José Antonio Márquez Russo

The design-to-code handoff is one of the most expensive gaps in enterprise software development. Weeks of engineering time spent interpreting Figma files, reconciling spacing math, and rebuilding what designers already specified. On March 30, join Aditya Karra, Blitzy's Founding Designer, and Ben Bergerson, Senior AI Solutions Consultant, for a walk thru of Blitzy native Figma-to-production capability. No prototypes. No Refine PR. Production-ready code. - Every design token read before a single line of code is written - Responsive output across five viewports from one desktop frame - A new feature integrated into an existing codebase, brand-aligned, checked directly into the repo Designers and product teams can now move at the speed of design. Come see what that looks like in practice. Register with the link in the comments. March 30 | 12pm ET | Free with live Q&A #Blitzy #Webinar #Figma #Platform40 #FrontendDevelopment #EnterpriseAI #ProductVelocity

29

1 Comment

Thrilled to share my latest article: "The Mixed-Initiative Interface: Designing Control Handoffs Between Humans and AI." In a world where AI handles more decisions, the real UX frontier is the seamless transfer of control—ensuring humans can step in without losing context, state, or accountability. We're moving beyond rigid autonomy to dynamic systems where handoffs are graceful and empowering. Key insights include: - The Handoff Problem: Mixed-initiative systems allow bidirectional control shifts; the challenge is preserving state during transitions to avoid confusion. - Decision Ledger: An append-only log of actions, confidence scores, and reasoning to brief humans on AI's prior steps. - Non-Destructive Overrides: Use proposal queues for AI suggestions that can be reviewed or modified without halting workflows. - Calibrating Confidence: Dynamic thresholds based on consequence, reversibility, and confidence—err toward escalation to build trust. - Reversibility and Intervention Windows: Leverage event sourcing for undos and strategic delays to enable human oversight in high-stakes scenarios. This is essential for anyone building AI-powered products: think pricing optimization, fraud detection, or any domain blending human judgment with machine efficiency. Does this align with challenges you're facing in your work? Read the full piece here: https://lnkd.in/dX_y7YMa

5

"AI and the Future of Filmmaking" panel plus screenings, and a room full of builders. Organizer Tony Shyu mentions tools are evolving fast and poses the question: where will this be in six months? We dug into formats clients pay for, “content as marketing,” and the creator economy’s real business model: diversified revenue beyond views. I enjoyed the #AI #film shorts, but what I most treasure was meeting Fred Grinstein and getting invited to the Machine Cinema community for long-lasting connections. I also connected with Charlie Sung from ByteDance and Siyuan (Leanna) Ren from MiniMax, with whom I'm very excited to explore collaboration opportunities.

7

1 Comment

There's a lot of nuance behind the spatial interaction & interface system we designed for SnapOS over the past 3 years. We wrote about the frameworks we created to abstract away the complexity. https://lnkd.in/gs5znJGb

72

1 Comment

This week’s lesson, don’t solely rely on a coding agent for a complex multi phase UX refactor. All the right plans, docs and guardrails will not stop it quietly defecating over your codebase.

7

1 Comment

I’m incredibly proud of the work our team is doing to modernize the inner dev loop at The New York Times. Our engineers are deeply committed to quality, but when you work at the speed of news, efficiency is everything. We are now scaling unit test coverage by integrating AI agent flows directly into our developer workflows—always with strict human supervision. This shift has significantly improved our efficiency in writing tests and allowed us to quickly expand coverage across our most critical codebases. As the team shared in Open NYT, we are putting this philosophy into practice to increase velocity without ever sacrificing quality. Beyond speed, we are doubling down on our commitment to inclusive design. At our core, we believe that "accessibility is a requirement, not a feature." It is now a non-negotiable standard in how we think, test, and build across every surface. It’s inspiring to see this culture of "quality + inclusivity" take root! Read more about our journey here:  🔗 Scaling Unit Tests with AI: https://lnkd.in/eSCf2zje  🔗 Accessibility as a Requirement: https://lnkd.in/e8bcvzgr Special shout out to: Eric Chima 👤 Leonardo Quixada Erica Vendetti Rachel M.L. Dixon David Leininger Matt Argomaniz #SoftwareEngineering #AI #Accessibility #DeveloperExperience #UnitTesting #NYTTech

