[{"data":1,"prerenderedAt":814},["ShallowReactive",2],{"/en-us/blog/10-best-practices-for-using-ai-powered-gitlab-duo-chat":3,"navigation-en-us":40,"banner-en-us":450,"footer-en-us":460,"blog-post-authors-en-us-Michael Friedrich":701,"blog-related-posts-en-us-10-best-practices-for-using-ai-powered-gitlab-duo-chat":715,"next-steps-en-us":752,"blog-promotions-en-us":762},{"id":4,"title":5,"authorSlugs":6,"body":8,"categorySlug":9,"config":10,"content":14,"description":8,"extension":27,"isFeatured":12,"meta":28,"navigation":12,"path":29,"publishedDate":20,"seo":30,"stem":35,"tagSlugs":36,"__hash__":39},"blogPosts/en-us/blog/10-best-practices-for-using-ai-powered-gitlab-duo-chat.yml","10 Best Practices For Using Ai Powered Gitlab Duo Chat",[7],"michael-friedrich",null,"ai-ml",{"slug":11,"featured":12,"template":13},"10-best-practices-for-using-ai-powered-gitlab-duo-chat",true,"BlogPost",{"title":15,"description":16,"authors":17,"heroImage":19,"date":20,"body":21,"category":9,"tags":22},"10 best practices for using AI-powered GitLab Duo Chat","Explore tips and tricks for integrating GitLab Duo Chat into your AI-powered DevSecOps workflows. Plus, expert advice on how to refine chat prompts for the best results.",[18],"Michael Friedrich","https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097639/Blog/Hero%20Images/Blog/Hero%20Images/blog-image-template-1800x945%20%281%29_77JeTV9gAmbXM0224acirV_1750097638765.png","2024-04-02","Getting into a conversation with AI can be challenging. What question do you start with? How do you frame the question? How much context is needed? Will the conversation provide the best and most efficient results?\n\nIn this tutorial, we explore 10 tips and best practices to integrate GitLab Duo Chat into your AI-powered DevSecOps workflows and refine your prompts for the best results.\n\n[Get started: Keep GitLab Duo Chat open and in sight](#get-started-keep-gitlab-duo-chat-open-and-in-sight)\n\n[10 best practices for using GitLab Duo Chat](#10-best-practices-for-using-gitlab-duo-chat)\n\n1. [Have a conversation](#1.-have-a-conversation)\n2. [Refine the prompt for more efficiency](#2.-refine-the-prompt-for-more-efficiency)\n3. [Follow prompt patterns](#3.-follow-prompt-patterns)\n4. [Use low-context communication](#4.-use-low-context-communication)\n5. [Repeat yourself](#5.-repeat-yourself)\n6. [Be patient](#6.-be-patient)\n7. [Reset and start anew](#7.-reset-and-start-anew)\n8. [Gain efficiency with slash commands in the IDE](#8.-gain-efficiency-with-slash-commands-in-the-ide)\n9. [Refine the prompt for slash commands](#9.-refine-the-prompt-for-slash-commands)\n10. [Get creative with slash commands](#10.-get-creative-with-slash-commands)\n\nBonus content:\n- [Shortcuts](#shortcuts)\n- [Fun exercises](#fun-exercises)\n- [Learn more](#learn-more)\n\n> Live demo! Discover the future of AI-driven software development with our GitLab 17 virtual launch event. [Register today!](https://about.gitlab.com/eighteen/)\n\n## Get started: Keep GitLab Duo Chat open and in sight\n\n[GitLab Duo Chat](https://docs.gitlab.com/user/gitlab_duo_chat/) is available in the GitLab UI, Web IDE, and supported programming IDEs, for example, VS Code.\n\nIn VS Code, you can open GitLab Duo Chat in the default left pane. You can also drag and drop the icon into the right pane. This allows you to keep Chat open while you write code and navigate the file tree, perform Git actions, etc. To reset the Chat location, open the command palette (by pressing the `Command+Shift+P` (on macOS) or `Ctrl+Shift+P` (on Windows/Linux) keyboard shortcut and then type `View: Reset View Locations`. The following short video shows you how to do it.\n\n\u003C!-- blank line -->\n\u003Cfigure class=\"video_container\">\n  \u003Ciframe src=\"https://www.youtube.com/embed/foZpUvWPRJQ\" frameborder=\"0\" allowfullscreen=\"true\"> \u003C/iframe>\n\u003C/figure>\n\u003C!-- blank line -->\n\nThe Web IDE and VS Code share the same framework – the same method works in the Web IDE for more efficient workflows.\n\n![Chat in Web IDE](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image1_aHR0cHM6_1750097645344.png)\n\n## 10 best practices for using GitLab Duo Chat\n\n### 1. Have a conversation\n\nChats are conversations, not search forms.\n\nFor the first conversation icebreaker, you can start with the same search terms similar to a browser search and experiment with the response and output. In this example, let's start with a C# project and best practices.\n\n> c# start project best practices\n\n![Chat prompt for C# start project best practices and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097646/Blog/Content%20Images/Blog/Content%20Images/image11_aHR0cHM6_1750097645345.png)\n\nThe response is helpful to understand a broad scope of C#, but does not kickstart immediate best practices. Let's follow up with a more focused question in the same context.\n\n> Please show the project structure for the C# project.\n\n![Chat prompt for project structure for the C# project and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image9_aHR0cHM6_1750097645346.png)\n\nThis answer is helpful. Next, let's follow up with a Git question, and use the same question structure: Direct request to show something.\n\n> Show an example for a .gitignore for C#\n\n![Chat prompt for a .gitignore for C# and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image25_aHR0cHM6_1750097645347.png)\n\nContinue with CI/CD and ask how to build the C# project.\n\n> Show a GitLab CI/CD configuration for building the C# project\n\n![Chat prompt for GitLab CI/CD configuration for building C# project and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image16_aHR0cHM6_1750097645349.png)\n\nIn this example, Chat encouraged us to request specific changes. Let's ask to use the .NET SDK 8.0 instead of 6.0.\n\n> In the above example, please use the .NET SDK 8.0 image\n\n![Chat prompt to use .NET SDK 8.0 image and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image32_aHR0cHM6_1750097645350.png)\n\nThe CI/CD configuration uses the .NET command line interface (CLI). Maybe we can use that for more efficient commands to create the projects and tests structure, too?\n\n> Explain how to create projects and test structure on the CLI\n\n![Chat prompt to explain how to create projects and test structure on the CLI and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image14_aHR0cHM6_1750097645351.png)\n\nOf course, we could execute these commands in the terminal, but what if we wanted to stay in VS Code? Let's ask Chat.\n\n> Explain how to open a new terminal in VS Code\n\n![Chat prompt to explain how to open a new terminal in VS Code and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image5_aHR0cHM6_1750097645351.png)\n\n### 2. Refine the prompt for more efficiency\n\nThink of GitLab Duo Chat as a human, and engage with full sentences that provide as much context into your thoughts and questions.\n\nExperienced browser search users might know this approach to queries: Build up the question, add more terms to refine the scope, and restart the search after opening plenty of tabs.\n\nIn a browser search, this probably would result in four to five different search windows.\n\n```markdown\nc# start project best practices\nc# .gitignore\nc# gitlab cicd\nc# gitlab security scanning\nc# solutions and projects, application and tests\n```\n\nYou can follow this strategy in a chat conversation, too. It requires adding more context, making it a conversational approach. GitLab Duo Chat enables you to ask multiple questions in one conversation request. Example: You need to start with a new C# project, apply best practices, add a `.gitignore` file, and configure CI/CD and security scanning, just like in the above search. In Chat, you can combine the questions into one request.\n\n> How can I get started creating an empty C# console application in VS Code? Please show a .gitignore and .gitlab-ci.yml configuration with steps for C#, and add security scanning for GitLab. Explain how solutions and projects in C# work, and how to add a test project on the CLI.\n\n![Chat prompt adding more context and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image37_aHR0cHM6_1750097645352.png)\n\nIn this response, Chat suggests to ask for specific configuration examples in follow-up questions in the conversation. Async practice: Create follow-up questions. You can omit `C#` as context in the same chat session.\n\n> Please show an example for a .gitignore. Please show a CI/CD configuration. Include the SAST template.\n\n### 3. Follow prompt patterns\n\nFollow the pattern: `Problem statement, ask for help, provide additional requests`. Not everything comes to mind when asking the first question – don't feel blocked, and instead start with `Problem statement, ask for help` in the first iteration.\n\n> I need to fulfill compliance requirements. How can I get started with Codeowners and approval rules?\n\n![Chat prompt to get started with Codeowners and approval rules and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image19_aHR0cHM6_1750097645352.png)\n\nThe answer is helpful but obviously generic. Now, you may want to get specific help for your team setup.\n\n> Please show an example for Codeowners with different teams: backend, frontend, release managers.\n\n![Chat prompt to show an example for Codeowners with different teams: backend, frontend, release managers and reponse ](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image31_aHR0cHM6_1750097645353.png)\n\nAn alternative is to describe the situation you are in and to ask for input. It can feel a bit like a conversation to follow the STAR model (Situation, Task, Action, Results).