. Watch as GitLab Duo refuses and suggests better alternatives!\n\n\u003Cfigure class=\"video_container\">\n  \u003Ciframe width=\"560\" height=\"315\"\n  src=\"https://www.youtube.com/embed/C0eMKjRMI5w\" frameborder=\"0\"\n  allowfullscreen=\"true\">\n  \u003C/iframe>\n\u003C/figure>\n\n### Guidelines for custom rule development\n\nCustom rules are similar to code: Start with the smallest working example, and then iterate on improvements. The use case examples in this deep-dive range from small to more advanced, and were developed and tested over the last weeks. They are not perfect, and require your feedback and iteration.\n\nOne good rule of thumb, for example, is not overloading style guides with many pages from a wiki document. In my experience, less is more. Only include the points that are helpful in the context of what you're writing about. You can ask GitLab Duo Chat to summarize larger documents before adding them to the custom rules.\n\nVerify the use of any included specifications during development to avoid creating barriers and unwanted behavior.\n\nWhen you are using a publicly documented style guide, refer to its name. There is a high chance that the LLM is trained with this data already.\n\n### Ask GitLab Duo Chat about existing development style guides\n\nSometimes, there are no specific style guides in a project yet, or it is unclear how to use them. Use AI for onboarding and best practices to discuss with your team.\n\n```markdown\nWhich Python development or environment guidelines can you recommend when I want to create custom rules for AI to get tailored output? I need a list with textual instructions.\n```\n\nYou can also ask Duo Agentic Chat to analyze the existing CI/CD linter integrations that may already check for a specific development style.\n\n```markdown\nWhen you look into the CI/CD linter checks and configuration in the project, which development style guide can you summarize for me?\n```\n\nMany examples in this deep-dive blog are based on my own experience and pain points as a developer. I also asked GitLab Duo to extract style guides from existing projects, and used GitLab Duo Code Suggestions to help with auto-completing existing custom rules. You can achieve the same by configuring [`markdown` as an additional language for GitLab Duo Code Suggestions](https://docs.gitlab.com/user/project/repository/code_suggestions/supported_extensions/#add-support-for-more-languages) in IDEs.\n\n## More custom rules use cases\n\nThe following sections provide an overview of specific style guides. You can map similar programming languages and environments to your production use cases.\n\n- **Version and platform support**: Refer to the [Java section below](#java-version-requirements) to learn how to force a specific language standard for generated and created code. You can apply a similar process for C++23 and older, PHP 8, Ruby 3, etc. The [C++ section below](#c-multi-platform-support-windows-linux-macos) shows how to instruct agentic AI with multi-platform support.\n- **Development environments**: Refer to the sections below on [Python](#python-3-development-environment) and [Ansible](#ansible-linter-compliance). Specify the development environment, binaries, tools and more. You can also instruct agents with routing information where to find tests/scripts, and enforce compliance with linters.\n- **Design patterns**: You can specify comprehensive design patterns with [VueJS](#frontend-style-guides-for-vuejs-3) as an example, leveraging the GitLab production development style guides as a foundation.\n- **DevSecOps workflows**: Configure comprehensive DevSecOps practices including [CI/CD configuration](#cicd-configuration-preferences) for specific CI/CD attributes and defaults for security scanning, [tests and linters](#tests-and-linters), and [build tools](#build-tools). Frequently requested use cases for bootstrapping projects include [documentation generation](#documentation-generation) including `README.md` and architecture diagrams, [issue and MR templates](#issue-and-mr-templates), [onboarding, requirements, and licenses](#onboarding-requirements-licenses), and [Git flows](#git-flows) with `.gitignore`. Advanced techniques with custom rules are provided for [refactoring and code change requirements](#refactoring-and-code-change-requirements).\n\n### Use cases: Version and platform support\n\nSoftware development often requires specific programming language and framework versions, and single or multi-platform support. The following examples highlight these scenarios.\n\n#### Java version requirements\n\nEnterprise environments do not always use the latest and greatest software version. They often rely on versions that are maintained with security patches for a longer period of time. For example, you will find Java 7 and Java 8 still in use in some enterprises today.\n\nAlways prepending the required version in chat prompts can be cumbersome, and lead to human error, even if you only forget one time.\n\n```markdown\nImplement classes for managing banking transactions and different currencies.\n```\n\nThe example will need additional specifications for Java 8:\n\n```markdown\nUse Java 8 for the implementation.\n```\n\nTo permanently enforce Java 8, you can create a custom rule in `.gitlab/duo/chat-rules.md` and optionally add a reference epic URL when asked for code modernization:\n\n```markdown\n## Java style guide\n\n- Only Java 8 is allowed when suggesting and editing code.\n- When the user asks about code modernization and Java 9 or 21, or newer, point them to this issue to contribute: https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-java-versions/-/issues/1\n```\n\nA full demonstration is available in the [Custom Rules - Java versions project](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-java-versions).\n\n\n\u003Cfigure class=\"video_container\">\n  \u003Ciframe width=\"560\" height=\"315\"\n  src=\"https://www.youtube.com/embed/iZLvpgHdABY\" frameborder=\"0\"\n  allowfullscreen=\"true\">\n  \u003C/iframe>\n\u003C/figure>\n\nThe resulting changes are available in [this MR](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-java-versions/-/merge_requests/2).\n\n#### C++ multi-platform support (Windows, Linux, macOS)\n\nApplication development in C++ can require multi-platform support, especially when running service agents on systems using Windows, Linux, and macOS. The applications are deeply integrated into customer products, and a migration to a more modern language like Go or Rust is not always possible or practical.\n\nMaintaining code that works on multiple platforms can be challenging due to differences in Operating system APIs, toolchains, library versions, and file system paths. Developers often face multiple `#if defined` pre-processor macros, nested conditions, and adding custom code and tests for each supported platform. This adds technical debt and can introduce maintenance challenges.