With seamless integration between VS Code, GitHub and Azure, we provide a comprehensive AI development platform to transform your applications with AI.
Artificial intelligence has changed our expectations of what technology can achieve. From transforming the way we explore the universe to enabling doctors to deliver personalized care and business functions to operate more intelligently, it’s up to you, the developers, to make this potential a reality. As developers, you are experiencing a dramatic shift in what and how you build. And the tools you use should fit seamlessly into your workflow, solve real problems quickly, and keep you in the flow of development.
As a company of developers building for other developers, we’re excited to be a part of this change, and many of us will be sharing our experiences and learning from others on GitHub Universe about how AI is reshaping the way we work. We will not come empty-handed. I’m excited to announce new capabilities and tools that further integrate Microsoft Azure AI services directly into your favorite developer tools.
With seamless integration between Visual Studio (VS) Code, GitHub, and Azure, we provide a comprehensive AI development platform built on strong community support to help you transform your applications with AI. Read on for details and be sure to follow all GitHub news this week.
Now in Preview: GitHub Copilot for Azure, your personal expert
By integrating with tools you already use, like GitHub and Visual Studio Code, GitHub Copilot for Azure builds on the Copilot Chat capabilities of VS Code to help you manage resources and deploy applications. With “@azure” you can get personalized guidance to learn about services and tools without leaving your code. This can speed up and streamline development by provisioning and deploying Azure resources through Azure Developer CLI (azd) templates. GitHub Copilot for Azure also helps you diagnose issues and answer questions about resources and costs, saving you time so you can focus on what you prefer while GitHub Copilot for Azure takes care of the rest. Get started today.
Deploy in just five minutes using AI application templates
AI app templates accelerate your development by helping you get started faster and simplifying the evaluation and path to production. You can use AI app templates directly in your preferred development environment, such as GitHub Codespaces, VS Code, and Visual Studio. You can even get recommendations for specific templates directly from GitHub Copilot for Azure based on your use case or AI scenario. Most importantly, templates provide flexibility and choice, offering a variety of models, frameworks, programming languages, and solutions from popular AI toolchain vendors such as Arize, LangChain, LlamaIndex, and Pinecone. You can deploy entire applications at once or start with application components and provision resources across Azure and partner services. The templates also include recommendations for increased security, such as the use of Managed Identity and keyless authentication flows. Get started.
Customize and scale your AI applications
To help you quickly discover, learn, and experiment with a variety of the latest and most advanced AI models, GitHub today announced that GitHub Models is now in Preview, bringing you a selection of leading Azure AI models directly on GitHub. Building on this topic, the Azure AI model inference API now allows you to explore and access Azure AI models directly through the GitHub Marketplace. Compare model performance, experiment, and combine different models, including advanced proprietary and open source models that support a wide range of tasks, for free (usage limits apply).
Once you’ve chosen your model and are ready to customize and deploy, you can seamlessly set up and sign in to your Azure account and scale from free token usage to paid endpoints with enterprise-grade security and monitoring in production. Find out more.
Simplify Java Runtime updates with the GitHub Copilot Upgrade Assistant for Java
Keeping your Java applications up-to-date can be a time-consuming task. GitHub Copilot upgrade assistant for Java offers an AI-powered approach to simplify this process, allowing you to upgrade your Java applications with minimal manual effort. Integrated into popular tools like Visual Studio Code, the GitHub Copilot upgrade assistant for Java generates an upgrade plan and guides you through the process of moving from an older Java runtime to a newer version with optional dependencies and frameworks like Spring. Boot and JUnit. During an upgrade, the assistant automatically fixes issues through a dynamic build or fix loop and uses a human-in-the-loop approach to resolve other bugs and make fixes if necessary. It ensures transparency by providing access to logs, code changes, outputs and details at every step, giving you full control while benefiting from AI-enhanced automation throughout the process. Once the upgrade is complete, you can easily view a detailed summary and review all code modifications, making the entire upgrade process smooth and efficient, allowing you to focus on innovation instead of manual maintenance.
Scale AI applications with Azure AI evaluation and online A/B experimentation with CI/CD workflows
Given the trade-offs between business impact, risk and cost, you need to be able to constantly evaluate your AI applications and run A/B experiments at scale. We greatly simplify this process with GitHub Actions, which can be seamlessly integrated into existing GitHub CI/CD workflows. In your CI workflows, you’ll be able to run automated post-change evaluations using the Azure AI Evaluation SDK to calculate metrics like coherence and fluidity. After successful deployment, A/B experiments are automatically created and analyzed using pre-built AI model metrics and custom metrics as part of CD workflows. While you’re at it, you can also join the GitHub Copilot for Azure plugin to help with experimentation, create metrics, enable decision making, and more. Stay tuned for more details on the Microsoft Ignite website and sign up for our private preview to learn more!
We trust our business with Azure, so can you
When exploring new AI options for your organization, the platform you choose matters. Today, 95% of Fortune 500 companies trust their operations in Azure. Our business, including Microsoft 365, Dynamics 365, Bing, Copilots, etc., also runs on Azure. The same tools and services we use to build and run Microsoft are available to you. Our integration with GitHub and Visual Studio Code simplifies building with AI in Azure. And with more than 60 data center regions around the world and a dedicated security team, Azure offers a reliable and secure foundation for your AI projects. These are great reasons to build your next AI app with GitHub and Azure.
And if you’re at GitHub Universe this week, stop by and say hello to the Azure team.
About Jessica
Jessica leads data, artificial intelligence and digital application marketing at Microsoft. Find Jessica’s blog posts here and be sure to follow Jessica on LinkedIn.