\n\n> I have a Kubernetes cluster integrated in GitLab. Please generate a Yaml configuration for a Kubernetes service deployment. Explain how GitOps works as a second step. How to verify the results?\n\n![Chat prompt with multiple questions and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image27_aHR0cHM6_1750097645354.png)\n\n### 4. Use low-context communication\n\nProvide as much context as needed to provide an answer. Sometimes, the previous history or opened source code does not provide that helpful context. To make questions more efficient, apply a pattern of [low-context communication](https://handbook.gitlab.com/handbook/company/culture/all-remote/effective-communication/#understanding-low-context-communication), which is used in all-remote communication at GitLab.\n\nThe following question did not provide enough context in a C++ project.\n\n> Should I use virtual override instead of just override?\n\n![Chat prompt asking if the users should use virtual override instead of just override and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image34_aHR0cHM6_1750097645354.png)\n\nInstead, try to add more context:\n\n> When implementing a pure virtual function in an inherited class, should I use virtual function override, or just function override? Context is C++.\n\n![Chat prompt with more detail and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image36_aHR0cHM6_1750097645355.png)\n\nThe example is also shown in the [GitLab Duo Coffee Chat: Refactor C++ functions into OOP classes for abstract database handling](https://youtu.be/Z9EJh0J9358?t=2190).\n\n### 5. Repeat yourself\n\nAI is not predictable. Sometimes, it may not answer with the expected results, or does not produce source code examples or configuration snippets because it lacked context. It is recommended to repeat the question and refine the requirements.\n\nIn the following example, we want to create a C# application. In the first attempt, we did not specify the application type – C# can be used to create console/terminal but also UI applications. The result also does not provide an empty example source code. The second, repeated prompt adds two more words - `console` and `empty`.\n\n> How can I get started creating an C# application in VSCode?\n>\n> How can I get started creating an empty C# console application in VSCode?\n\nThe results in the prompt differ. The first response is helpful to get started by following the instructions in the VS Code window, but it does not tell us where the source code is located and how to modify it. The repeated prompt with refinements modifies the response and provides instructions how to override the default template with some “hello world” code.\n\n![Chat prompt with repeated prompt with modifications and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image28_aHR0cHM6_1750097645355.png)\n\nYou can also combine repeat and refine strategies, and ask Chat to show an example for application code and tests.\n\n> How can I get started creating an empty C# console application in VSCode? Please show an example for application and tests.\n\n![Chat prompt that asks for example for application and tests and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image3_aHR0cHM6_1750097645356.png)\n\n#### Repeat yourself after generic questions\n\nWhen asking generic technology questions, GitLab Duo Chat might not be able to help. In the following scenario, I wanted to get a suggestion for Java build tools and framework, and it did not work. There could be many answers: Maven, Gradle, etc., as build tools, and [100+ Java frameworks](https://en.wikipedia.org/wiki/List_of_Java_frameworks), depending on the technology stack and requirements.\n\n![Chat prompt for Java build tools and framework and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image2_aHR0cHM6_1750097645356.png)\n\nLet's assume that we want to focus on a customer environment with [Java Spring Boot](https://spring.io/projects/spring-boot).\n\n> I want to create a Java Spring Boot application. Please explain the project structure and show a hello world example.\n\n![Chat prompt that asks for more, including a hello world example and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image26_aHR0cHM6_1750097645357.png)\n\nThis provides great results already. As an async exercise, repeat the prompt, and ask how to deploy the application, adding more refinements in each step. Alternatively, you can make it a follow-up conversation.\n\n> I want to create a Java Spring Boot application. Please explain the project structure and show a hello world example. Show how to build and deploy the application in CI/CD.\n>\n> I want to create a Java Spring Boot application. Please explain the project structure and show a hello world example. Show how to build and deploy the application in CI/CD, using container images.\n>\n> I want to create a Java Spring Boot application. Please explain the project structure and show a hello world example. Show how to build and deploy the application in CI/CD, using container images. Use Kubernetes and GitOps in GitLab.\n\n### 6. Be patient\n\nSingle words or short sentences might not generate the desired results, [as shown in this video example](https://youtu.be/JketELxLNEw?t=1220). Sometimes, GitLab Duo Chat is able to guess from available data, but sometimes also might insist on providing more context.\n\nExample: `labels` matches the GitLab documentation content.\n\n![Chat prompt about labels and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image12_aHR0cHM6_1750097645357.png)\n\nRefine the question to problem statements and more refinements for issue board usage.\n\n> Explain labels in GitLab. Provide an example for efficient usage with issue boards.\n\n![Chat prompt that includes asking for an example and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image21_aHR0cHM6_1750097645358.png)\n\nOr use a problem statement, followed by a question and the ask for additional examples.\n\n> I don't know how to use labels in GitLab. Please provide examples, and how to use them for filters in different views. Explain these views with examples.\n\n![Chat prompt with problem statement and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image10_aHR0cHM6_1750097645358.png)\n\nAlso, avoid `yes/no` questions and instead add specific context.\n\n> Can you help me fix performance regressions?\n\n![Chat promptt that asks for help with fixing performance regressions and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image18_aHR0cHM6_1750097645359.png)\n\nInstead, provide the context of the performance regression, including the programming languages, frameworks, technology stack, and environments. The following example uses an environment from some years ago, which can still be accurate today.\n\n> My PHP application encounters performance regressions using PHP 5.6 and MySQL 5.5. Please explain potential root causes, and how to address them. The app is deployed on Linux VMs.\n\n![Chat prompt that includes more detail and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image24_aHR0cHM6_1750097645360.png)\n\n### 7. Reset and start anew\n\nSometimes, the chat history shows a different learning curve and provides the wrong context for follow-up questions. Or, you asked specific questions where GitLab Duo Chat cannot provide answers. Since generative AI is not predictable, it might also lack the ability to provide certain examples, but think it gave them in a future response (observed in Chat Beta). The underlying large language models, or LLMs, sometimes might insist on giving a specific response, in an endless loop.\n\n> How can I get started creating an empty C# console application in VSCode? Please show a .gitignore and .gitlab-ci.yml configuration with steps for C#, and add security scanning for GitLab. Explain how solutions and projects in C# work, and how to add a test project on the CLI.\n\nAfter asking the question above with an example configuration, I wanted to reduce the scope of the question to get a more tailored response. It did not work as expected, since Chat knows about the chat history in context, and refers to previous answers.\n\n> How can I get started creating an empty C# console application in VSCode? Please show a .gitignore and .gitlab-ci.yml configuration with steps for C#.\n\n![Chat prompt that asks for configuration examples and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image23_aHR0cHM6_1750097645360.png)\n\nTo force Chat into a new context, use `/reset` as slash command to reset the session, and repeat the question to get better results. You can also use `/clean` or `/clear` to delete all messages in the conversation.\n\n### 8. Gain efficiency with slash commands in the IDE\n\n#### Explain code\n\n- Q: Generated code? Existing code? Legacy code?\n- A: Use the [`/explain` slash command in the IDE](https://docs.gitlab.com/user/gitlab_duo_chat/#explain-code-in-the-ide).\n- A2: Refine the prompt with more focused responses, for example: `/explain focus on potential shortcomings or bugs`.\n\n![Chat prompt with /explain slash command](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/gitlab_duo_chat_slash_commands_explain_01_aHR0cHM6_1750097645361.png)\n\n![Chat prompt with refined prompt](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image6_aHR0cHM6_1750097645361.png)\n\n#### Refactor code\n\n- Q: Unreadable code? Long spaghetti code? Zero test coverage?\n- A: Use the [`/refactor` slash command in the IDE](https://docs.gitlab.com/user/gitlab_duo_chat/#refactor-code-in-the-ide).\n- A2: Refine the prompt for more targeted actions, for example object-oriented patterns: `/refactor into object-oriented classes with methods and attributes`.