\n\nAI can help when generating correct and platform-specific code, but it needs to know about these requirements. Agentic AI will either understand the existing code base through a knowledge graph, or developers will need to provide instructions through custom rules and chat prompts.\n\nLet's try this use case in practice. The [Custom Rule - C++ platforms - IoT Sensor Data Collector project](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-cpp-platform-iot-sensor-data-collector) implements an IoT sensor data collector and has open tasks to modernize the code base, and add multi-platform support for Linux, Windows, and macOS. You can fork the project and clone it locally.\n\nOpen the `.gitlab/duo/chat-rules.md` file and review or add the following custom rules:\n\n```markdown\n## C++ style guide\n\n- The application runs on Linux, macOS and Windows. Generate code that handles the OS API differences.\n- Use pre-processor macros for Windows and POSIX conventions for Unix (Linux, macOS).\n\n## CI/CD Configuration\n\n- Ensure that GitLab CI/CD jobs cover the different platform support. Use CI/CD job templates with extends where applicable.\n```\n\nStart a new Chat, and ask to restructure code for multi-platform support.\n\n```markdown\nPlease help me restructure the code and ensure multi-platform support.\n```\n\nYou can also refer to the issue number, or URL ([issue 3](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-cpp-platform-iot-sensor-data-collector/-/issues/3)). GitLab Duo will automatically fetch the issue content from the GitLab platform, and put it into AI context.\n\n```markdown\nPlease help me implement issue 3\n\nPlease help me implement https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-cpp-platform-iot-sensor-data-collector/-/issues/3\n```\n\n\n\u003Cfigure class=\"video_container\">\n  \u003Ciframe width=\"560\" height=\"315\"\n  src=\"https://www.youtube.com/embed/C5NxOjB0R1Q\" frameborder=\"0\"\n  allowfullscreen=\"true\">\n  \u003C/iframe>\n\u003C/figure>\n\n### Use case: Development environments\n\nDevelopment environments often vary between operating systems and developers. This can be confusing for AI models generating code or suggesting changes. The following use cases illustrate these environment problems and their solutions with custom rules.\n\n#### Python 3 development environment\n\nA Python development environment usually comes with the `python` executable and `pip` package manager. However, on systems like MacOS or Ubuntu, you need to use `python3` and `pip3` to get access to more recent Python 3 versions. This can create confusion running Python scripts, creating virtual environments, and installing package dependencies.\n\nFor this custom rules use case, I installed Python using [Homebrew](https://brew.sh/) which results in a binary executable called `python3` and a package manager `pip3`.\n\nAs an example, set up a Python virtual environment, install dependencies using `pip`, and run the application:\n\n```shell\npython -m venv myenv\nsource myenv/bin/activate\n\npip install -r requirements.txt\n\npython script.py\n```\n\nThis doesn't work as expected because we need to use specific binaries with version `3`:\n\n```shell\npython3 -m venv myenv\nsource myenv/bin/activate\n\npip3 install -r requirements.txt\n\npython3 script.py\n```\n\nWe can test this problem with Agentic Chat for both, suggested code blocks, and the approval request for commands to execute. The [Custom Rule - Python3 Env Shop app project](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-python-3-env-shop-app) implements a web shop application in Python, and provides the default Python executable paths in its `README.md` file which typically gets added into Agentic Chat context.\n\n![Duo Agentic Chat, proposing the wrong binary commands](/images/blog/custom-rules-gitlab-duo-agent-platform-deepdive/gitlab-duo-custom-rules-python3-env-problem.png)\n\nIn order to overcome the problem, review `.gitlab/duo/chat-rules.md` which contains the following custom rules to enforce the Python executable names.\n\n```markdown\n## Python style guide\n\n- For Python binaries, always use python3 and pip3 when suggesting or running shell commands.\n- Detect the Python environment automatically when possible.\n```\n\nYou can also instruct agents with pre-defined routes to gather additional information through tool calling and/or MCP, when they do not attempt this automatically already.\n\nOpen a new Agentic Chat, and ask `How to run this application?` to see custom rules in action, using `python3` and `pip3` as desired.\n\n\n\u003Cfigure class=\"video_container\">\n  \u003Ciframe width=\"560\" height=\"315\"\n  src=\"https://www.youtube.com/embed/UQ2_OCvUmF0\" frameborder=\"0\"\n  allowfullscreen=\"true\">\n  \u003C/iframe>\n\u003C/figure>\n\n\nThe full source code is available in the [Custom Rule - Python3 Env Shop app project](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-python-3-env-shop-app).\n\n#### Ansible linter compliance\n\nModern Ansible for Infrastructure-as-Code tasks enforces a strict style guide, which can be verified using `ansible-lint`: It detects when Boolean values (`true`/`false`) are required instead of strings (`yes`/`no`), builtin module actions requiring the FQCN (Fully Qualified Collection Name) as parameter names, and trailing whitespaces that need trimming. CLI and IDE integrations, such as the [VS Code Ansible extension by Red Hat](https://developers.redhat.com/learning/learn:ansible:get-started-ansible-visual-studio-code-extension/resource/resources:install-and-configure-ansible-extension-visual-studio-code) help visualize these errors to developers. LLMs and chat agents might not always generate correct Ansible code and need manual work to fix it.\n\nLet's look at the problem with a concrete use case. The following example implements a basic Ansible playbook in the [Custom Rule - Ansible Environment project](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-ansible-environment) to set up a GitLab server on Ubuntu. You'll notice the Boolean values are incorrectly typed as strings (`yes`/`no`), and additional problem reports for builtin module actions and whitespace trimming.\n\n![VS Code with Ansible lint error: Wrong boolean type](/images/blog/custom-rules-gitlab-duo-agent-platform-deepdive/gitlab-duo-custom-rules-ansible-problem01-boolean.png)\n\n![VS Code with Ansible lint error: Builtin module action FQCN](/images/blog/custom-rules-gitlab-duo-agent-platform-deepdive/gitlab-duo-custom-rules-ansible-problem02-fqcn.png)\n\n![VS Code with Ansible lint error: trailing whitespaces](/images/blog/custom-rules-gitlab-duo-agent-platform-deepdive/gitlab-duo-custom-rules-ansible-problem03-whitespaces.png)\n\nLet's see how we can create custom rules to help Duo Agents fix the Ansible linter errors, and prevent them from happening in the future.