Microsoft’s AI Toolkit for Visual Studio Code hits version 0.14.0 with powerful new features like integrated evaluation, built-in agent evaluators, model optimization tools, and LoRA adapter training on Azure. Now part of the AI Tools extension pack, it streamlines AI app development. Unique :
AI Toolkit for VS Code June Update: What’s New and Why It Matters
Microsoft just dropped a major update for the AI Toolkit in Visual Studio Code. Version 0.14.0 is packed with features that will seriously boost your AI development workflow. Whether you’re building intelligent agents or fine-tuning models, this update has something for you.
Integrated Evaluation and Built-in Agent Evaluators
One of the coolest additions is the integrated evaluation suite for AI agents. Now, you can switch smoothly between prompting and evaluation without leaving your editor. It also supports generating synthetic data with large language models and importing/exporting datasets in CSV or JSONL formats.
Microsoft added quick feedback options with thumbs-up/down indicators, making it easier to rate your agent’s performance on the fly. Plus, new built-in evaluators help you measure key metrics like Intent Resolution, Tool Call Accuracy, and Task Adherence.
“You can now seamlessly switch between prompting and evaluation, generate synthetic data using LLMs, and provide quick feedback on results.”
Model Conversion, Optimization, and LoRA Adapter Training
The update also simplifies model management. New tools let you convert and optimize models with recipes tailored for Intel, AMD, and Qualcomm NPUs. All of this happens inside a customizable workspace, so your workflow stays neat and efficient.
For fine-tuning enthusiasts, launching LoRA adapter training jobs on Azure is now a breeze. After training, just download your adapter and integrate it directly into your Windows AI apps.
Expanded Model Library and AI Tools Extension Pack
Microsoft onboarded fresh models like DeepSeek-V3, Llama-4-Maverick, Phi-4-reasoning, and cohere-command-a. These models bring advanced reasoning, code generation, and multimodal capabilities right to your fingertips.
Additionally, the AI Toolkit is now a core part of the new AI Tools extension pack for VS Code. This pack bundles powerful tools to explore models, transform data, build agents locally, and deploy to Azure—all from your editor.
Sneak Peek: June Pre-release Features
Looking ahead, the June pre-release will introduce function calling, letting your AI models invoke custom functions for richer interactions. Version management will help you save, track, and delete versions of your work effortlessly.
Also, a new evaluation comparison view will make it easier to spot differences between evaluation runs, helping you optimize your agents faster.
“We believe these updates will help you build amazing AI-powered applications with even greater ease and efficiency.”
Get Started Today
Ready to level up your AI projects? Download the AI Toolkit and the AI Tools extension pack from the Visual Studio Marketplace. Join the community on GitHub to share feedback and help shape the future of AI development in VS Code.
With these updates, Microsoft is making AI development more integrated, efficient, and powerful. Happy coding!
From the Microsoft Developer Community Blog articles
Windows Server Devices Now Recognized as a New OS in Intune Microsoft has announced that Windows Server devices are Read more
Microsoft Power Platform is leading the way in AI-generated low-code app development. With the help of AI, users can quickly Read more
Microsoft Intune is an enterprise mobility management platform that helps organizations manage mobile devices, applications, and data. The October edition Read more
Microsoft Intune has released its November edition, featuring new updates to help IT admins better manage their organization’s mobile devices. Read more