\n\n![Chat prompt with /refactor slash command](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image35_aHR0cHM6_1750097645362.png)\n\n![Chat prompt with refined prompt](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image30_aHR0cHM6_1750097645362.png)\n\n#### Generate tests\n\n- Q: Testable code but writing tests takes too much time?\n- A: Use the [`/tests` slash command in the IDE](https://docs.gitlab.com/user/gitlab_duo_chat/#write-tests-in-the-ide).\n- A2: Refine the prompt for specific test frameworks, or test targets. You can also instruct the prompt to focus on refactoring, and then generate tests: `/tests focus on refactoring the code into functions, and generate tests`.\n\n![Chat prompt with /tests slash command](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image29_aHR0cHM6_1750097645363.png)\n\n![Chat prompt with refined prompt](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image4_aHR0cHM6_1750097645363.png)\n\nMore practical examples in complete development workflows are available in the [GitLab Duo examples](https://docs.gitlab.com/user/gitlab_duo_examples/) documentation.\n\n### 9. Refine the prompt for slash commands\n\nYou will see refined prompts tips in this blog post a lot. It is one of the ingredients for better AI-powered workflow efficiency. Slash commands are no different, and allow for better results in GitLab Duo Chat.\n\nA customer recently asked: \"Can code explanations using `/explain` create comments in code?\" The answer is: no. But you can use the Chat prompt to ask follow-up questions, and ask for a summary in a code comment format. It requires the context of the language.\n\nThe following example with a [C++ HTTP client code using the curl library](https://gitlab.com/gitlab-da/use-cases/ai/ai-workflows/gitlab-duo-prompts/-/blob/5cc9bdd65ee8ee16c548bea0402c18f8209d4d06/chat/slash-commands/c++/cli.cpp) needs more documentation. You can refine the `/explain` prompt by giving more refined instructions to explain the code by adding code comments, and then copy-paste that into the editor.\n\n> /explain add documentation, rewrite the code snippet\n\n![Chat prompt to add documentation and rewrite code snippet and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image13_aHR0cHM6_1750097645363.png)\n\nAlternatively, you can ask Chat to `/refactor` the source code, and generate missing code comments through a refined prompt.\n\n> /refactor add code comments and documentation\n\n![Chat prompt to refactor source code and generate code comments](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image15_aHR0cHM6_1750097645364.png)\n\n### 10. Get creative with slash commands\n\nWhen the Chat prompt does not know an answer to a question about the source code or programming language, look into the slash commands `/explain`, `/refactor`, and `/tests` and how much they can help in the context.\n\nIn the following example, an SQL query string in C++ is created in a single line. To increase readability, and also add more database columns in the future, it can be helpful to change the formatting into a multi-line string.\n\n> std::string sql = \"CREATE TABLE IF NOT EXISTS users (id INTEGER PRIMARY KEY AUTOINCREMENT, name TEXT NOT NULL, email TEXT NOT NULL)\";\n\nYou can ask GitLab Duo Chat about it, for example, with the following question:\n\n> How to create a string in C++ using multiple lines?\n\nChat may answer with an explanation and optional, a source code example. In this context, it can interpret the question to create a C++ string value with multiple lines, for example, using the `\\n` character, assigned to a variable.\n\nThe requirement instead is to only format the written code, and variable value assignment in multiple lines. The string value itself does not need to contain a multi-line string representation.\n\nThere is an alternative for additional context in VS Code and the Web IDE: Select the source code in question, right-click, and navigate into `GitLab Duo Chat > Refactor`. This opens the Chat prompt and fires the `/refactor` code task immediately.\n\nAlthough, the code task might not bring the expected results. Refactoring a single-line SQL string can mean a lot of things: Use multiple lines for readability, create constants, etc.\n\nCode tasks provide an option to refine the prompt. You can add more text after the `/refactor` command, and instruct GitLab Duo Chat to use a specific code type, algorithm, or design pattern.\n\nLet's try it again: Select the source code, change focus into Chat, and type the following prompt, followed by `Enter`.\n\n> /refactor into a multi-line written string. Show different approaches for all C++ standards.\n\n![Chat prompt to refactor into a multi-line written string and response](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image17_aHR0cHM6_1750097645364.png)\n\n**Tip:** You can use GitLab Duo Code Suggestions to refine the source code even more after refactoring, or use alternative `/refactor` prompt refinements.\n\n>/refactor into a multi-line written string, show different approaches\n>\n> /refactor into multi-line string, not using raw string literals\n>\n> /refactor into a multi-line written string. Make the table name parametrizable\n\nAn alternative approach with the `stringstream` type is shown in the [GitLab Duo Coffee Chat: Refactor C++ functions into OOP classes for abstract database handling](https://www.youtube.com/watch?v=Z9EJh0J9358), [MR diff](https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-coffee-chat/gitlab-duo-coffee-chat-2024-01-23/-/commit/7ea233138aed46d77e6ce0d930dd8e10560134eb#4ce01e4c84d4b62df8eed159c2db3768ad4ef8bf_33_35).\n\n#### Explain vulnerabilities\n\nIt might not always work, but the `/explain` slash command can be asked about security vulnerability explanations, too. In this example, the [C code](https://gitlab.com/gitlab-da/use-cases/ai/ai-workflows/gitlab-duo-prompts/-/blob/5a5f293dfbfac7222ca4013d8f9ce9b462e4cd3a/chat/slash-commands/c/vuln.c) contains multiple vulnerabilities for strcpy() buffer overflows, world writable file permissions, race condition attacks, and more.\n\n> /explain why this code has multiple vulnerabilities\n\n![Chat prompt about the code's multiple vulnerabilities](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image20_aHR0cHM6_1750097645365.png)\n\n#### Refactor C code into Rust\n\nRust provides memory safety. You can ask Duo Chat to refactor the vulnerable [C code](https://gitlab.com/gitlab-da/use-cases/ai/ai-workflows/gitlab-duo-prompts/-/blob/5a5f293dfbfac7222ca4013d8f9ce9b462e4cd3a/chat/slash-commands/c/vuln.c) into Rust, using `/refactor into Rust`. Practice with more refined prompts to get better results.\n\n> /refactor into Rust and use high level libraries\n\n![Chat prompt](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image8_aHR0cHM6_1750097645366.png)\n\n### Shortcuts\n\nGive these shortcuts a try in your environment, and practice async using GitLab Duo Chat.\n\n1. Inspect vulnerable code from CVEs, and ask what it does, and how to fix it, using `/explain why is this code vulnerable`.\n**Tip:** Import open-source projects in GitLab to take advantage of GitLab Duo Chat code explanations.\n1. Try to refactor code into new programming languages to help legacy code migration plans.\n1. You can also try to refactor Jenkins configuration into GitLab CI/CD, using `/refactor into GitLab CI/CD configuration`.\n\n### Fun exercises\n\nTry to convince Chat to behave like Clippy.\n![Chat prompt](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image22_aHR0cHM6_1750097645366.png)\n\nAsk about GitLab's mission: \"Everyone can contribute.\"\n\n![Chat prompt](https://res.cloudinary.com/about-gitlab-com/image/upload/v1750097645/Blog/Content%20Images/Blog/Content%20Images/image33_aHR0cHM6_1750097645367.png)\n\n### Learn more\n\nThere are many different environments and challenges out there. We have updated the [GitLab Duo Chat documentation](https://docs.gitlab.com/user/gitlab_duo_chat/) with more practical examples, and added a new [GitLab Duo examples](https://docs.gitlab.com/user/gitlab_duo_examples/) section with deep dives into AI-powered DevSecOps workflows, including Chat.\n\n> Want to get going with GitLab Duo Chat? [Start your free trial today](https://about.gitlab.com/sales/).\n",[23,24,25,26],"AI/ML","tutorial","DevSecOps platform","features","yml",{},"/en-us/blog/10-best-practices-for-using-ai-powered-gitlab-duo-chat",{"title":15,"description":16,"ogTitle":15,"ogDescription":16,"noIndex":31,"ogImage":19,"ogUrl":32,"ogSiteName":33,"ogType":34,"canonicalUrls":32},false,"https://about.gitlab.com/blog/10-best-practices-for-using-ai-powered-gitlab-duo-chat","https://about.gitlab.com","article","en-us/blog/10-best-practices-for-using-ai-powered-gitlab-duo-chat",[37,24,38,26],"aiml","devsecops-platform","DiZFEtbG3Fp1M4KjnWlIlg8Cxm6tLliZiSB3fCwH0MM",{"data":41},{"logo":42,"freeTrial":47,"sales":52,"login":57,"items":62,"search":370,"minimal":401,"duo":420,"switchNav":429,"pricingDeployment":440},{"config":43},{"href":44,"dataGaName":45,"dataGaLocation":46},"/","gitlab logo","header",{"text":48,"config":49},"Get free trial",{"href":50,"dataGaName":51,"dataGaLocation":46},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com&glm_content=default-saas-trial/","free trial",{"text":53,"config":54},"Talk to sales",{"href":55,"dataGaName":56,"dataGaLocation":46},"/sales/","sales",{"text":58,"config":59},"Sign in",{"href":60,"dataGaName":61,"dataGaLocation":46},"https://gitlab.com/users/sign_in/","sign in",[63,90,185,190,291,351],{"text":64,"config":65,"cards":67},"Platform",{"dataNavLevelOne":66},"platform",[68,74,82],{"title":64,"description":69,"link":70},"The intelligent orchestration platform for DevSecOps",{"text":71,"config":72},"Explore