By John Holt, Principle Product Designer | UX for AI Systems Design Most technology companies can't build AI products. Not because they lack technical talent or tools, but because they systematically destroyed the collaborative capabilities AI development requires. The design-to-code automation tools emerging today - Figma to Builder.io, Cursor with ChatGPT, generative React components - aren't empowering designers. They're exposing a fundamental organizational dysfunction. From…

OpenAI: Here’s a ranking of Supabase and its main alternatives based on factors like ease of use, features, scalability, community support, and flexibility. Keep in mind that the best choice depends on your specific project needs, but this should give you a general idea: https://raibach.net/backend-as-a-ser…al-time-features/1. Supabase Pros: Open-source, PostgreSQL-based, real-time capabilities, built-in authentication, storage, and auto-generated REST and GraphQL APIs. Ease of Use: High — simple setup and…

Product-market fit (PMF) for AI products means aligning a solution closely with distinct market needs, delivering clear value that naturally drives ongoing demand. Achieving this can be seen as an art of craftsmanship—a thoughtful design that conveys quality and earns trust. Humans can be unpredictable with technology; many expect some sort of magic from AI if only they could trust it. Building this trust means…

Most all of my projects follow basic design guidelines from WCAG, which covers a lot of issues for all users. Clear text, correct contrast, etc. is key; the interface should not compete with the task flow or the feedback from the system. You will notice in my portfolio that containers/components are modular/expandable/scalable, they are meant to be grouped, change and guide - not to simply…

Regulations and governance for AI agents are evolving rapidly, focusing on risk-based frameworks and the need for robust oversight. The European Union's AI Act represents a comprehensive regulatory approach, classifying AI systems by risk level—unacceptable, high, limited, or minimal risk—and imposing corresponding requirements, particularly for high-risk systems used in sensitive sectors. This legislation includes specific provisions for general-purpose AI models, mandating obligations related to cybersecurity, red…

Microsoft principles and guidelines for building agentic experiences By Microsoft Design - April 2025 Mark Weiser, the visionary behind ubiquitous computing, once said, “The most profound technologies are those that disappear. They weave themselves into the fabric of everyday life until they are indistinguishable from it.” In other words, good design is invisible, allowing us to accomplish tasks and achieve our goals without technology getting…

Agentic UX refers to a design paradigm that emphasizes the development of AI systems capable of acting autonomously, making decisions, and adapting to user needs. It shifts the focus from traditional, predefined user journeys to more flexible, personalized, and dynamic interactions. This approach allows users to articulate their goals, while AI systems handle the pathways to achieve them, resulting in more intuitive and collaborative experiences. Key…

The future of digital experience is here — but it’s being minced into microscopic use cases. Alex Klein May 6, 2024 TLDR: The thing missing from AI user experience is, well, the experience. It’s been 17 months since the tech gods bestowed generative artificial intelligence on us. Here’s a state of the union for AI UX: A bunch of companies shipped either an AI summary…

“We believe that, in 2025, we may see the first AI agents 'join the workforce' and materially change the output of companies,” said Sam Altman.  Greg Nudelman - March 18, 2025 What are AI Agents? Imagine an ant colony. In a typical ant colony, you have different specialties of ants: workers, soldiers, drones, queens, etc. Every ant in a colony has a different job –…