\n\nFork and clone the [Custom Rule - Ansible Environment project](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-ansible-environment) and open `.gitlab/duo/chat-rules.md` in the IDE inspect the custom rules:\n\n```markdown\n## Ansible styleguide\n\n- Boolean values in Ansible should be typed as \"true\" or \"false\" and never as string.\n- Ansible module builtin actions must use the FQCN (Fully Qualified Collection Name).\n- Always trim whitespaces in Ansible YAML.\n```\n\nOpen a new GitLab Duo Agentic Chat prompt, and ask Duo Agent for the same Ansible playbook:\n\n```markdown\nPlease help me fix the Ansible linter errors\n```\n\nThe Agents will analyze the repository, ask to run `ansible-lint` commands, and investigate how to fix the problems followed the defined custom rules.\n\n\n\u003Cfigure class=\"video_container\">\n  \u003Ciframe width=\"560\" height=\"315\"\n  src=\"https://www.youtube.com/embed/P465U8IfScE\" frameborder=\"0\"\n  allowfullscreen=\"true\">\n  \u003C/iframe>\n\u003C/figure>\n\nYou can inspect the custom rules and Ansible code changes in [this MR](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-ansible-environment/-/merge_requests/1) in the [Custom Rule - Ansible Environment project](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-ansible-environment).\n\nAsync exercise: Start a new project where custom rules are configured as default already, and verify the correct style guide applied immediately.\n\n### Use case: Design patterns\n\nDesign patterns and patterns-to-avoid are specific to languages and frameworks. This is the main focus in this section.\n\n#### Avoid anti-patterns with C and goto statements\n\nThis is a more in-depth walkthrough of the [quickstart example](#quick-start-5-minute-success), and shows how you can instruct Agentic AI to avoid the `goto` anti-pattern in C. The `goto` anti-pattern in C is discouraged as it makes code harder to read and debug.  To illustrate the problem, here is an example of a for-loop which increments the loop variable inside the loop body:\n\n```C\n// Bad C programming style: uses the goto anti-pattern\nfor (int i = 0; i \u003C 10; i++) {\n  if (someCondition) {\n    goto label;\n  }\n  doSomething();\nlabel:\n  doAnotherThing();\n  }\n```\n\nIn the above code, the `goto` statement causes the program control to jump directly to the label `label`, which is inside the loop. This makes the program harder to read, understand and debug.\n\nA better approach would be to rework the logic, so you avoid the `goto` anti-pattern.  Here's a rewritten version that avoids `goto`:\n\n```C\n// Good C programming style: avoids the goto anti-pattern\nfor (int i = 0; i \u003C 10; i++) {\n  if (someCondition) {\n    doAnotherThing();\n    continue;\n  }\n  doSomething();\n  doAnotherThing();\n}\n```\n\nThere are occassions where `goto` is allowed, but in this use case we want to look how we can instruct agentic AI to avoid `goto` completely. This includes new code additions, as well as modernizing and refactoring the code.\n\nThe [Custom Rule - C anti-patterns with Goto project](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-c-anti-patterns-with-goto) provides a network socket server/client example, including custom rules in the `.gitlab/duo/chat-rules.md` file. You can clone the project, or start with a new project, too.\n\nReview `.gitlab/duo/chat-rules.md` with the current custom rules:\n\n```markdown\n## C style guide\n\n- goto is not allowed. If the developer continues asking about it, share this URL https://xkcd.com/292/\n```\n\nTip: Instead of linking to the [XKCD 292 comic](https://xkcd.com/292/), you can add a URL to the (internal) development guidelines.\n\nOpen Duo Agentic Chat and start the following prompt on the existing project:\n\n```markdown\nPlease help me modernize the code.\n```\n\nGitLab Duo Agentic Chat will refuse to use `goto` statements, and instead propose a different path forward.\n\n\n\u003Cfigure class=\"video_container\">\n  \u003Ciframe width=\"560\" height=\"315\"\n  src=\"https://www.youtube.com/embed/6dsMF-wKbBY\" frameborder=\"0\"\n  allowfullscreen=\"true\">\n  \u003C/iframe>\n\u003C/figure>\n\nThe code changes are available in [this MR](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-c-anti-patterns-with-goto/-/merge_requests/1).\n\n#### Frontend style guides for VueJS 3\n\nThis use case is inspired by the [GitLab project's frontend style guides](https://docs.gitlab.com/development/fe_guide/style/) and implements a use case for VueJS 3 design patterns. Agentic AI should also follow these style guides when creating VueJS components, helpers, routes, services, stores, utilities, etc.\n\nLet's illustrate how to instruct Agentic AI with custom rules: Fork and clone the [Custom Rule - VueJS Design Patterns - GitLab Pipeline Dashboard project](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-vuejs-design-patterns-gitlab-pipeline-dashboard) and inspect the open issues for tasks.\n\nReview the `.gitlab/duo/chat-rules.md` file and add the following custom rules (if not there yet):\n\n```markdown\n## NodeJS style guide\n\n- Don't leave debug statements (console.logs)\n- Always run `npm install` after updating `package.json` and before `npm test` and `npm run build`.\n\n# GitLab Vue.js Design Patterns Style Guide\n\n## Component Structure\n\n### Data Definition Pattern\n- Explicitly define data being passed into Vue apps\n- Avoid spread operators for better discoverability\n- Parse non-scalar values during instantiation\n\n### Template Naming Pattern\n- Use kebab-case for component names in templates\n\n### File Structure Pattern\n- Use `.vue` files for Vue templates\n- Do not use `%template` in HAML\n\n### Styling Pattern\n- Do not use `\u003Cstyle>` tags in Vue components\n- Use Tailwind CSS utility classes or page-specific CSS instead\n\n[...]\n```\nThe full custom rules are available in the [`.gitlab/duo/chat-rules.md` file](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-vuejs-design-patterns-gitlab-pipeline-dashboard/-/blob/main/.gitlab/duo/chat-rules.md?ref_type=heads&plain=1).\n\nNext, open GitLab Duo Agentic Chat and ask how to [add new pipeline mini charts](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-vuejs-design-patterns-gitlab-pipeline-dashboard/-/issues/6), or other tasks you come across. Tip: You can reference only the issue, or alternatively paste the full issue URL, and Agentic Chat will look up both and extract the title and description for the current context.