Articles · Well Crafted AI

Building thoughtful, user-centered AI experiences.

Well Crafted AI is the publication where I think out loud about agent UX, AI-Ready Design Systems, MCP, trust, and the new shape of human-in-the-loop work. Articles go live on Medium first; this page is the index.

Well Crafted AI — illustrated banner showing a designer and an AI collaborator at adjacent workstations, with framework diagrams in the background

The thread across the work: good UX patterns don't expire when the underlying tech changes — they get a better engine. Most of these articles are short reads (2–4 minutes), built around a single sharp idea, with a hard close and a link back to the project work that inspired it.

Publication Well Crafted AI
Author Jay Bellew
Cadence Roughly monthly · resuming weekly
Latest The New UX Layer

All articles

All articles · most recent first
A three-layer diagram: Layer 01 The human, Layer 02 The new UX layer (model, tools, skills, prompts, MCPs), Layer 03 The systems — with intent/response and action/result arrows running between them.
In progress · 4 MIN

The New UX Layer

What MCPs, agentic tools, and AI-native workflows are quietly building underneath your software — and why the next decade of design lives in the gap between you and the rest of your stack. First in a new series.

A 5-step flow diagram titled 'AI Integration with MCP' showing AI Application Initiation → Connect to MCP Server → Server Communicates with Service → AI Uses Service → Action Taken
3 MIN · on Medium

MCP: The Missing Piece in AI Agents

Model Context Protocol as the USB of AI integrations — a clean, standard way for agents to act on the world.

Read on Medium
A semicircle illustration of five design tips for 2025: Develop AI Skills, Solve Meaningful Problems, Stand Out with Judgment, Collaborate and Be Kind, Stay Grounded in Principles
2 MIN · on Medium

Design Tips for 2025

Five ways to thrive and make an impact as AI reshapes the design landscape — develop AI skills, solve meaningful problems, stand out with judgment and taste, collaborate kindly, stay grounded in first principles.

Read on Medium
Screenshot of an AI image generator with the prompt 'Create an img of a beautifull sunset over the ocean with a litehouse' showing the AI is unfazed by typos
3 MIN · on Medium

A Typo-Forgiving UX Is One of My Favorite Things About AI

Communicating with AI doesn't require perfect spelling, and I love it. A short post on fuzzy matching, intent recognition, and the human-centered design of "I know what you meant."

Read on Medium
A blueprint-style illustration of the five-step AI/UX framework: Define and Understand, Metrics and Success Criteria, Prototype and Test, User Testing and Refinement, Launch and Learn
4 MIN · on Medium

The AI/UX Blueprint

A practical, five-step framework for designing AI products — from defining the "why" to launching, monitoring, and continuously improving. The shape of the work behind every AI experience that earns trust.

Read on Medium
Basketball court background overlaid with three diagrams: Celtics' Strategic Transformation roadmap, Three-Point Shooting Comparison metrics, and a Product Design Strategy seesaw
4 MIN · 12 ★ · on Medium

The Three-Point Playbook

What the Boston Celtics' strategic shift to three-point shooting can teach product teams about high-impact focus. A short case for finding your "three-point shot" and concentrating on it.

Read on Medium
Two side-by-side diagrams: Evolution to Frictionless UX funnel and Balancing User Empowerment and Autonomous Action venn diagram
4 MIN · 17 ★ · on Medium

The UX of Invisible AI

What autonomous agents show us about the future of interaction. The most engaged-with piece in the publication — on designing for cooperation, not just usability, when the best interaction is the one that never happens.

Read on Medium
A research session with humans and robot teammates in a meeting room, alongside two trust diagrams: Build Trust loop and Designing Trust in AI mind map
4 MIN · on Medium

Designing Trust

How do you design AI systems that people actually trust? A short post on clarity over complexity, transparency, fail-safes for human intervention, and humanizing AI decisions.

Read on Medium

Want the next one in your inbox?

Follow Well Crafted AI on Medium. New posts land roughly monthly — back to a weekly cadence soon, with the AI-Ready Design Systems series queued up next.

Follow on Medium