our Platform",{"href":73,"dataGaName":66,"dataGaLocation":46},"/platform/",{"title":75,"description":76,"link":77},"GitLab Duo Agent Platform","Agentic AI for the entire software lifecycle",{"text":78,"config":79},"Meet GitLab Duo",{"href":80,"dataGaName":81,"dataGaLocation":46},"/gitlab-duo-agent-platform/","gitlab duo agent platform",{"title":83,"description":84,"link":85},"Why GitLab","See the top reasons enterprises choose GitLab",{"text":86,"config":87},"Learn more",{"href":88,"dataGaName":89,"dataGaLocation":46},"/why-gitlab/","why gitlab",{"text":91,"left":12,"config":92,"link":94,"lists":98,"footer":167},"Product",{"dataNavLevelOne":93},"solutions",{"text":95,"config":96},"View all Solutions",{"href":97,"dataGaName":93,"dataGaLocation":46},"/solutions/",[99,123,146],{"title":100,"description":101,"link":102,"items":107},"Automation","CI/CD and automation to accelerate deployment",{"config":103},{"icon":104,"href":105,"dataGaName":106,"dataGaLocation":46},"AutomatedCodeAlt","/solutions/delivery-automation/","automated software delivery",[108,112,115,119],{"text":109,"config":110},"CI/CD",{"href":111,"dataGaLocation":46,"dataGaName":109},"/solutions/continuous-integration/",{"text":75,"config":113},{"href":80,"dataGaLocation":46,"dataGaName":114},"gitlab duo agent platform - product menu",{"text":116,"config":117},"Source Code Management",{"href":118,"dataGaLocation":46,"dataGaName":116},"/solutions/source-code-management/",{"text":120,"config":121},"Automated Software Delivery",{"href":105,"dataGaLocation":46,"dataGaName":122},"Automated software delivery",{"title":124,"description":125,"link":126,"items":131},"Security","Deliver code faster without compromising security",{"config":127},{"href":128,"dataGaName":129,"dataGaLocation":46,"icon":130},"/solutions/application-security-testing/","security and compliance","ShieldCheckLight",[132,136,141],{"text":133,"config":134},"Application Security Testing",{"href":128,"dataGaName":135,"dataGaLocation":46},"Application security testing",{"text":137,"config":138},"Software Supply Chain Security",{"href":139,"dataGaLocation":46,"dataGaName":140},"/solutions/supply-chain/","Software supply chain security",{"text":142,"config":143},"Software Compliance",{"href":144,"dataGaName":145,"dataGaLocation":46},"/solutions/software-compliance/","software compliance",{"title":147,"link":148,"items":153},"Measurement",{"config":149},{"icon":150,"href":151,"dataGaName":152,"dataGaLocation":46},"DigitalTransformation","/solutions/visibility-measurement/","visibility and measurement",[154,158,162],{"text":155,"config":156},"Visibility & Measurement",{"href":151,"dataGaLocation":46,"dataGaName":157},"Visibility and Measurement",{"text":159,"config":160},"Value Stream Management",{"href":161,"dataGaLocation":46,"dataGaName":159},"/solutions/value-stream-management/",{"text":163,"config":164},"Analytics & Insights",{"href":165,"dataGaLocation":46,"dataGaName":166},"/solutions/analytics-and-insights/","Analytics and insights",{"title":168,"items":169},"GitLab for",[170,175,180],{"text":171,"config":172},"Enterprise",{"href":173,"dataGaLocation":46,"dataGaName":174},"/enterprise/","enterprise",{"text":176,"config":177},"Small Business",{"href":178,"dataGaLocation":46,"dataGaName":179},"/small-business/","small business",{"text":181,"config":182},"Public Sector",{"href":183,"dataGaLocation":46,"dataGaName":184},"/solutions/public-sector/","public sector",{"text":186,"config":187},"Pricing",{"href":188,"dataGaName":189,"dataGaLocation":46,"dataNavLevelOne":189},"/pricing/","pricing",{"text":191,"config":192,"link":194,"lists":198,"feature":278},"Resources",{"dataNavLevelOne":193},"resources",{"text":195,"config":196},"View all resources",{"href":197,"dataGaName":193,"dataGaLocation":46},"/resources/",[199,232,250],{"title":200,"items":201},"Getting started",[202,207,212,217,222,227],{"text":203,"config":204},"Install",{"href":205,"dataGaName":206,"dataGaLocation":46},"/install/","install",{"text":208,"config":209},"Quick start guides",{"href":210,"dataGaName":211,"dataGaLocation":46},"/get-started/","quick setup checklists",{"text":213,"config":214},"Learn",{"href":215,"dataGaLocation":46,"dataGaName":216},"https://university.gitlab.com/","learn",{"text":218,"config":219},"Product documentation",{"href":220,"dataGaName":221,"dataGaLocation":46},"https://docs.gitlab.com/","product documentation",{"text":223,"config":224},"Best practice videos",{"href":225,"dataGaName":226,"dataGaLocation":46},"/getting-started-videos/","best practice videos",{"text":228,"config":229},"Integrations",{"href":230,"dataGaName":231,"dataGaLocation":46},"/integrations/","integrations",{"title":233,"items":234},"Discover",[235,240,245],{"text":236,"config":237},"Customer success stories",{"href":238,"dataGaName":239,"dataGaLocation":46},"/customers/","customer success stories",{"text":241,"config":242},"Blog",{"href":243,"dataGaName":244,"dataGaLocation":46},"/blog/","blog",{"text":246,"config":247},"Remote",{"href":248,"dataGaName":249,"dataGaLocation":46},"https://handbook.gitlab.com/handbook/company/culture/all-remote/","remote",{"title":251,"items":252},"Connect",[253,258,263,268,273],{"text":254,"config":255},"GitLab Services",{"href":256,"dataGaName":257,"dataGaLocation":46},"/services/","services",{"text":259,"config":260},"Community",{"href":261,"dataGaName":262,"dataGaLocation":46},"/community/","community",{"text":264,"config":265},"Forum",{"href":266,"dataGaName":267,"dataGaLocation":46},"https://forum.gitlab.com/","forum",{"text":269,"config":270},"Events",{"href":271,"dataGaName":272,"dataGaLocation":46},"/events/","events",{"text":274,"config":275},"Partners",{"href":276,"dataGaName":277,"dataGaLocation":46},"/partners/","partners",{"backgroundColor":279,"textColor":280,"text":281,"image":282,"link":286},"#2f2a6b","#fff","Insights for the future of software development",{"altText":283,"config":284},"the source promo card",{"src":285},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758208064/dzl0dbift9xdizyelkk4.svg",{"text":287,"config":288},"Read the latest",{"href":289,"dataGaName":290,"dataGaLocation":46},"/the-source/","the source",{"text":292,"config":293,"lists":295},"Company",{"dataNavLevelOne":294},"company",[296],{"items":297},[298,303,309,311,316,321,326,331,336,341,346],{"text":299,"config":300},"About",{"href":301,"dataGaName":302,"dataGaLocation":46},"/company/","about",{"text":304,"config":305,"footerGa":308},"Jobs",{"href":306,"dataGaName":307,"dataGaLocation":46},"/jobs/","jobs",{"dataGaName":307},{"text":269,"config":310},{"href":271,"dataGaName":272,"dataGaLocation":46},{"text":312,"config":313},"Leadership",{"href":314,"dataGaName":315,"dataGaLocation":46},"/company/team/e-group/","leadership",{"text":317,"config":318},"Team",{"href":319,"dataGaName":320,"dataGaLocation":46},"/company/team/","team",{"text":322,"config":323},"Handbook",{"href":324,"dataGaName":325,"dataGaLocation":46},"https://handbook.gitlab.com/","handbook",{"text":327,"config":328},"Investor relations",{"href":329,"dataGaName":330,"dataGaLocation":46},"https://ir.gitlab.com/","investor relations",{"text":332,"config":333},"Trust Center",{"href":334,"dataGaName":335,"dataGaLocation":46},"/security/","trust center",{"text":337,"config":338},"AI Transparency Center",{"href":339,"dataGaName":340,"dataGaLocation":46},"/ai-transparency-center/","ai transparency center",{"text":342,"config":343},"Newsletter",{"href":344,"dataGaName":345,"dataGaLocation":46},"/company/contact/#contact-forms","newsletter",{"text":347,"config":348},"Press",{"href":349,"dataGaName":350,"dataGaLocation":46},"/press/","press",{"text":352,"config":353,"lists":354},"Contact us",{"dataNavLevelOne":294},[355],{"items":356},[357,360,365],{"text":53,"config":358},{"href":55,"dataGaName":359,"dataGaLocation":46},"talk to sales",{"text":361,"config":362},"Support portal",{"href":363,"dataGaName":364,"dataGaLocation":46},"https://support.gitlab.com","support portal",{"text":366,"config":367},"Customer portal",{"href":368,"dataGaName":369,"dataGaLocation":46},"https://customers.gitlab.com/customers/sign_in/","customer portal",{"close":371,"login":372,"suggestions":379},"Close",{"text":373,"link":374},"To search repositories and projects, login to",{"text":375,"config":376},"gitlab.com",{"href":60,"dataGaName":377,"dataGaLocation":378},"search login","search",{"text":380,"default":381},"Suggestions",[382,384,388,390,394,398],{"text":75,"config":383},{"href":80,"dataGaName":75,"dataGaLocation":378},{"text":385,"config":386},"Code Suggestions (AI)",{"href":387,"dataGaName":385,"dataGaLocation":378},"/solutions/code-suggestions/",{"text":109,"config":389},{"href":111,"dataGaName":109,"dataGaLocation":378},{"text":391,"config":392},"GitLab on AWS",{"href":393,"dataGaName":391,"dataGaLocation":378},"/partners/technology-partners/aws/",{"text":395,"config":396},"GitLab on Google Cloud",{"href":397,"dataGaName":395,"dataGaLocation":378},"/partners/technology-partners/google-cloud-platform/",{"text":399,"config":400},"Why GitLab?",{"href":88,"dataGaName":399,"dataGaLocation":378},{"freeTrial":402,"mobileIcon":407,"desktopIcon":412,"secondaryButton":415},{"text":403,"config":404},"Start free trial",{"href":405,"dataGaName":51,"dataGaLocation":406},"https://gitlab.com/-/trials/new/","nav",{"altText":408,"config":409},"Gitlab Icon",{"src":410,"dataGaName":411,"dataGaLocation":406},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203874/jypbw1jx72aexsoohd7x.svg","gitlab icon",{"altText":408,"config":413},{"src":414,"dataGaName":411,"dataGaLocation":406},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203875/gs4c8p8opsgvflgkswz9.svg",{"text":416,"config":417},"Get