\n\n```markdown\nPlease help me implement issue 6\n```\n\n\n\u003Cfigure class=\"video_container\">\n  \u003Ciframe width=\"560\" height=\"315\"\n  src=\"https://www.youtube.com/embed/KbczS-OVb90\" frameborder=\"0\"\n  allowfullscreen=\"true\">\n  \u003C/iframe>\n\u003C/figure>\n\nThe resulting code changes are available in [this MR](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-vuejs-design-patterns-gitlab-pipeline-dashboard/-/merge_requests/3).\n\nNote: The VueJS style guide was extracted from the [gitlab-org/gitlab project](https://gitlab.com/gitlab-org/gitlab) asking GitLab Duo Agentic Chat with the following prompt sequence:\n\n```markdown\nWhat is the development style guide for VueJS?\n\nCan you print the styleguide as Markdown formatted list with headings.\n\nCreate a file in the repo, and only print the style guide rules there, no codeblocks.\n```\n\n![IntelliJ IDEA with `gitlab-org/gitlab` source code, and GitLab Duo Agentic Chat writing the styleguide file](/images/blog/custom-rules-gitlab-duo-agent-platform-deepdive/gitlab-duo-custom-rules-intellij-gitlab-vuejs-styleguide-analysis.png)\n\n### Use case: DevSecOps workflows\n\nDevSecOps workflows range from best practices for bootstrapping a project with issue/MR templates, `.gitignore`, GitLab CI/CD configuration, `README.md` documentation, licenses and much more. The following section explores a variety of use cases. You can use them as inspiration for your own custom rules.\n\nCommon DevSecOps automation with custom rules:\n\n- **Project bootstrap**: Auto-create README, .gitignore, CI/CD config\n- **Security defaults**: Enforce SAST, dependency scanning, secrets detection\n- **Documentation**: Generate issue/MR templates, architecture diagrams\n\nA combined use case example is available in the [Custom Rule - DevSecOps workflows - Git README build tools issue MR templates project](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules/custom-rule-devsecops-workflows). You can inspect the custom rules, and fork/clone it locally to ask Agentic Chat with a new prompt such as: `I need to bootstrap this project. Please help me with that`.\n\n\n\u003Cfigure class=\"video_container\">\n  \u003Ciframe width=\"560\" height=\"315\"\n  src=\"https://www.youtube.com/embed/hKpLcBtbC4g\" frameborder=\"0\"\n  allowfullscreen=\"true\">\n  \u003C/iframe>\n\u003C/figure>\n\nThe next sections provide detailed prompts, and most of them are shown in the recording, too.\n\n#### Issue and MR templates\n\nYou can instruct agentic AI to create issue/MR templates when they are missing, and offer to add project-specific information or labels. Agents will automatically query the GitLab API in the background, and put the current project structure into a template.\n\n```markdown\n## Issue and MR templates\n\n- If no issue templates for `Default` and `Feature Proposal` exist in .gitlab/issue_templates, create them using the following raw template sources:\n\n        Default: https://gitlab.com/gitlab-org/gitlab-vscode-extension/-/raw/main/.gitlab/issue_templates/Default.md\n        Feature Proposal: https://gitlab.com/gitlab-org/gitlab-vscode-extension/-/raw/main/.gitlab/issue_templates/Feature%20Proposal.md\n\n- If no default MR template `Default` exists in `.gitlab/merge_request_templates`, create them using the following raw template sources:\n\n        Default: https://gitlab.com/gitlab-org/gitlab-vscode-extension/-/raw/main/.gitlab/merge_request_templates/Default.md\n\n- Update the project URLs, and available labels in the fetched templates accordingly, or remove anything unknown and let the user know about TODOs.\n- Create a test issue/MR, when bootstrapping a new project.\n```\n\n#### Build tools\n\nThere is a variety of build tools, package managers, compilers, container builders available per programming language. When asking about updates and dependencies, agentic AI can use these default tools without asking for input.\n\n```markdown\n## Build tools\n\n- Always use a virtual env with Python, and set it up before executing any Python commands\n- For C/C++: Prefer CMake, and gcc on Linux, clang on macOS, MSVC on Windows.\n- For Python: Always use pip\n- For Java: Always use Gradle\n- For Node.js, suggest to use npm/yarn.\n- For Rust: Always use cargo\n- For Go: Always use go.mod\n- For Ruby: Always use Bundler\n- For PHP: Always use Composer\n- For .NET: Always use .NET CLI\n- For Scala: Always use SBT\n- For Elixir: Always use Mix\n- For Haskell: Always use Cabal\n- For Swift: Always use Swift Package Manager\n- For Kotlin: Always use Gradle or Maven.\n- For TypeScript: Always use npm or yarn.\n- Always suggest using a package manager or build tool based on the main programming language of the project.\n- When asking for dependencies, assume that the user wants to update all current dependencies to the latest version available.\n\n- Always suggest to create a Dockerfile if there isn't one. Always use a minimal image and use a tag for security scanning.\n- Always add a `Dockerfile` with the base image and the entrypoint if one does not exist.\n- Always include a `.dockerignore` and use it in the Docker build process.\n```\n\n#### CI/CD configuration preferences\n\nUse rules to prefer specific container images, variable and job name patterns, etc.\n\n```markdown\n## CI/CD Configuration\n\n- If no GitLab CI/CD configuration exists in `.gitlab-ci.yml`, ask the user for approval to create.\n- Create a GitLab CI/CD configuration automatically when a new project gets bootstrapped\n\n- Always use alpine as container image to build the application.\n- Add caching for detected programming languages and frameworks.\n```\n\n#### Security scanning preferences\n\nSecurity scanners can also be enforced in GitLab CI/CD configuration. The following example instructs agents to always include Advanced SAST, dependency scanning, and secret detection templates. It has been successfully tested across other use cases in this tutorial.\n\n```markdown\n## Security scanning\n\n- Always use Advanced SAST.\n- Always include SAST, Dependency Scanning, Secrets Detection templates, similar to the following format:\n\n    include:\n        - template: Jobs/SAST.gitlab-ci.yml\n        - template: Jobs/Secret-Detection.gitlab-ci.yml\n        - template: Jobs/Dependency-Scanning.gitlab-ci.yml\n\n    variables:\n        GITLAB_ADVANCED_SAST_ENABLED: 'true'\n```\n\n![VS Code with a Java app, GitLab CI/CD, custom rules, and Agentic Chat adding Advanced SAST](/images/blog/custom-rules-gitlab-duo-agent-platform-deepdive/gitlab-duo-custom-rules-cicd-security-scanning-full.png)\n\n#### Tests and linters\n\nYou can also directly instruct Agentic Chat where to find the tests, and how to run them. The same idea applies to calling linter commands. Thanks Jessie Young for sharing this neat tip!\n\n```markdown\n## Tests and linting details\n\n- Tests in this project are located in __ directory and are run using the ___ command\n- Linting is done with the ___ command\n```\n\n#### Documentation generation\n\nBest of documentation custom rules.