UX/UI product designer. I share #webdesign, #webdev knowledge and #AI adventures. DM's are open.
Houston, TX
Joined May 2010
- Tweets16.9K
- Following752
- Followers949
- Likes11.5K
A spinner says the software is busy. It doesn't explain that a person needs to approve the work. Design the waiting state around the real dependency.
ALT Two navy hands pass an orange relay baton across a gap between platforms, illustrating work that depends on a handoff.
Not every risky action needs another warning dialog. Some need undo. Others need confirmation or a recovery path. I'd separate those decisions before designing the interruption.
ALT An orange ball on a looping navy track against a cream background, suggesting a route back after moving forward.
Translation: At last we got the Adobe Flash we were hoping/craving for.
👍🎯💯
Rive is now a full engine. Most think of Rive as an animation tool, because that’s where the format started, but the goal was always to build a new type of experience engine. Lightweight enough to run in another engine or runtime (like Spotify Wrapped) yet powerful enough to run an entire game.
It’s lightweight, accelerates vector graphics like no other engine or runtime, supports shaders for 3D and effects, and it runs anywhere. It opens up all kinds of experiences not just for the web, but also for native mobile, consoles, underpowered smart TVs, vehicles, and anything else with a gpu.
Royalty free, no rev share, no runtime fee, MIT open-source. No other engine gives you all that with a tiny runtime that can run anywhere.
The UX bible.
Still holds up!
On October 13, 2000, Steve Krug, a UX designer and information architect, published Don’t Make Me Think. The book deals with web usability and the interdisciplinary field of HCI.
ALT On October 13, 2000, Steve Krug, a UX designer and information architect, published Don’t Make Me Think. The book deals with web usability and the interdisciplinary field of HCI.
Luis -Let´s 2026 ⚡️- Suarez retweeted
On October 13, 2000, Steve Krug, a UX designer and information architect, published Don’t Make Me Think. The book deals with web usability and the interdisciplinary field of HCI.
ALT On October 13, 2000, Steve Krug, a UX designer and information architect, published Don’t Make Me Think. The book deals with web usability and the interdisciplinary field of HCI.
Less clutter helps. Losing context doesn't. A simpler screen can still make the task harder if people must search elsewhere.
ALT A person steadies a large blue TASK folder holding cards labeled DECISION, CURRENT FILE and NEXT ACTION, marked with a check, document and arrow. Orange paperclips keep the cards together.
A cleaner screen isn't always a clearer workflow. What does someone need to know, do next, and keep in view?
ALT Three illustrated cards connect left to right: KNOW with an eye and note, ACT with a hand pressing a button, and KEEP CONTEXT with clipped papers. A person studies them.
Great food for thought and topic to discuss.
There’s still time with current AI state of the union.
As engineering, product, design, DS, etc. melt into a new kind of role, I was reflecting on what roles might look like in the future. For example, when I look at the Claude Code team I see what I think is five archetypes:
1. Prototyper: comes up with brand new ideas; churns out many ideas, most of which don't ship
2. Builder: quickly turns a prototype/idea into production-grade product/infra
3. Sweeper: cleans up the UI, simplifies the code and system, unships, optimizes performance
4. Grower: takes a product that has been built and iterates on it to improve Product-Market Fit
5. Maintainer: owns a mature system to make it secure, reliable, fast, and efficient as it scales
Many people span across 2 roles, and sometimes 3 roles. I also notice that these roles are not really tied to job function -- eg. across Anthropic, some designers match category 1, some 2, some 3; same for engineers, PM, DS.
A healthy team needs a mix of these, depending on the product:
- A product that is new and pre-PMF needs people that are strong at 1+2+3
- A product that is growing and has found PMF needs 2+3+4 and some 5
- A product that has strong PMF needs 3+4+5 and some 2
Maybe product roles of the future will look more like this, and less like the domain-specific roles of today?
Just read this headline:
“A Third of Recruiters Say AI Is Replacing Entry-Level Jobs”
World changed 3 years ago because of AI and most people are not paying attention.
Future is now.
Learn how to think, not how to make things.
Great approach 👍
You don't need the $100 Claude plan.
Instead, you just need these 9 (free) fixes:
1. Shrink Your Files.
Open a Google Doc. Paste the text from your PDF.
Download as .md file format & upload that instead.
A 15-page PDF = 45,000 tokens.
The same text as the .md file = 2,000 tokens.
2. Plan First. Build Last.
Open Claude Chat. Prompt: "Help me plan a [financial model]. Ask me questions first."
Then paste the final plan into Cowork and prompt, "Build exactly this."
You just saved 1/10th of the cost.
3. Let Claude Ask You.
Stop writing long prompts. Prompt this instead: "I want to [TASK] to [SUCCESS CRITERIA]. Ask me questions using AskUserQuestion before you start."
Then just select answers. Clicking costs almost zero tokens. Your 500-word prompt costs 500.
Full guide here: ruben.substack.com/p/how-to-…
But here's what's really draining your credits:
4. Edit Your Messages, Don't Resend.
Click "Edit" on your last message to Claude.
Fix the mistake there. Hit Save. Claude regenerates without stacking a new message on top.
Every "no wait, I meant..." doubles your cost.
5. Summarize Every 15 Messages.
After having an entire chat with Claude. Prompt: "Summarize this entire conversation into a brief."
Copy it & paste it as the 1st message in a new chat.
You just compressed 105,000 tokens into 500.
6. Switch Models Before You Start.
Click the model dropdown. If the task takes Claude under 30 seconds to answer, pick Haiku or Sonnet. Only pick Opus for deep, multi-step work. This saves you 3–5x per message.
7. Use Projects, Not Uploads.
Go to Projects. Create one. Upload files there once.
Every new chat inside that Project reads it without re-tokenizing. Stop uploading the same contract to 5 separate chats.
8. Turn Off Extra Features.
Go to the tools panel. Turn off Web Search.
Turn off connectors. Turn off Extended Thinking.
Only turn on what this specific task needs.
Idle features burn credits silently.
9. Batch 3 Tasks Into 1 Message.
Instead of sending "Summarize this" then "List the key points" then "Write a headline" - send all three in one message.
Three messages = three full context reloads.
One message = one reload.
Access the free guides to copy my full system:
✦ 23-fixes breakdown: ruben.substack.com/p/how-to-…
✦ The infographic cheat sheet: how-to-ai.guide
Send it to the one who keeps hitting Claude's limits.
Please and thank you!! ❤️
Announcing Paper Desktop + MCP
Now any agent can read or write with Paper
Paper is connected. To your code. To your agents. To your data. To your teammates.
Download Paper Desktop at paper.design
