Steve Sanderson, the creator of Blazor, recently spoke at the NDC London 2025 conference, highlighting the future of .NET application development. His keynote introduced smaller AI models and autonomous agents as key elements for application developers. He emphasized the potential of “agentic AI,” which allows systems to handle multiple tasks independently, making it ideal for complex applications. Sanderson also demonstrated a new Blazor voice assistant that can understand user intent and interact seamlessly within .NET. Furthermore, he discussed the benefits of using smaller language models for AI-powered apps, which can enhance performance and privacy. Overall, Sanderson’s insights showcase an exciting direction for developers in integrating AI into their projects.
Steve Sanderson Previews AI App Dev: Small Models, Agents and a Blazor Voice Assistant
Blazor creator Steve Sanderson recently shared exciting insights at the NDC London 2025 conference. His keynote focused on the future of .NET application development, highlighting the use of smaller AI models and autonomous agents, along with a demonstration of a new Blazor voice assistant project.
In a YouTube video titled “The past, present, and future of AI for application developers“, Sanderson, who works on ASP.NET at Microsoft, discussed how the future revolves around agentic systems. These systems are meant to perform multiple autonomous tasks instead of relying on single answers.
Agentic AI represents a significant shift for developers. Sanderson explained, “The idea is to provide the AI the ability to handle a series of tasks independently.” This approach is particularly beneficial for creating tools, DevOps automation, or complex enterprise applications. One example he provided was a software upgrade agent that could research new framework versions and suggest changes autonomously.
Additionally, Sanderson emphasized the significance of small-model choices. Developers don’t always need hefty models like GPT-4 for their projects. For many .NET applications, smaller language models can be equally effective. These lighter models can run on local servers or even in-browser, enhancing performance, lowering costs, and ensuring data privacy. He showcased a zero-shot classification example using a lightweight model in a browser to illustrate their practicality.
One highlight of his keynote was a Blazor voice assistant demo, built using Blazor Server and OpenAI’s API. This intelligent assistant understood user intent, interacted with UI data models, and could carry out backend functions seamlessly. It also demonstrated how to apply tone adjustments and formatting based on voice cues, showcasing the next generation of user experiences that developers can create.
In summary, Sanderson’s keynote revealed the evolving landscape of AI in application development, focusing on autonomy, scalability, and user interaction. Developers are encouraged to explore the potential of small language models and agentic systems to innovate and streamline their applications effectively.
For a deeper dive, be sure to check out Sanderson’s full keynote on YouTube, where he covers topics including historical AI developments, live model training, and structured data extraction using Microsoft technologies.
Tags: AI Development, Blazor, .NET, Small Language Models, Voice Assistant
What are Small Models and Agents?
Small models and agents are simplified versions of AI programs. They perform specific tasks like answering questions or recommending products. They are designed to be lightweight, making them easy to use and efficient.
How do Small Models improve the Blazor Voice Assistant?
Small models make the Blazor Voice Assistant faster and more responsive. They help the assistant understand voice commands better, allowing it to listen and respond quickly. This leads to a smoother user experience.
Can I create my own voice commands for the Blazor Voice Assistant?
Yes, you can create your own voice commands! The Blazor Voice Assistant allows you to customize commands based on your needs. You can set up commands to control applications or retrieve information, making it tailored to your preferences.
What are the benefits of using a Blazor Voice Assistant in applications?
Using a Blazor Voice Assistant makes applications more interactive and user-friendly. It allows users to interact through voice, which is convenient, especially for hands-free tasks. This can enhance accessibility and improve overall engagement.
Are there any limitations to using Small Models and Voice Assistants?
Yes, there are some limitations. Small models may not handle complex tasks as well as larger models. Additionally, voice assistants depend on clear speech input. Background noise or unclear commands can cause misunderstandings or errors in responses.