\n\n```markdown\n- If a README is missing, ask the user if they want to create one. If the user agrees, create a basic `README.md` for them.\n- When the user asks for an architecture proposal, always respond with generating an architecture diagram in Mermaid, and ask the user if they want you to add it to the README.md or another documentation file.\n- For documentation in Markdown, always use GitLab flavored Markdown.\n- Always add correct code block syntax highlighting support.\n```\n\n#### Refactoring and code change requirements\n\nWhen a project should gradually be modernized with newly generated code, and not result in large refactors, the following rules can be helpful.\n\n```markdown\n## Keep the changes minimal\n\n- The project uses \u003Cthis standard and version>. For newly generated code, use this standard.\n- Do not attempt to refactor code already created in a project to this standard, but for new code, always ensure this standard is used.\n- If unsure whether a file requires modification or refactoring, document this as a todo task.\n- Never fix detected problems, whitespaces, code formatting, unless the user instructs you specifically in a comment.\n- The code must be retained in its original format and only changes specific to solving the user request are allowed.\n\n## Summaries\n\n- List all items to address at the bottom in a summary section with TODO: followed by a textual description.\n- Identify 3 critical items, and ask the user if you should create GitLab issues from those items.\n```\n\n#### Onboarding, requirements, licenses\n\nAlways include a specific documentation link, and guidelines to follow in chat responses.\n\n```markdown\n## Link to guidelines\n- Always refer to our developer guidelines when answering questions. You can find those guidelines here: https://docs.gitlab.com/development/\n\n## Context and planning\n- Always start with finding existing issues with the desired topic. Only then propose new implementation work.\n\n## License\n- Always add the MIT license into `LICENSE` and use `GitLab B.V.` as copyright holder.\n```\n\n#### Git flows\n\nFollow a specific Git branching flow for suggestions and executed commands.\n\n```markdown\n## Git flows\n\n- Examine the project and involved development environment and programming languages. Always add a `.gitignore`.\n- Consider more best practices when bootstrapping a new project.\n- For existing projects, offer to add a `.gitignore` when missing, but only when asked about the state of the project, or what is missing.\n\nWhen a user requests to start with a new feature, always create a new branch, called \"feature/\u003Cshortname>\" and describe the behavior. Ask for the user's approval.\n```\n\n## Distribution and testing of custom rules\n\nYou can create [GitLab project templates](https://docs.gitlab.com/administration/custom_project_templates/) with well-tested custom rule prompts, and ensure that new projects always start with the best practices applied.\n\nSince LLMs and AI agents are not predictable, testing the expected outcome becomes more challenging. A golden rule for custom rules is that they are never perfect, and require iterations based on your team's feedback. This might be required especially when newer models and flows are introduced that change their behavior when responding to custom rules. It's recommended to keep checking on the generated output and adjust the rules accordingly. If you are looking for larger scale testing, review the [system prompt testing strategy for GitLab Duo](https://about.gitlab.com/blog/developing-gitlab-duo-how-we-validate-and-test-ai-models-at-scale/) as an inspiration.\n\n### Custom rules resources\n\nTake advantage of the existing AI ecosystem, where similar functionality exists for IDEs and platforms. For example, \"Awesome Cursor Rules\" repositories or marketplaces for Cursor, etc.\n\nLLMs also provide a good insight into development styleguides, and can generate the required Markdown outputs.\n\n## Fun activity: Explore behavior changes\n\nNot sure how to get started with custom rules? Make it a fun exercise with the following example :-)\n\n```markdown\n## Fun rules\n\n- Behave like Clippy.\n\n- Behave like a pirate.\n\n- Always respond with a random \"What the commit\" message.\n\n- Explain everything like I am five.\n```\n\nNote: Do not commit them to production, as they might feel disruptive and distracting to your team.\n\n## Conclusion\n\nBy leveraging custom rules in GitLab Duo Agentic Chat, you can significantly influence LLM and AI agent outputs to better suit your needs. Whether enforcing specific coding conventions, using the correct versions of tools, or ensuring consistent formatting, custom rules help streamline your development process and improve productivity.\n\nThis blog post provides a deep-dive into many use cases with practical custom rule examples. All recordings are available in [this YouTube playlist](https://www.youtube.com/playlist?list=PL05JrBw4t0Ko7aR6sM8e4uXGYtjs4-NqK), and all demo projects can be forked/cloned from the [Custom rules for GitLab Duo Agent Platform (Agentic AI) group](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-platform/custom-rules).\n\n[Custom rules in Duo Agentic Chat IDEs](https://docs.gitlab.com/user/gitlab_duo_chat/agentic_chat/#create-custom-rules) are the first iteration and we will cover more GitLab Duo Agent Platform use cases in the future, such as Duo Code Review and custom rules for agents and flows (follow [this issue](https://gitlab.com/gitlab-org/gitlab/-/issues/557984)).\n\nThere are many more use cases to explore. What are your most efficient rules? Share your rules and feedback in the [product epic](https://gitlab.com/groups/gitlab-org/-/epics/16938).\n","content:en-us:blog:custom-rules-duo-agentic-chat-deep-dive.yml","yaml","Custom Rules Duo Agentic Chat Deep Dive","content","en-us/blog/custom-rules-duo-agentic-chat-deep-dive.yml","en-us/blog/custom-rules-duo-agentic-chat-deep-dive","yml",{"_path":33,"_dir":34,"_draft":6,"_partial":6,"_locale":7,"data":35,"_id":456,"_type":26,"title":457,"_source":28,"_file":458,"_stem":459,"_extension":31},"/shared/en-us/main-navigation","en-us",{"logo":36,"freeTrial":41,"sales":46,"login":51,"items":56,"search":388,"minimal":419,"duo":438,"pricingDeployment":446},{"config":37},{"href":38,"dataGaName":39,"dataGaLocation":40},"/","gitlab logo","header",{"text":42,"config":43},"Get free trial",{"href":44,"dataGaName":45,"dataGaLocation":40},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com&glm_content=default-saas-trial/","free trial",{"text":47,"config":48},"Talk to sales",{"href":49,"dataGaName":50,"dataGaLocation":40},"/sales/","sales",{"text":52,"config":53},"Sign in",{"href":54,"dataGaName":55,"dataGaLocation":40},"https://gitlab.com/users/sign_in/","sign