Started",{"href":418,"dataGaName":419,"dataGaLocation":406},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com/get-started/","get started",{"freeTrial":421,"mobileIcon":425,"desktopIcon":427},{"text":422,"config":423},"Learn more about GitLab Duo",{"href":80,"dataGaName":424,"dataGaLocation":406},"gitlab duo",{"altText":408,"config":426},{"src":410,"dataGaName":411,"dataGaLocation":406},{"altText":408,"config":428},{"src":414,"dataGaName":411,"dataGaLocation":406},{"button":430,"mobileIcon":435,"desktopIcon":437},{"text":431,"config":432},"/switch",{"href":433,"dataGaName":434,"dataGaLocation":406},"#contact","switch",{"altText":408,"config":436},{"src":410,"dataGaName":411,"dataGaLocation":406},{"altText":408,"config":438},{"src":439,"dataGaName":411,"dataGaLocation":406},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1773335277/ohhpiuoxoldryzrnhfrh.png",{"freeTrial":441,"mobileIcon":446,"desktopIcon":448},{"text":442,"config":443},"Back to pricing",{"href":188,"dataGaName":444,"dataGaLocation":406,"icon":445},"back to pricing","GoBack",{"altText":408,"config":447},{"src":410,"dataGaName":411,"dataGaLocation":406},{"altText":408,"config":449},{"src":414,"dataGaName":411,"dataGaLocation":406},{"title":451,"button":452,"config":457},"See how agentic AI transforms software delivery",{"text":453,"config":454},"Watch GitLab Transcend now",{"href":455,"dataGaName":456,"dataGaLocation":46},"/events/transcend/virtual/","transcend event",{"layout":458,"icon":459,"disabled":12},"release","AiStar",{"data":461},{"text":462,"source":463,"edit":469,"contribute":474,"config":479,"items":484,"minimal":690},"Git is a trademark of Software Freedom Conservancy and our use of 'GitLab' is under license",{"text":464,"config":465},"View page source",{"href":466,"dataGaName":467,"dataGaLocation":468},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/","page source","footer",{"text":470,"config":471},"Edit this page",{"href":472,"dataGaName":473,"dataGaLocation":468},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/content/","web ide",{"text":475,"config":476},"Please contribute",{"href":477,"dataGaName":478,"dataGaLocation":468},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/CONTRIBUTING.md/","please contribute",{"twitter":480,"facebook":481,"youtube":482,"linkedin":483},"https://twitter.com/gitlab","https://www.facebook.com/gitlab","https://www.youtube.com/channel/UCnMGQ8QHMAnVIsI3xJrihhg","https://www.linkedin.com/company/gitlab-com",[485,532,585,629,656],{"title":186,"links":486,"subMenu":501},[487,491,496],{"text":488,"config":489},"View plans",{"href":188,"dataGaName":490,"dataGaLocation":468},"view plans",{"text":492,"config":493},"Why Premium?",{"href":494,"dataGaName":495,"dataGaLocation":468},"/pricing/premium/","why premium",{"text":497,"config":498},"Why Ultimate?",{"href":499,"dataGaName":500,"dataGaLocation":468},"/pricing/ultimate/","why ultimate",[502],{"title":503,"links":504},"Contact Us",[505,508,510,512,517,522,527],{"text":506,"config":507},"Contact sales",{"href":55,"dataGaName":56,"dataGaLocation":468},{"text":361,"config":509},{"href":363,"dataGaName":364,"dataGaLocation":468},{"text":366,"config":511},{"href":368,"dataGaName":369,"dataGaLocation":468},{"text":513,"config":514},"Status",{"href":515,"dataGaName":516,"dataGaLocation":468},"https://status.gitlab.com/","status",{"text":518,"config":519},"Terms of use",{"href":520,"dataGaName":521,"dataGaLocation":468},"/terms/","terms of use",{"text":523,"config":524},"Privacy statement",{"href":525,"dataGaName":526,"dataGaLocation":468},"/privacy/","privacy statement",{"text":528,"config":529},"Cookie preferences",{"dataGaName":530,"dataGaLocation":468,"id":531,"isOneTrustButton":12},"cookie preferences","ot-sdk-btn",{"title":91,"links":533,"subMenu":541},[534,537],{"text":25,"config":535},{"href":73,"dataGaName":536,"dataGaLocation":468},"devsecops platform",{"text":538,"config":539},"AI-Assisted Development",{"href":80,"dataGaName":540,"dataGaLocation":468},"ai-assisted development",[542],{"title":543,"links":544},"Topics",[545,550,555,560,565,570,575,580],{"text":546,"config":547},"CICD",{"href":548,"dataGaName":549,"dataGaLocation":468},"/topics/ci-cd/","cicd",{"text":551,"config":552},"GitOps",{"href":553,"dataGaName":554,"dataGaLocation":468},"/topics/gitops/","gitops",{"text":556,"config":557},"DevOps",{"href":558,"dataGaName":559,"dataGaLocation":468},"/topics/devops/","devops",{"text":561,"config":562},"Version Control",{"href":563,"dataGaName":564,"dataGaLocation":468},"/topics/version-control/","version control",{"text":566,"config":567},"DevSecOps",{"href":568,"dataGaName":569,"dataGaLocation":468},"/topics/devsecops/","devsecops",{"text":571,"config":572},"Cloud Native",{"href":573,"dataGaName":574,"dataGaLocation":468},"/topics/cloud-native/","cloud native",{"text":576,"config":577},"AI for Coding",{"href":578,"dataGaName":579,"dataGaLocation":468},"/topics/devops/ai-for-coding/","ai for coding",{"text":581,"config":582},"Agentic AI",{"href":583,"dataGaName":584,"dataGaLocation":468},"/topics/agentic-ai/","agentic ai",{"title":586,"links":587},"Solutions",[588,590,592,597,601,604,608,611,613,616,619,624],{"text":133,"config":589},{"href":128,"dataGaName":133,"dataGaLocation":468},{"text":122,"config":591},{"href":105,"dataGaName":106,"dataGaLocation":468},{"text":593,"config":594},"Agile development",{"href":595,"dataGaName":596,"dataGaLocation":468},"/solutions/agile-delivery/","agile delivery",{"text":598,"config":599},"SCM",{"href":118,"dataGaName":600,"dataGaLocation":468},"source code management",{"text":546,"config":602},{"href":111,"dataGaName":603,"dataGaLocation":468},"continuous integration & delivery",{"text":605,"config":606},"Value stream management",{"href":161,"dataGaName":607,"dataGaLocation":468},"value stream management",{"text":551,"config":609},{"href":610,"dataGaName":554,"dataGaLocation":468},"/solutions/gitops/",{"text":171,"config":612},{"href":173,"dataGaName":174,"dataGaLocation":468},{"text":614,"config":615},"Small business",{"href":178,"dataGaName":179,"dataGaLocation":468},{"text":617,"config":618},"Public sector",{"href":183,"dataGaName":184,"dataGaLocation":468},{"text":620,"config":621},"Education",{"href":622,"dataGaName":623,"dataGaLocation":468},"/solutions/education/","education",{"text":625,"config":626},"Financial services",{"href":627,"dataGaName":628,"dataGaLocation":468},"/solutions/finance/","financial services",{"title":191,"links":630},[631,633,635,637,640,642,644,646,648,650,652,654],{"text":203,"config":632},{"href":205,"dataGaName":206,"dataGaLocation":468},{"text":208,"config":634},{"href":210,"dataGaName":211,"dataGaLocation":468},{"text":213,"config":636},{"href":215,"dataGaName":216,"dataGaLocation":468},{"text":218,"config":638},{"href":220,"dataGaName":639,"dataGaLocation":468},"docs",{"text":241,"config":641},{"href":243,"dataGaName":244,"dataGaLocation":468},{"text":236,"config":643},{"href":238,"dataGaName":239,"dataGaLocation":468},{"text":246,"config":645},{"href":248,"dataGaName":249,"dataGaLocation":468},{"text":254,"config":647},{"href":256,"dataGaName":257,"dataGaLocation":468},{"text":259,"config":649},{"href":261,"dataGaName":262,"dataGaLocation":468},{"text":264,"config":651},{"href":266,"dataGaName":267,"dataGaLocation":468},{"text":269,"config":653},{"href":271,"dataGaName":272,"dataGaLocation":468},{"text":274,"config":655},{"href":276,"dataGaName":277,"dataGaLocation":468},{"title":292,"links":657},[658,660,662,664,666,668,670,674,679,681,683,685],{"text":299,"config":659},{"href":301,"dataGaName":294,"dataGaLocation":468},{"text":304,"config":661},{"href":306,"dataGaName":307,"dataGaLocation":468},{"text":312,"config":663},{"href":314,"dataGaName":315,"dataGaLocation":468},{"text":317,"config":665},{"href":319,"dataGaName":320,"dataGaLocation":468},{"text":322,"config":667},{"href":324,"dataGaName":325,"dataGaLocation":468},{"text":327,"config":669},{"href":329,"dataGaName":330,"dataGaLocation":468},{"text":671,"config":672},"Sustainability",{"href":673,"dataGaName":671,"dataGaLocation":468},"/sustainability/",{"text":675,"config":676},"Diversity, inclusion and belonging (DIB)",{"href":677,"dataGaName":678,"dataGaLocation":468},"/diversity-inclusion-belonging/","Diversity, inclusion and belonging",{"text":332,"config":680},{"href":334,"dataGaName":335,"dataGaLocation":468},{"text":342,"config":682},{"href":344,"dataGaName":345,"dataGaLocation":468},{"text":347,"config":684},{"href":349,"dataGaName":350,"dataGaLocation":468},{"text":686,"config":687},"Modern Slavery Transparency Statement",{"href":688,"dataGaName":689,"dataGaLocation":468},"https://handbook.gitlab.com/handbook/legal/modern-slavery-act-transparency-statement/","modern slavery transparency statement",{"items":691},[692,695,698],{"text":693,"config":694},"Terms",{"href":520,"dataGaName":521,"dataGaLocation":468},{"text":696,"config":697},"Cookies",{"dataGaName":530,"dataGaLocation":468,"id":531,"isOneTrustButton":12},{"text":699,"config":700},"Privacy",{"href":525,"dataGaName":526,"dataGaLocation":468},[702],{"id":703,"title":18,"body":8,"config":704,"content":706,"description":8,"extension":27,"meta":710,"navigation":12,"path":711,"seo":712,"stem":713,"__hash__":714},"blogAuthors/en-us/blog/authors/michael-friedrich.yml",{"template":705},"BlogAuthor",{"name":18,"config":707},{"headshot":708,"ctfId":709},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1749659879/Blog/Author%20Headshots/dnsmichi-headshot.jpg","dnsmichi",{},"/en-us/blog/authors/michael-friedrich",{},"en-us/blog/authors/michael-friedrich","lJ-nfRIhdG49Arfrxdn1Vv4UppwD51BB13S3HwIswt4",[716,729,741],{"content":717,"config":727},{"title":718,"description":719,"authors":720,"heroImage":722,"date":723,"body":724,"category":9,"tags":725},"GitLab and Anthropic: Governed AI for enterprise development","GitLab deepens its Anthropic Claude integration, bringing governed AI, access to new models, and cloud flexibility to enterprise software development.",[721],"Stuart Moncada","https://res.cloudinary.com/about-gitlab-com/image/upload/v1776457632/llddiylsgwuze0u1rjks.png","2026-04-28","For enterprise and public sector leaders, the tension is familiar: Software teams need to move faster with AI, while security, compliance, and regulatory expectations only get more stringent. GitLab deepens its Anthropic Claude integration so organizations get access to newly released Claude models inside GitLab’s intelligent orchestration platform where governance, compliance, and auditability already run.