Umbraco Commerce Technical Team Lead @ Umbraco HQ | Co-founder of CODECABIN | Creator of UMB.FYI
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.
Matt Brailsford discusses the significance of Umbraco's 17.4.0 release, which introduces JSON Schema support to the Management API. This enhancement allows AI to understand data structures accurately, transforming content creation and editing by eliminating guesswork. The update promises to improve integrations and facilitate intelligent content workflows across Umbraco.
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.
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.
Matt Brailsford discusses transitioning from a custom Claude Code skill for managing git worktrees to utilizing Claude Code's native worktree support. He highlights the benefits of using hooks for customization, allowing for gitflow branch naming and essential file copying, while simplifying code maintenance and enhancing session management.
Matt Brailsford introduces Umbraco AI, a provider-agnostic AI integration layer for Umbraco CMS, allowing seamless connections to multiple AI services through a unified API. It features a flexible architecture with customizable profiles, contexts, and capabilities, promoting community-driven extensions and open-source collaboration. Future enhancements include automation and improved RAG support.
Matt Brailsford discusses how AI coding assistants have transformed his workflow, particularly through the use of git worktrees for parallel development. He addresses the "Port Discovery Problem" when multiple demo sites need to run simultaneously, proposing a solution using named pipes for local communication, enhancing reliability and simplifying tooling.
Matt Brailsford discusses his upcoming talk on Spec-Driven Development (SDD) and explores the collaborative potential of AI in software development through his SPECKL Manifesto. SPECKL emphasizes structured specifications to guide AI assistance, balancing control and automation. Matt invites feedback and experimentation with this approach as a transitional tool in AI-assisted development.
Matt Brailsford reflects on the two-year journey of UMB.FYI, which has evolved from a weekly digest into a comprehensive record of the Umbraco community's developments. Matt celebrates the milestone with the release of the UMB.FYI Pulse Check, a year-in-data snapshot of the Umbraco community’s heartbeat.
Building on Phil Whittaker and Matt Wise’s MCP integration at Codegarden, which supercharged Umbraco’s AI capabilities, Matt Brailsford unveils an Umbraco Commerce proof-of-concept: a conversational store-management assistant delivering actionable insights and analytics—and inviting the community’s feedback to shape what comes next.