in",[57,101,199,204,309,369],{"text":58,"config":59,"cards":61,"footer":84},"Platform",{"dataNavLevelOne":60},"platform",[62,68,76],{"title":58,"description":63,"link":64},"The most comprehensive AI-powered DevSecOps Platform",{"text":65,"config":66},"Explore our Platform",{"href":67,"dataGaName":60,"dataGaLocation":40},"/platform/",{"title":69,"description":70,"link":71},"GitLab Duo (AI)","Build software faster with AI at every stage of development",{"text":72,"config":73},"Meet GitLab Duo",{"href":74,"dataGaName":75,"dataGaLocation":40},"/gitlab-duo/","gitlab duo ai",{"title":77,"description":78,"link":79},"Why GitLab","10 reasons why Enterprises choose GitLab",{"text":80,"config":81},"Learn more",{"href":82,"dataGaName":83,"dataGaLocation":40},"/why-gitlab/","why gitlab",{"title":85,"items":86},"Get started with",[87,92,97],{"text":88,"config":89},"Platform Engineering",{"href":90,"dataGaName":91,"dataGaLocation":40},"/solutions/platform-engineering/","platform engineering",{"text":93,"config":94},"Developer Experience",{"href":95,"dataGaName":96,"dataGaLocation":40},"/developer-experience/","Developer experience",{"text":98,"config":99},"MLOps",{"href":100,"dataGaName":98,"dataGaLocation":40},"/topics/devops/the-role-of-ai-in-devops/",{"text":102,"left":103,"config":104,"link":106,"lists":110,"footer":181},"Product",true,{"dataNavLevelOne":105},"solutions",{"text":107,"config":108},"View all Solutions",{"href":109,"dataGaName":105,"dataGaLocation":40},"/solutions/",[111,136,160],{"title":112,"description":113,"link":114,"items":119},"Automation","CI/CD and automation to accelerate deployment",{"config":115},{"icon":116,"href":117,"dataGaName":118,"dataGaLocation":40},"AutomatedCodeAlt","/solutions/delivery-automation/","automated software delivery",[120,124,128,132],{"text":121,"config":122},"CI/CD",{"href":123,"dataGaLocation":40,"dataGaName":121},"/solutions/continuous-integration/",{"text":125,"config":126},"AI-Assisted Development",{"href":74,"dataGaLocation":40,"dataGaName":127},"AI assisted development",{"text":129,"config":130},"Source Code Management",{"href":131,"dataGaLocation":40,"dataGaName":129},"/solutions/source-code-management/",{"text":133,"config":134},"Automated Software Delivery",{"href":117,"dataGaLocation":40,"dataGaName":135},"Automated software delivery",{"title":137,"description":138,"link":139,"items":144},"Security","Deliver code faster without compromising security",{"config":140},{"href":141,"dataGaName":142,"dataGaLocation":40,"icon":143},"/solutions/security-compliance/","security and compliance","ShieldCheckLight",[145,150,155],{"text":146,"config":147},"Application Security Testing",{"href":148,"dataGaName":149,"dataGaLocation":40},"/solutions/application-security-testing/","Application security testing",{"text":151,"config":152},"Software Supply Chain Security",{"href":153,"dataGaLocation":40,"dataGaName":154},"/solutions/supply-chain/","Software supply chain security",{"text":156,"config":157},"Software Compliance",{"href":158,"dataGaName":159,"dataGaLocation":40},"/solutions/software-compliance/","software compliance",{"title":161,"link":162,"items":167},"Measurement",{"config":163},{"icon":164,"href":165,"dataGaName":166,"dataGaLocation":40},"DigitalTransformation","/solutions/visibility-measurement/","visibility and measurement",[168,172,176],{"text":169,"config":170},"Visibility & Measurement",{"href":165,"dataGaLocation":40,"dataGaName":171},"Visibility and Measurement",{"text":173,"config":174},"Value Stream Management",{"href":175,"dataGaLocation":40,"dataGaName":173},"/solutions/value-stream-management/",{"text":177,"config":178},"Analytics & Insights",{"href":179,"dataGaLocation":40,"dataGaName":180},"/solutions/analytics-and-insights/","Analytics and insights",{"title":182,"items":183},"GitLab for",[184,189,194],{"text":185,"config":186},"Enterprise",{"href":187,"dataGaLocation":40,"dataGaName":188},"/enterprise/","enterprise",{"text":190,"config":191},"Small Business",{"href":192,"dataGaLocation":40,"dataGaName":193},"/small-business/","small business",{"text":195,"config":196},"Public Sector",{"href":197,"dataGaLocation":40,"dataGaName":198},"/solutions/public-sector/","public sector",{"text":200,"config":201},"Pricing",{"href":202,"dataGaName":203,"dataGaLocation":40,"dataNavLevelOne":203},"/pricing/","pricing",{"text":205,"config":206,"link":208,"lists":212,"feature":296},"Resources",{"dataNavLevelOne":207},"resources",{"text":209,"config":210},"View all resources",{"href":211,"dataGaName":207,"dataGaLocation":40},"/resources/",[213,246,268],{"title":214,"items":215},"Getting started",[216,221,226,231,236,241],{"text":217,"config":218},"Install",{"href":219,"dataGaName":220,"dataGaLocation":40},"/install/","install",{"text":222,"config":223},"Quick start guides",{"href":224,"dataGaName":225,"dataGaLocation":40},"/get-started/","quick setup checklists",{"text":227,"config":228},"Learn",{"href":229,"dataGaLocation":40,"dataGaName":230},"https://university.gitlab.com/","learn",{"text":232,"config":233},"Product documentation",{"href":234,"dataGaName":235,"dataGaLocation":40},"https://docs.gitlab.com/","product documentation",{"text":237,"config":238},"Best practice videos",{"href":239,"dataGaName":240,"dataGaLocation":40},"/getting-started-videos/","best practice videos",{"text":242,"config":243},"Integrations",{"href":244,"dataGaName":245,"dataGaLocation":40},"/integrations/","integrations",{"title":247,"items":248},"Discover",[249,254,258,263],{"text":250,"config":251},"Customer success stories",{"href":252,"dataGaName":253,"dataGaLocation":40},"/customers/","customer success stories",{"text":255,"config":256},"Blog",{"href":257,"dataGaName":5,"dataGaLocation":40},"/blog/",{"text":259,"config":260},"Remote",{"href":261,"dataGaName":262,"dataGaLocation":40},"https://handbook.gitlab.com/handbook/company/culture/all-remote/","remote",{"text":264,"config":265},"TeamOps",{"href":266,"dataGaName":267,"dataGaLocation":40},"/teamops/","teamops",{"title":269,"items":270},"Connect",[271,276,281,286,291],{"text":272,"config":273},"GitLab Services",{"href":274,"dataGaName":275,"dataGaLocation":40},"/services/","services",{"text":277,"config":278},"Community",{"href":279,"dataGaName":280,"dataGaLocation":40},"/community/","community",{"text":282,"config":283},"Forum",{"href":284,"dataGaName":285,"dataGaLocation":40},"https://forum.gitlab.com/","forum",{"text":287,"config":288},"Events",{"href":289,"dataGaName":290,"dataGaLocation":40},"/events/","events",{"text":292,"config":293},"Partners",{"href":294,"dataGaName":295,"dataGaLocation":40},"/partners/","partners",{"backgroundColor":297,"textColor":298,"text":299,"image":300,"link":304},"#2f2a6b","#fff","Insights for the future of software development",{"altText":301,"config":302},"the source promo