\n\nClaude powers capabilities across GitLab Duo Agent Platform as the default model out of the box, across a variety of use cases from code generation and review to agentic chat and vulnerability resolution. If you've used GitLab Duo, you've already experienced how Duo agents automate workflows across the entire software development lifecycle (SDLC).\n\nThis accelerates the integration of Claude’s capabilities into GitLab, broadens how enterprises can deploy them, and reinforces what makes GitLab fundamentally different as a platform for software development and engineering: governance, compliance, and auditability built into every AI interaction.\n\n> \"GitLab Duo has accelerated how our teams plan, build, and ship software. The combination of Anthropic's Claude and GitLab's platform means we're getting more capable AI without changing how we work or how it is governed.\"\n>\n> – Mans Booijink, Operations Manager, Cube\n\n## The real differentiator: Governed AI\n\nWith GitLab, governance controls and auditing are built into the SDLC. When Claude suggests a code change through the GitLab Duo Agent Platform, that suggestion flows through the same merge request process, the same approval rules, the same security scanning, and the same audit trail as every other change. AI doesn't get a shortcut around your controls. It operates within them.\n\nAs GitLab moves deeper into agentic software development, where AI autonomously handles well-defined tasks, the governance layer becomes more important. An AI agent that can open a merge request, help resolve a vulnerability, or refactor a service needs to be auditable, attributable, and subject to the same policy enforcement as a human developer. That requirement is an architectural decision GitLab made from the start, and one that grows more consequential as AI agents take on broader responsibilities.\n\n## Enterprise deployment flexibility\n\nThis also expands how organizations access the latest Claude models through GitLab. Claude is available within GitLab through Google Cloud's Vertex AI and Amazon Bedrock, which means enterprises can route AI workloads through the hyperscaler commitments and cloud governance frameworks they already have in place. No separate vendor contract. No new data residency questions. Your existing Google Cloud or AWS relationship is the on-ramp. \n\nGitLab is now also available in the [Claude Marketplace](https://claude.com/platform/marketplace), allowing customers to purchase GitLab Credits and apply them toward existing Anthropic spending commitments – consolidating AI spend and simplifying how teams discover and procure GitLab alongside their Anthropic investments.\n\n## Advancing an agentic future\n\nGitLab's vision for agentic software development, where AI handles defined tasks autonomously across planning, coding, testing, securing, and deploying, requires models with strong reasoning, reliability, and safety characteristics. It also requires a platform where those autonomous actions are fully governed.\n\nAgentic workflows demand models with strong reasoning, reliability, and safety characteristics, criteria that guide how GitLab selects and integrates AI model partners. And GitLab's governance framework helps ensure that as AI agents assume more advanced development work, enterprises maintain full visibility and control over what those agents do, when they do it, and how changes are tracked.\n\n## What this means for GitLab customers\n\nIf you're already using GitLab Duo Agent Platform, you'll get access to Claude models and deeper AI assistance across your software development lifecycle, all within the governance framework you already rely on.\n\nIf you're evaluating AI-powered software development platforms, you shouldn't have to choose between advanced AI capabilities and enterprise control. This strategic integration is built to deliver both.\n\n> Want to learn more about GitLab Duo Agent Platform? [Get a demo or start a free trial today](https://about.gitlab.com/gitlab-duo-agent-platform/).",[23,726,277],"product",{"featured":12,"template":13,"slug":728},"gitlab-and-anthropic-governed-ai-for-enterprise-development",{"content":730,"config":739},{"title":731,"description":732,"authors":733,"heroImage":735,"date":736,"body":737,"category":9,"tags":738},"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.",[734],"Kai Armstrong","https://res.cloudinary.com/about-gitlab-com/image/upload/v1776347152/unw3mzatkd5xyfbzcnni.png","2026-04-27","\nWhen teams use GitLab Duo, Claude, Cursor, and other AI assistants, more of the development workflow runs through an AI agent acting on your behalf — reading issues, reviewing merge requests, running pipelines, and helping you ship faster. Most developers are already using the GitLab CLI (`glab`) from the terminal to interact with GitLab. Combining the two is a natural next step.\n\n\nThe problem is that without the right tools, AI agents are essentially guessing when it comes to your GitLab projects. They might hallucinate the details of an issue they've never seen, summarize a merge request based on stale training data rather than its actual state, or require you to manually copy context from a browser tab and paste it into a chat window just to get started. Every one of those workarounds is friction: it slows you down, introduces the possibility of error, and puts a hard ceiling on what your agent can actually do on your behalf. `glab` changes that by giving agents a direct, reliable interface to your projects.\n\n\nWith `glab`, your agent fetches what it needs directly from GitLab, acts on it, and reports back — so you spend less time relaying information and more time on the work that matters.\n\n\nIn this tutorial, you'll learn how to use `glab` to give AI agents structured, reliable access to your GitLab projects. You'll also discover how that unlocks a faster, more capable development workflow.\n\n\n## How to connect your AI agent to GitLab through MCP\n\n\nThe most direct way to supercharge your AI workflow is to give your AI agent native access to `glab` through Model Context Protocol ([MCP](https://about.gitlab.com/topics/ai/model-context-protocol/)).\n\n\n MCP is an open standard that lets AI tools discover and use external capabilities at runtime. Once connected, your AI assistant can read issues, comment on merge requests, check pipeline status, and write back to GitLab, all without copying anything from the UI or writing a single API call yourself.\n\n\n To get started, run:\n\n\n ```shell\n # Start the glab MCP server\n glab mcp serve\n ```\n\n\n Once your MCP client is configured, your AI can answer questions like *\"What's the status of my open MRs?\"* or *\"Are there any failing pipelines on main?\"* by querying GitLab directly, not scraping the web UI, not relying on stale training data. See the [full setup docs](https://docs.gitlab.com/cli/) for configuration steps for Claude Code, Cursor, and other editors.\n\n\n One detail worth knowing: `glab` automatically adds `--output json` when invoked through MCP, for any command that supports it. Your agent gets clean, structured data without you needing to think about output formats. And because `glab` uses the official MCP SDK, it stays compatible as the\n protocol evolves.\n\n\n We've also been deliberate about *which* commands are exposed through MCP. Commands that require interactive terminal input are intentionally\n excluded, so your agent never gets stuck waiting for input that will never come. What's exposed is what actually works reliably in an agent context.\n\n\n ## Let your AI participate in code review\n\n\n Most developers have a backlog of MRs waiting for review. It's one of the most time-consuming parts of the job and one of the best places to put\n AI to work. With `glab`, your agent doesn't just observe your review queue, it can work through it with you.\n\n\n ### See exactly what still needs addressing\n\n\n Start with this:\n\n\n ```shell\n glab mr view 2677 --comments --unresolved --output json\n ```\n\n\n This input returns the full MR: metadata, description, and every\n unresolved discussion, as a single structured JSON payload. Hand that to\n your AI and it has everything it needs: which threads are open, what the\n reviewer asked for, and in what context. No tab-switching, no copy-pasting\n individual comments.\n\n\n \n ```json\n {\n   \"id\": 2677,\n   \"title\": \"feat: add OAuth2 support\",\n   \"state\": \"opened\",\n   \"author\": { \"username\": \"jdwick\" },\n   \"labels\": [\"backend\", \"needs-review\"],\n   \"blocking_discussions_resolved\": false,\n   \"discussions\": [\n     {\n       \"id\": \"3107030349\",\n       \"resolved\": false,\n       \"notes\": [\n         {\n           \"author\": { \"username\": \"dmurphy\" },\n           \"body\": \"This error handling will swallow panics — consider wrapping with recover()\",\n           \"created_at\": \"2026-03-14T09:23:11.000Z\"\n         }\n       ]\n     },\n     {\n       \"id\": \"3107030412\",\n       \"resolved\": false,\n       \"notes\": [\n         {\n           \"author\": { \"username\": \"sreeves\" },\n           \"body\": \"Token refresh logic needs a test for the expired token case\",\n           \"created_at\": \"2026-03-14T10:05:44.000Z\"\n         }\n       ]\n     }\n   ]\n }\n ```\n\n\n Instead of reading through every thread yourself, you ask your agent  *\"what do I still need to fix in MR 2677?