76

4 Comments

📣 Some good AI news for designers: agentic AI is just UX in disguise! You know when someone says something simple and suddenly the hard thing makes sense? Just had one of those 💡 lightbulb moments in a workshop with Chris Johnson about command line tools for process optimization with agentic AI. I've been watching a lot of videos about building AI workflows lately. About 30 seconds in, the presenter usually dives off into n8n or some other visual coding environment where they have 10000 boxes joined up with spaghetti string. If you just set all of this up, magic will happen! (Anyone who has used a prototyping tool has been there: no judgment!) CJ skipped past the complicated tools, and stuck with the concepts. Turns out that "agents" are just a very thorough and structured JTBD-like persona in a file that the AI uses as context for its work. Let's break it down a bit: ( 💻 AI-speak) -----------------------> (👩‍💻 UX-speak) As long as you have a tool capable of agentic AI (e.g. Claude), you create: * a "knowledge base/context" ------> "folder" of files, including * "skills" ------------------------------> "user expertise & knowledge" * "agents" ----------------------------> "persona" * "processes" -------------------------> "tasks, workflows & journey maps" ...to get things done. Who knew? UX-ers have been AI-ers all along! 🙌 I might just be the last person on the planet to "get" it (wouldn't be the first time...), but I figured maybe others have been as mystified as me. I'm pretty excited about the possibilities that this opens up: using a new technology to play a bigger UX game on our own home turf. Especially when you throw a little OOUX into the mix...😎 More from CJ here: https://lnkd.in/eunxQAXa https://lnkd.in/eFQds6KT https://lnkd.in/emvdvm5Q

2

2 Comments

I am excited to share with you the first post of our Engineering Blog! In this issue we cover some of the key engineering decisions we made that have enabled our lean team to build a multi-cloud, regional platform that is used by enterprises today. We will be sharing deeper dives into many of the topics mentioned in this post. If the problems and the tech we are building at Thread AI excite you, we'd love to hear from you!

48

2 Comments

Optimization needs to be considered across the board, including aspects such as onboarding. Read how Russ Harding and EQengineered have created measurable gains (50%+) for the onboarding process.

3

AI tools like Cursor and Claude Code can now "read" Figma via MCP. On paper, that sounds like the end of the painful design-to-code handoff. In practice? It's complicated. When it works, it's genuinely impressive. Figma's MCP paired with Code Connect can produce results that feel like magic. When it doesn't work — and that happens often — the AI picks up DS components but gets the props wrong. Or misses them entirely. Or generates something that looks right at a glance but breaks edge cases. The deeper issue is that AI works best with well-known component libraries it's already been trained on: ShadCN, MUI, AntDesign. Ask it to understand a custom, company-specific design system with hundreds of components and nuanced variant logic? That's expensive in context, tricky to teach, and inconsistent in execution. So is AI handoff realistic? Getting there — but not yet. The flow is improving fast, and when the tooling catches up, it will genuinely change things. Just don't cancel your visual QA sprint yet. 🔗 Read more: https://lnkd.in/dyb6QbqB

8

2 Comments

Ethan Mollick finally covering Claude Code is significant. He's one of the most influential voices in practical AI adoption, and this will introduce it to hundreds of thousands who've never touched a CLI.  His examples - the $1000/month business, the civilisation game - demonstrate real capability. But what he describes is the starting point, not the ceiling.  What's emerging in the community is Claude Code as Persistent Infrastructure: orchestration systems that maintain context across sessions, skill libraries that accumulate domain expertise, agent networks handling entire business workflows autonomously.  Ethan's right that the interface is intimidating for non-technical users. But the DOS terminal didn't scare away a generation - people learned it because the capability was worth the curve. Claude Code is the same: it rewards System Thinkers regardless of coding background. The skill is process design, not syntax.  If his article gets you experimenting: don't stop at one-shot tasks. The power emerges when you think about continuity.

2

EMOTIONAL SUPPORT GOOSE: Chef 🧑‍🍳 Trish Winter-Hunt visited the Cozy AI Kitchen to demo her Emotional Support Goose 🪿 https://lnkd.in/gk4t6R8d in a brand new episode of CAIK 🎂. 🧑‍🍳 Trish shares her creative and strategic approach to content design, AI agents, and how emotional support geese (yes, really!) can inspire better UX. This 📺 episode: https://lnkd.in/gk4t6R8d All 50 🎂 episodes: https://lnkd.in/g6upvbGX

104

9 Comments