card",{"src":303},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758208064/dzl0dbift9xdizyelkk4.svg",{"text":305,"config":306},"Read the latest",{"href":307,"dataGaName":308,"dataGaLocation":40},"/the-source/","the source",{"text":310,"config":311,"lists":313},"Company",{"dataNavLevelOne":312},"company",[314],{"items":315},[316,321,327,329,334,339,344,349,354,359,364],{"text":317,"config":318},"About",{"href":319,"dataGaName":320,"dataGaLocation":40},"/company/","about",{"text":322,"config":323,"footerGa":326},"Jobs",{"href":324,"dataGaName":325,"dataGaLocation":40},"/jobs/","jobs",{"dataGaName":325},{"text":287,"config":328},{"href":289,"dataGaName":290,"dataGaLocation":40},{"text":330,"config":331},"Leadership",{"href":332,"dataGaName":333,"dataGaLocation":40},"/company/team/e-group/","leadership",{"text":335,"config":336},"Team",{"href":337,"dataGaName":338,"dataGaLocation":40},"/company/team/","team",{"text":340,"config":341},"Handbook",{"href":342,"dataGaName":343,"dataGaLocation":40},"https://handbook.gitlab.com/","handbook",{"text":345,"config":346},"Investor relations",{"href":347,"dataGaName":348,"dataGaLocation":40},"https://ir.gitlab.com/","investor relations",{"text":350,"config":351},"Trust Center",{"href":352,"dataGaName":353,"dataGaLocation":40},"/security/","trust center",{"text":355,"config":356},"AI Transparency Center",{"href":357,"dataGaName":358,"dataGaLocation":40},"/ai-transparency-center/","ai transparency center",{"text":360,"config":361},"Newsletter",{"href":362,"dataGaName":363,"dataGaLocation":40},"/company/contact/","newsletter",{"text":365,"config":366},"Press",{"href":367,"dataGaName":368,"dataGaLocation":40},"/press/","press",{"text":370,"config":371,"lists":372},"Contact us",{"dataNavLevelOne":312},[373],{"items":374},[375,378,383],{"text":47,"config":376},{"href":49,"dataGaName":377,"dataGaLocation":40},"talk to sales",{"text":379,"config":380},"Get help",{"href":381,"dataGaName":382,"dataGaLocation":40},"/support/","get help",{"text":384,"config":385},"Customer portal",{"href":386,"dataGaName":387,"dataGaLocation":40},"https://customers.gitlab.com/customers/sign_in/","customer portal",{"close":389,"login":390,"suggestions":397},"Close",{"text":391,"link":392},"To search repositories and projects, login to",{"text":393,"config":394},"gitlab.com",{"href":54,"dataGaName":395,"dataGaLocation":396},"search login","search",{"text":398,"default":399},"Suggestions",[400,402,406,408,412,416],{"text":69,"config":401},{"href":74,"dataGaName":69,"dataGaLocation":396},{"text":403,"config":404},"Code Suggestions (AI)",{"href":405,"dataGaName":403,"dataGaLocation":396},"/solutions/code-suggestions/",{"text":121,"config":407},{"href":123,"dataGaName":121,"dataGaLocation":396},{"text":409,"config":410},"GitLab on AWS",{"href":411,"dataGaName":409,"dataGaLocation":396},"/partners/technology-partners/aws/",{"text":413,"config":414},"GitLab on Google Cloud",{"href":415,"dataGaName":413,"dataGaLocation":396},"/partners/technology-partners/google-cloud-platform/",{"text":417,"config":418},"Why GitLab?",{"href":82,"dataGaName":417,"dataGaLocation":396},{"freeTrial":420,"mobileIcon":425,"desktopIcon":430,"secondaryButton":433},{"text":421,"config":422},"Start free trial",{"href":423,"dataGaName":45,"dataGaLocation":424},"https://gitlab.com/-/trials/new/","nav",{"altText":426,"config":427},"Gitlab Icon",{"src":428,"dataGaName":429,"dataGaLocation":424},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203874/jypbw1jx72aexsoohd7x.svg","gitlab icon",{"altText":426,"config":431},{"src":432,"dataGaName":429,"dataGaLocation":424},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203875/gs4c8p8opsgvflgkswz9.svg",{"text":434,"config":435},"Get Started",{"href":436,"dataGaName":437,"dataGaLocation":424},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com/compare/gitlab-vs-github/","get started",{"freeTrial":439,"mobileIcon":442,"desktopIcon":444},{"text":440,"config":441},"Learn more about GitLab Duo",{"href":74,"dataGaName":21,"dataGaLocation":424},{"altText":426,"config":443},{"src":428,"dataGaName":429,"dataGaLocation":424},{"altText":426,"config":445},{"src":432,"dataGaName":429,"dataGaLocation":424},{"freeTrial":447,"mobileIcon":452,"desktopIcon":454},{"text":448,"config":449},"Back to pricing",{"href":202,"dataGaName":450,"dataGaLocation":424,"icon":451},"back to pricing","GoBack",{"altText":426,"config":453},{"src":428,"dataGaName":429,"dataGaLocation":424},{"altText":426,"config":455},{"src":432,"dataGaName":429,"dataGaLocation":424},"content:shared:en-us:main-navigation.yml","Main Navigation","shared/en-us/main-navigation.yml","shared/en-us/main-navigation",{"_path":461,"_dir":34,"_draft":6,"_partial":6,"_locale":7,"title":462,"button":463,"image":468,"config":472,"_id":474,"_type":26,"_source":28,"_file":475,"_stem":476,"_extension":31},"/shared/en-us/banner","is now in public beta!",{"text":464,"config":465},"Try the Beta",{"href":466,"dataGaName":467,"dataGaLocation":40},"/gitlab-duo/agent-platform/","duo banner",{"altText":469,"config":470},"GitLab Duo Agent Platform",{"src":471},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1753720689/somrf9zaunk0xlt7ne4x.svg",{"layout":473},"release","content:shared:en-us:banner.yml","shared/en-us/banner.yml","shared/en-us/banner",{"_path":478,"_dir":34,"_draft":6,"_partial":6,"_locale":7,"data":479,"_id":683,"_type":26,"title":684,"_source":28,"_file":685,"_stem":686,"_extension":31},"/shared/en-us/main-footer",{"text":480,"source":481,"edit":487,"contribute":492,"config":497,"items":502,"minimal":675},"Git is a trademark of Software Freedom Conservancy and our use of 'GitLab' is under license",{"text":482,"config":483},"View page source",{"href":484,"dataGaName":485,"dataGaLocation":486},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/","page source","footer",{"text":488,"config":489},"Edit this page",{"href":490,"dataGaName":491,"dataGaLocation":486},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/content/","web ide",{"text":493,"config":494},"Please contribute",{"href":495,"dataGaName":496,"dataGaLocation":486},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/CONTRIBUTING.md/","please contribute",{"twitter":498,"facebook":499,"youtube":500,"linkedin":501},"https://twitter.com/gitlab","https://www.facebook.com/gitlab","https://www.youtube.com/channel/UCnMGQ8QHMAnVIsI3xJrihhg","https://www.linkedin.com/company/gitlab-com",[503,526,582,611,645],{"title":58,"links":504,"subMenu":509},[505],{"text":506,"config":507},"DevSecOps platform",{"href":67,"dataGaName":508,"dataGaLocation":486},"devsecops platform",[510],{"title":200,"links":511},[512,516,521],{"text":513,"config":514},"View plans",{"href":202,"dataGaName":515,"dataGaLocation":486},"view plans",{"text":517,"config":518},"Why Premium?",{"href":519,"dataGaName":520,"dataGaLocation":486},"/pricing/premium/","why