MagenticLite is an experimental agent that works across the browser and local file system

A shared language for designing and communicating AI experiences.

Split-pane canvas UI for OpenClaw agents — dashboards, kanban boards, charts, spreadsheets, and more, rendered by AI on the fly

AI Interactive — The interaction layer where intent flows freely between humans and AI. An open exploration of human-AI interaction patterns.

GestureBind is a cross-platform desktop app that maps hand gestures (via webcam) to system actions like hotkeys, app launches, or shell commands. Built with Python, OpenCV, MediaPipe (YOLOv8 planned), and PyQt5, it features YAML configs, profile management, system tray support, and on-screen feedback — all processed locally for privacy.

AI Thinking Animation Generator

The 12-Skill AI UX Design Engine for Claude Code & GitHub Copilot — purpose-built skills for designing UX for AI products, AI agents, and AI-powered experiences

Noir-inspired legal-tech AI SaaS mockup for document analysis, timeline building, issue spotting, evidence review, and export summaries.

An open-source Chrome extension that adds a "Trust & Quality Score" to Idealista listings. Built in a 12-hour sprint as a public case study on AI-augmented product development.

State-of-the-art email productivity interface built with Next.js 16 & Ant Design 5. Features dynamic Kanban triage, real-time updates, and Gemini-integrated email intelligence.

A behavioural operating system for human–technology interaction. Services → Solutions → Neural Matrix.

Production-tested UX patterns for AI products: streaming, RAG citations, token-cost transparency, quota fallback, evals, empty states — with real screens

A structured, repeatable system for designing and prototyping AI-enabled product experiences.

Sentinel — embeddable inline AI oversight. Wraps the host AI's output in place so the human expert can validate, correct, and audit without leaving their workflow.

Conversational portfolio chat interface built with HTML, CSS, JS, and JSON

A working UX systems prototype for agentic AI travel experiences, modeling explicit states, autonomy boundaries, confidence signals, and recovery patterns.

Design vocabulary for AI surfaces that are honest about uncertainty. Calibrated confidence, evidence anchors, the cross-hatch primitive — shared across the agentic-UX trilogy.

Real-time oversight of LLM agents — watch the agent execute, approve or edit every tool call, abort if it goes sideways. Third piece of the trilogy with Sentinel + Recourse.

Consumer-side AI for fighting institutional loops — insurance denials, surprise bills, parity violations. Document-first, statute-anchored, never lets the clock slip.

AI workflow state modelling, guardrails, and human-in-the-loop design patterns for SaaS platforms.