\"* and get back a prioritized summary with suggested changes. This all happens from a single command.\n\n\n ### Close the loop programmatically\n\n\n Once your AI has helped you address the feedback, it can resolve\n discussions:\n\n\n ```shell\n # List all discussions — structured, ready for the agent to process\n glab mr note list 456 --output json\n\n # Resolve a discussion once the feedback is addressed\n glab mr note resolve 456 3107030349\n\n # Reopen if something needs another look\n glab mr note reopen 456 3107030349\n ```\n\n\n\n ```json\n [\n   {\n     \"id\": 3107030349,\n     \"body\": \"This error handling will swallow panics — consider wrapping with recover()\",\n     \"author\": { \"username\": \"dmurphy\" },\n     \"resolved\": false,\n     \"resolvable\": true\n   },\n   {\n     \"id\": 3107030412,\n     \"body\": \"Token refresh logic needs a test for the expired token case\",\n     \"author\": { \"username\": \"sreeves\" },\n     \"resolved\": false,\n     \"resolvable\": true\n   }\n ]\n ```\n\n\n\n Note IDs are visible directly in the GitLab UI and API, no extra lookup needed. Your agent can work through the full list, verify each fix, and\n resolve as it goes.\n\n\n ## Talk to your AI about your code more effectively\n\n\n Even if you're not running an MCP server, there's a simpler shift that makes a huge difference: using `glab` to feed your AI better information.\n\n\n Think about the last time you asked an AI assistant to help triage issues or debug a failing pipeline. You probably copied some text from the GitLab UI and pasted it into the chat. Here's what your agent is actually\n working with when you do that:\n\n\n ```text\n open issues: 12 • milestone: 17.10 • label: bug, needs-triage ...\n ```\n\n\n Compare that to what it gets with `glab`:\n\n\n \n ```json\n [\n   {\n     \"iid\": 902,\n     \"title\": \"Pipeline fails on merge to main\",\n     \"labels\": [\"bug\", \"needs-triage\"],\n     \"milestone\": { \"title\": \"17.10\" },\n     \"assignees\": []\n   },\n   ...\n ]\n ```\n\n\n Structured, typed, complete; no ambiguity, no parsing guesswork. That's the difference between an agent that can act and one that has to ask\n follow-up questions.\n\n\n If you're using the MCP server, you get this automatically: `glab` adds `--output json` for any command that supports it. If you're working directly\n from the terminal, just add the flag yourself:\n\n\n ```shell\n # Pull open issues for triage\n glab issue list --label \"needs-triage\" --output json\n\n # Check pipeline status\n glab ci status --output json\n\n # Get full MR details\n glab mr view 456 --output json\n ```\n\n\n We've significantly expanded JSON output support in recent releases. It now covers CI status, milestones, labels, releases, schedules, cluster agents, work items, MR approvers, repo contributors, and more. If `glab` can\n retrieve it, your AI can consume it cleanly.\n\n\n ### A real workflow\n\n\n ```shell\n $ glab issue list --label \"needs-triage\" --milestone \"17.10\"\n --output json\n ```\n\n\n ```text\n Agent: I found 2 unassigned bugs in the 17.10 milestone that need triage:\n 1. #902 — Pipeline fails on merge to main (opened 5 days ago)\n 2. #903 — Auth token not refreshing on expiry (opened 4 days ago)\n Both are unassigned. Want me to draft triage notes and suggest assignees based on recent commit history?\n ```\n\n\n ## Your agent is never limited to built-in commands\n\n\n `glab`'s first-class commands cover the most common workflows, but your agent is never limited to them. Through `glab api`, it has authenticated access to the full GitLab REST and GraphQL API surface, using the same session, with no extra credentials or configuration required.\n\n\n This is a meaningful differentiator. Most CLI tools stop at what their commands expose. With `glab`, if GitLab's API supports it, your agent can do it. It's always working from a trusted, authenticated context.\n\n\n A practical example: fetching just the list of changed files in an MR before deciding which diffs to pull in full:\n\n\n ```shell\n # Get changed file paths — lightweight, no diff content yet\n glab api \"/projects/$CI_PROJECT_ID/merge_requests/$CI_MERGE_REQUEST_IID/diffs?per_page=100\" \\\n | jq '.[].new_path'\n\n# Then fetch only the specific file your agent needs\nglab api \"/projects/$CI_PROJECT_ID/merge_requests/$CI_MERGE_REQUEST_IID/diffs?per_page=100\" \\\n| jq '.[] | select(.new_path == \"path/to/file.go\")'\n ```\n\n\n ```text\n \"internal/auth/token.go\"\n \"internal/auth/token_test.go\"\n \"internal/oauth/refresh.go\"\n ```\n\n\n For anything the REST API doesn't cover (epics, certain work item queries, complex cross-project data),  `glab api graphql` gives you the full\n GraphQL interface:\n\n\n ```shell\n   glab api graphql -f query='\n {\n   project(fullPath: \"gitlab-org/gitlab\") {\n     mergeRequest(iid: \"12345\") {\n       title\n       reviewers { nodes { username } }\n     }\n   }\n }'\n ```\n\n ```json\n{\n   \"data\": {\n     \"project\": {\n       \"mergeRequest\": {\n         \"title\": \"feat: add OAuth2 support\",\n         \"reviewers\": {\n           \"nodes\": [\n             { \"username\": \"dmurphy\" },\n             { \"username\": \"sreeves\" }\n           ]\n         }\n       }\n     }\n   }\n }\n\n ```\n\n\n Your agent has a single, authenticated entry point to everything GitLab exposes without the token juggling, separate API clients, or configuration\n overhead.\n\n\n ## What's coming and your feedback\n\n\n Two improvements we're actively working on will make `glab` even more useful for agent workflows:\n\n\n **Agent-aware help text.** Today, `--help` output is written for humansvat a terminal. We're updating it to surface the non-interactive alternative\n for every interactive command, flag which commands support `--output json`, and generally make help a useful resource for agents discovering\n capabilities at runtime — not just humans.\n\n\n **Better machine-readable errors.** When something goes wrong today, agents get the same human-readable error messages as terminal users. We're\n changing that so errors in JSON mode return structured output, giving your agent the information it needs to handle failures gracefully, retry intelligently, or surface the right context back to you.\n\n\n Both of these are in active development. If you're already using `glab` with an AI tool, you're exactly the audience we want feedback from.\n\n\n * **What friction are you hitting?** Commands that don't behave well in agent contexts, error messages that aren't actionable, gaps in JSON output\n coverage. We want to know.\n\n * **What workflows have you unlocked?** Real usage patterns help us prioritize what to build next.\n\n\n Join the discussion in [our feedback issue](https://gitlab.com/gitlab-org/cli/-/issues/8177) — that's where we're shaping the roadmap for agent-friendliness, and where your input will have the most direct impact. If you've found a specific gap, [open an issue](https://gitlab.com/gitlab-org/cli/-/issues/new). If you've got a fix in mind, contributions are welcome. Visit [CONTRIBUTING.md](https://gitlab.com/gitlab-org/cli/-/blob/main/CONTRIBUTING.md) to get started.\n\n\n The GitLab CLI has always been about giving developers more control over their workflow. As AI becomes a bigger part of how we all work, that means making `glab` the best possible interface between your AI tools and your GitLab projects. We're just getting started and we'd love to build the next part with you.\n",[23,726,24],{"featured":12,"template":13,"slug":740},"give-your-ai-agent-direct-structured-gitlab-access-with-glab-cli",{"content":742,"config":750},{"title":743,"description":744,"authors":745,"heroImage":735,"date":747,"body":748,"category":9,"tags":749},"GitHub Copilot's new policy for AI training is a governance wake-up call","Learn what GitHub's Copilot policy change means for regulated industries, and why GitLab's commitment to customer data privacy matters.",[746],"Allie Holland","2026-04-20","GitHub recently [announced](https://github.blog/news-insights/company-news/updates-to-github-copilot-interaction-data-usage-policy/) a significant change to how it handles data from Copilot users. Starting April 24, 2026, interaction data from Copilot Free, Pro, and Pro+ users, including inputs, outputs, code snippets, and associated context, will be used to train AI models by default, unless users actively opt out. Copilot Business and Enterprise customers are exempt under existing contract terms.\n\nFor organizations in regulated industries, including finance, healthcare, defense, and public sector, the policy shift raises questions that go beyond individual developer preferences. It forces a harder look at a question that engineering and security leaders should be asking every AI vendor in their stack: Do you train on our code? \n\nGitLab's answer is no. GitLab does not train AI models on customer code at any tier, and AI vendors are contractually prohibited from using customer inputs or outputs for their own purposes. The [GitLab AI Transparency Center](https://about.gitlab.com/ai-transparency-center/) makes that commitment auditable: a single location documenting which models power which features, how data is handled, subprocessor relationships, and data retention periods. The GitLab AI Transparency Center also lists the compliance status of each feature, including confirmation that GitLab's current AI features do not qualify as high-risk systems under the EU AI Act. It's a standard GitLab CEO Bill Staples has consistently [reiterated](https://www.linkedin.com/posts/williamstaples_gitlab-1810-agentic-ai-now-open-to-even-activity-7443280763715985408-aHxf?utm_source=share&utm_medium=member_desktop&rcm=ACoAABsu7EUBcb_a1-JHKS9RC0B5rf8Ye-5XM60) and one reflected in GitLab's mission and [Trust Center](https://trust.gitlab.com/).