premium",{"text":522,"config":523},"Why Ultimate?",{"href":524,"dataGaName":525,"dataGaLocation":486},"/pricing/ultimate/","why ultimate",{"title":527,"links":528},"Solutions",[529,534,536,538,543,548,552,555,559,564,566,569,572,577],{"text":530,"config":531},"Digital transformation",{"href":532,"dataGaName":533,"dataGaLocation":486},"/topics/digital-transformation/","digital transformation",{"text":146,"config":535},{"href":148,"dataGaName":146,"dataGaLocation":486},{"text":135,"config":537},{"href":117,"dataGaName":118,"dataGaLocation":486},{"text":539,"config":540},"Agile development",{"href":541,"dataGaName":542,"dataGaLocation":486},"/solutions/agile-delivery/","agile delivery",{"text":544,"config":545},"Cloud transformation",{"href":546,"dataGaName":547,"dataGaLocation":486},"/topics/cloud-native/","cloud transformation",{"text":549,"config":550},"SCM",{"href":131,"dataGaName":551,"dataGaLocation":486},"source code management",{"text":121,"config":553},{"href":123,"dataGaName":554,"dataGaLocation":486},"continuous integration & delivery",{"text":556,"config":557},"Value stream management",{"href":175,"dataGaName":558,"dataGaLocation":486},"value stream management",{"text":560,"config":561},"GitOps",{"href":562,"dataGaName":563,"dataGaLocation":486},"/solutions/gitops/","gitops",{"text":185,"config":565},{"href":187,"dataGaName":188,"dataGaLocation":486},{"text":567,"config":568},"Small business",{"href":192,"dataGaName":193,"dataGaLocation":486},{"text":570,"config":571},"Public sector",{"href":197,"dataGaName":198,"dataGaLocation":486},{"text":573,"config":574},"Education",{"href":575,"dataGaName":576,"dataGaLocation":486},"/solutions/education/","education",{"text":578,"config":579},"Financial services",{"href":580,"dataGaName":581,"dataGaLocation":486},"/solutions/finance/","financial services",{"title":205,"links":583},[584,586,588,590,593,595,597,599,601,603,605,607,609],{"text":217,"config":585},{"href":219,"dataGaName":220,"dataGaLocation":486},{"text":222,"config":587},{"href":224,"dataGaName":225,"dataGaLocation":486},{"text":227,"config":589},{"href":229,"dataGaName":230,"dataGaLocation":486},{"text":232,"config":591},{"href":234,"dataGaName":592,"dataGaLocation":486},"docs",{"text":255,"config":594},{"href":257,"dataGaName":5,"dataGaLocation":486},{"text":250,"config":596},{"href":252,"dataGaName":253,"dataGaLocation":486},{"text":259,"config":598},{"href":261,"dataGaName":262,"dataGaLocation":486},{"text":272,"config":600},{"href":274,"dataGaName":275,"dataGaLocation":486},{"text":264,"config":602},{"href":266,"dataGaName":267,"dataGaLocation":486},{"text":277,"config":604},{"href":279,"dataGaName":280,"dataGaLocation":486},{"text":282,"config":606},{"href":284,"dataGaName":285,"dataGaLocation":486},{"text":287,"config":608},{"href":289,"dataGaName":290,"dataGaLocation":486},{"text":292,"config":610},{"href":294,"dataGaName":295,"dataGaLocation":486},{"title":310,"links":612},[613,615,617,619,621,623,625,629,634,636,638,640],{"text":317,"config":614},{"href":319,"dataGaName":312,"dataGaLocation":486},{"text":322,"config":616},{"href":324,"dataGaName":325,"dataGaLocation":486},{"text":330,"config":618},{"href":332,"dataGaName":333,"dataGaLocation":486},{"text":335,"config":620},{"href":337,"dataGaName":338,"dataGaLocation":486},{"text":340,"config":622},{"href":342,"dataGaName":343,"dataGaLocation":486},{"text":345,"config":624},{"href":347,"dataGaName":348,"dataGaLocation":486},{"text":626,"config":627},"Sustainability",{"href":628,"dataGaName":626,"dataGaLocation":486},"/sustainability/",{"text":630,"config":631},"Diversity, inclusion and belonging (DIB)",{"href":632,"dataGaName":633,"dataGaLocation":486},"/diversity-inclusion-belonging/","Diversity, inclusion and belonging",{"text":350,"config":635},{"href":352,"dataGaName":353,"dataGaLocation":486},{"text":360,"config":637},{"href":362,"dataGaName":363,"dataGaLocation":486},{"text":365,"config":639},{"href":367,"dataGaName":368,"dataGaLocation":486},{"text":641,"config":642},"Modern Slavery Transparency Statement",{"href":643,"dataGaName":644,"dataGaLocation":486},"https://handbook.gitlab.com/handbook/legal/modern-slavery-act-transparency-statement/","modern slavery transparency statement",{"title":646,"links":647},"Contact Us",[648,651,653,655,660,665,670],{"text":649,"config":650},"Contact an expert",{"href":49,"dataGaName":50,"dataGaLocation":486},{"text":379,"config":652},{"href":381,"dataGaName":382,"dataGaLocation":486},{"text":384,"config":654},{"href":386,"dataGaName":387,"dataGaLocation":486},{"text":656,"config":657},"Status",{"href":658,"dataGaName":659,"dataGaLocation":486},"https://status.gitlab.com/","status",{"text":661,"config":662},"Terms of use",{"href":663,"dataGaName":664,"dataGaLocation":486},"/terms/","terms of use",{"text":666,"config":667},"Privacy statement",{"href":668,"dataGaName":669,"dataGaLocation":486},"/privacy/","privacy statement",{"text":671,"config":672},"Cookie preferences",{"dataGaName":673,"dataGaLocation":486,"id":674,"isOneTrustButton":103},"cookie preferences","ot-sdk-btn",{"items":676},[677,679,681],{"text":661,"config":678},{"href":663,"dataGaName":664,"dataGaLocation":486},{"text":666,"config":680},{"href":668,"dataGaName":669,"dataGaLocation":486},{"text":671,"config":682},{"dataGaName":673,"dataGaLocation":486,"id":674,"isOneTrustButton":103},"content:shared:en-us:main-footer.yml","Main Footer","shared/en-us/main-footer.yml","shared/en-us/main-footer",[688],{"_path":689,"_dir":690,"_draft":6,"_partial":6,"_locale":7,"content":691,"config":695,"_id":697,"_type":26,"title":16,"_source":28,"_file":698,"_stem":699,"_extension":31},"/en-us/blog/authors/michael-friedrich","authors",{"name":16,"config":692},{"headshot":693,"ctfId":694},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1749659879/Blog/Author%20Headshots/dnsmichi-headshot.jpg","dnsmichi",{"template":696},"BlogAuthor","content:en-us:blog:authors:michael-friedrich.yml","en-us/blog/authors/michael-friedrich.yml","en-us/blog/authors/michael-friedrich",{"_path":701,"_dir":34,"_draft":6,"_partial":6,"_locale":7,"header":702,"eyebrow":703,"blurb":704,"button":705,"secondaryButton":709,"_id":711,"_type":26,"title":712,"_source":28,"_file":713,"_stem":714,"_extension":31},"/shared/en-us/next-steps","Start shipping better software faster","50%+ of the Fortune 100 trust GitLab","See what your team can do with the intelligent\n\n\nDevSecOps platform.\n",{"text":42,"config":706},{"href":707,"dataGaName":45,"dataGaLocation":708},"https://gitlab.com/-/trial_registrations/new?glm_content=default-saas-trial&glm_source=about.gitlab.com/","feature",{"text":47,"config":710},{"href":49,"dataGaName":50,"dataGaLocation":708},"content:shared:en-us:next-steps.yml","Next Steps","shared/en-us/next-steps.yml","shared/en-us/next-steps",1758326216881]