Matt Brailsford discusses the integration of Microsoft.Extensions.AI (M.E.AI) and the Microsoft Agent Framework (MAF) in developing AI capabilities for Umbraco. The use of IChatClient and middleware patterns enabled efficient feature development and agent orchestration, allowing for scalable, transferable skills while maintaining a cohesive architecture.
Matt Brailsford discusses the implementation of guardrails in Umbraco.AI, which are safety policies that evaluate content before and after AI model interactions. Guardrails consist of evaluators, phases, and actions to manage inappropriate content. They are customizable and essential for maintaining content integrity in AI-driven systems.
In the video, Paul Seal demonstrates how to use Umbraco AI to create and publish a fully structured article in about 20-30 seconds. He showcases the tool's ability to automatically populate content blocks, insert quotes, and add images, highlighting its potential to enhance editorial workflows on Umbraco 17.
Experimental community Browser AI provider for Umbraco AI.
Matt Brailsford introduces Umbraco.AI.Search, a semantic vector search add-on for Umbraco that enhances search capabilities by understanding user intent rather than relying solely on keyword matching. This tool addresses limitations of traditional searches, supports multilingual queries, and integrates with Umbraco.Cms.Search, offering improved content discovery and related content features.
Matt Brailsford discusses the new file upload feature in Umbraco.AI, allowing users to drag and drop documents into Copilot. The system supports various file types, enabling text extraction from Office documents and direct processing of images and PDFs. The extensible architecture allows for additional file formats to be integrated seamlessly.
2026-04-21 from 13:00 to 14:30 (America/New_York) - Online
Matt Brailsford discusses the Umbraco.AI.Prompt package, detailing how content editors can utilize prompt templates for AI-generated tasks like SEO titles and alt text. He explains the syntax, available variables, and the importance of using the image: prefix for image prompts, alongside practical examples and tips for maximizing AI capabilities.
Matt Brailsford discusses the concept of contexts in Umbraco AI, which serve as reusable containers of knowledge that enhance AI output by providing essential background information. Contexts can include various resource types, such as Brand Voice and Text, and can be assigned at multiple levels, improving the relevance and quality of generated content.
Umbraco AI offers a modular, opt-in approach to integrating AI features into its CMS, allowing users to select desired functionalities and providers while maintaining data control. The architecture includes core packages for connections, profiles, and prompts, enabling custom AI feature development. A practical example demonstrates an AI log analyzer, showcasing the system's flexibility and provider-agnostic design.
In this week's Embraco Devril deep dive, Lotty and Sebastian discuss Umbraco.AI with Matt Brazford. They explore its features, including integration with various AI providers, installation guidance, and the functionality of Umbraco.AI.Prompt and Umbraco.AI.Agent. The session emphasizes the open-source nature and extensibility of Umbraco.AI for CMS development.
2026-03-25 from 14:00 to 20:00 (Europe/Copenhagen) - twoday Aarhus, Søren Frichs Vej 44D, 8230 Åbyhøj, Aarhus, DK
Matt Brailsford introduces a streamlined installation script for Umbraco AI, simplifying the setup process by automatically installing necessary packages and seed data. This allows users to quickly create a functional demo site, explore features, and customize AI integrations without extensive configuration, enhancing accessibility for new users.
Owain.Codes discusses his experience with Umbraco.AI, a free, open-source AI integration for Umbraco CMS. He faced challenges during a demo, particularly with API access and permissions. After resolving issues with Google Gemini's free tier, he modified the source code to include the latest model, gemini-3-flash-preview, and submitted a pull request for updates.
At the Winter Keynote 2026, Umbraco HQ reviewed a successful 2025, showcasing growth, product advancements, and community engagement. Key announcements included 24/5 support, a new partner portal, ISO 27001 certification, and the launch of Umbraco Compose for data orchestration, alongside a focus on AI and future roadmap insights.