\n\n## What the policy change actually means\n\nGitHub's announcement also specifies that the data may be shared with GitHub affiliates, including Microsoft, for AI development purposes.\n\nA policy change of this nature forces organizations to re-examine their AI governance posture, audit their Copilot license tiers, and confirm that the right controls are configured across their teams.\n\n## Why AI governance matters in regulated environments\n\nSource code is often among an organization's most sensitive intellectual property. It may contain references to internal systems, reflect proprietary business logic, or touch data flows governed by strict retention and access policies. When that code passes through an AI assistant, questions about training data usage, model vendor relationships, and data residency become compliance concerns.\n\nThe exposure is particularly acute for financial services firms that have invested in proprietary algorithms, fraud detection logic, credit risk models, underwriting rules, trading strategies. When AI tooling processes that code and uses it to train models serving competitors, vendor data practices become an IP concern.\n\nFinancial institutions operating under [the Federal Reserve's Supervisory Guidance on Model Risk Management (SR 11-7) and the](https://www.federalreserve.gov/supervisionreg/srletters/sr1107.htm) [Digital Operational Resilience Act (DORA)](https://eur-lex.europa.eu/eli/reg/2022/2554/oj/eng) are required to maintain documented, auditable oversight of third-party technology providers, including understanding how those providers handle data. Third-party AI tools used in development workflows increasingly fall within the scope of model risk oversight, and material changes to vendor data practices require updated documentation. \n\nIn the public sector, [the National Institute of Standards and Technology Special Publication 800-53 (NIST 800-53)](https://csrc.nist.gov/publications/detail/sp/800-53/rev-5/final) and the [Federal Information Security Modernization Act (FISMA)](https://www.cisa.gov/topics/cyber-threats-and-advisories/federal-information-security-modernization-act) establish that sensitive or classified code must never leave a controlled boundary. For U.S. Department of Defense and intelligence community environments in particular, a vendor's default data posture is an operational concern. In healthcare, [the Health Insurance Portability and Accountability Act (HIPAA)](https://www.hhs.gov/hipaa/index.html) governs how patient-adjacent data is handled by third parties, and development environments that touch clinical systems increasingly fall within that scope.\n\nAcross all of these contexts, the common thread is the same: A vendor policy that changes data usage defaults, requires individual opt-out, and offers different protections depending on account tier introduces exactly the kind of uncontrolled variable that compliance teams cannot afford.\n\n## What regulated industries actually need from AI vendors\n\nRegulated organizations have largely moved past debating whether to adopt AI in development workflows. The focus now is on doing so in a way they can defend to regulators, boards, and customers. That shift has surfaced a consistent set of requirements regardless of sector.\n\n**Contractual certainty.** Regulated firms need to know, with specificity, what happens to their data. A clear, documented, unconditional commitment is what's required, not something that varies by plan or requires action before a deadline.\n\n**Auditability.** Model risk management frameworks require organizations to understand and validate the AI systems they deploy, including the training data behind those models and the third parties involved in their development. Vendors who cannot answer these questions create documentation risk for the organizations relying on them.\n\n**Separation from vendor incentives.** When an AI vendor trains models on customer usage data, code and workflows become inputs to a system that also serves competitors. For institutions with proprietary trading logic, underwriting models, or fraud detection systems, that's a genuine IP exposure.\n\n## GitLab's position on AI data governance\n\nGitLab does not use customer code to train AI models. This commitment applies at every tier, and AI vendors are contractually prohibited from using inputs or outputs associated with GitLab customers for their own purposes.\n\nThis is a deliberate architectural and policy choice, not a feature of a particular pricing tier. As GitLab's [post on enterprise independence](https://about.gitlab.com/blog/why-enterprise-independence-matters-more-than-ever-in-devsecops/) notes, data governance has become \"an increasingly critical factor in enterprise technology decisions, driven by a complex web of national and regional data protection laws and growing concern about control over sensitive intellectual property.\"\n\nGitLab is also cloud-neutral and model-neutral while supporting self-hosted deployments, not commercially tied to any single cloud provider or large language model (LLM). That i[ndependence matters](https://about.gitlab.com/blog/why-enterprise-independence-matters-more-than-ever-in-devsecops/) for regulated organizations evaluating vendor concentration risk. The [AI Continuity Plan](https://handbook.gitlab.com/handbook/product/ai/continuity-plan/) documents how vendor changes are managed, including material changes to how AI vendors treat customer data, a direct response to the governance requirements under frameworks like [DORA](https://handbook.gitlab.com/handbook/legal/dora/). \n\n## The governance gap AI teams need to close\n\nGitHub's policy update is a reminder that for organizations in regulated industries, understanding exactly how an AI tool handles data is a prerequisite for using it at all. That means asking vendors for clear, documented answers: Is our data used for model training? Who are your AI model subprocessors? What happens if a vendor changes its data practices? Can we deploy in a way that keeps all AI processing within our own infrastructure? What indemnification do you offer for AI-generated output?\n\nVendors who can answer those questions clearly, and document those answers in an auditable form, are vendors you can build on. **Those who cannot will create compliance debt every time they ship a policy update.** And when a vendor can change its data practices with 30 days notice, that's not a partnership built for regulated industries. That's a liability.\n\n> Learn more about GitLab's approach to AI governance at the [GitLab AI Transparency Center](https://about.gitlab.com/ai-transparency-center/).",[23,726],{"featured":31,"template":13,"slug":751},"github-copilots-new-policy-for-ai-training-is-a-governance-wake-up-call",{"header":753,"blurb":754,"button":755,"secondaryButton":760},"Start building faster today","See what your team can do with the intelligent orchestration platform for DevSecOps.\n",{"text":756,"config":757},"Get your free trial",{"href":758,"dataGaName":51,"dataGaLocation":759},"https://gitlab.com/-/trial_registrations/new?glm_content=default-saas-trial&glm_source=about.gitlab.com/","feature",{"text":506,"config":761},{"href":55,"dataGaName":56,"dataGaLocation":759},{"promotions":763},[764,777,788,800],{"id":765,"categories":766,"header":767,"text":768,"button":769,"image":774},"ai-modernization",[9],"Is AI achieving its promise at scale?","Quiz will take 5 minutes or less",{"text":770,"config":771},"Get your AI maturity score",{"href":772,"dataGaName":773,"dataGaLocation":244},"/assessments/ai-modernization-assessment/","modernization assessment",{"config":775},{"src":776},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/qix0m7kwnd8x2fh1zq49.png",{"id":778,"categories":779,"header":780,"text":768,"button":781,"image":785},"devops-modernization",[726,569],"Are you just managing tools or shipping innovation?",{"text":782,"config":783},"Get your DevOps maturity score",{"href":784,"dataGaName":773,"dataGaLocation":244},"/assessments/devops-modernization-assessment/",{"config":786},{"src":787},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138785/eg818fmakweyuznttgid.png",{"id":789,"categories":790,"header":792,"text":768,"button":793,"image":797},"security-modernization",[791],"security","Are you trading speed for security?",{"text":794,"config":795},"Get your security maturity score",{"href":796,"dataGaName":773,"dataGaLocation":244},"/assessments/security-modernization-assessment/",{"config":798},{"src":799},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/p4pbqd9nnjejg5ds6mdk.png",{"id":801,"paths":802,"header":805,"text":806,"button":807,"image":812},"github-azure-migration",[803,804],"migration-from-azure-devops-to-gitlab","integrating-azure-devops-scm-and-gitlab","Is your team ready for GitHub's Azure move?","GitHub is already rebuilding around Azure. Find out what it means for you.",{"text":808,"config":809},"See how GitLab compares to GitHub",{"href":810,"dataGaName":811,"dataGaLocation":244},"/compare/gitlab-vs-github/github-azure-migration/","github azure migration",{"config":813},{"src":787},1777576576280]