HeyJaredEidos Design | UX AI Community
A community of UX designers exploring AI, new ideas, embracing challenges, and uncovering what it takes to create a better, more thoughtful digital world.
- Indexed issues, last 90 days
- 11
- Latest publication
- Sep 30, 2026
- Audience
- Checking…
- Earliest in this view
- Jul 18, 2026
Latest issues
Eidos Design. Vol. XXXIX: Why your "Umms" beat perfect prompts (and the app built on that) (opens the original)
Read excerpt
Hello fellow designers, creatives, digital professionals and Eidos Design members!A year ago my prompts looked like legal contracts: numbered rules, role definitions, output formats, and a “do not” list longer than the task itself. Some weeks I’d run one AI tool just to polish the prompt I was about to feed another one. A prompt for the prompt. It felt like engineering.Lately that ritual works worse. The thing that works best on my desk right now is a voice note. Unedited, full of “umm,” “so, li
AI in UX Studio #17: OpenAI Is Killing Custom GPTs. Here's How to Save Yours Before December 11 (opens the original)
Read excerpt
Hey AI expert designers, Siavash here! Welcome back to AI in UX Studio. Read more
Building Logs #1: I Wanted A Chess Clock. I Ended Up Shipping One. (opens the original)
Read excerpt
A new section starts today.Building Logs is the record of the things we at Eidos Design build. Every product we ship gets one: the idea, the design, the code, the store, the hours, the money, and the parts where we got it wrong. and are writing these while the details are still warm, before the story sands itself down into something tidier than it was.We’re starting simple. Case one is a Just Chess Clock designed, built and shipped to the AppSto
The sycophancy trap: what happens when feelings become the metric (opens the original)
Read excerpt
For the past year I worked on an app that pays people to play mobile games.The business model is quite straightforward: game developers want players to stay longer and spend money on in-app purchases. Our app sat in the middle and paid users to play. Developers got loyal players, we got paid, and players earned a few dollars for something they were doing anyway. You can’t earn a lot of money, but it still makes playing feel different. Now, you’re not just “having fun” or “killing time,” you can
Claude Fable 5.1 vs GPT-6 Astra for Product Design: Which One Is Actually Better? (opens the original)
Read excerpt
Two frontier models landed within days of each other, both priced identically at $10 per million input tokens and $50 per million output, both carrying 1M-token context windows, and both claiming the crown. Anthropic shipped Claude Fable 5.1 (alongside its restricted-access twin, Mythos 5.1). OpenAI shipped GPT-6 Astra, announcing it, without much modesty, as “the most intelligent and aligned model in the world.”Every comparison written since has been about coding benchmarks, agent loops and tok
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
No verified audience measurement yet.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.