The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Three ways AI products fail that have nothing to do with the model:
I've spent the last year designing conversational interfaces, triage flows, copilots, and agent UIs. The pattern I keep hitting: teams ship a genuinely good model wrapped in an experience that undoes it.
The blank box problem. You give someone an open text field and no idea what to type. "Ask me anything" is the least helpful instruction in software. Users don't want infinite capability; they want to know what this thing is for. The fix is rarely more onboarding copy but rather constraining the first turn.
Errors that read as dead ends. Deterministic software fails loudly and recoverably. AI fails plausibly confidently wrong, or vaguely unhelpful. If your interface treats "I didn't understand" as a terminal, you lose the user at the exact moment they were still willing to try.
Trust spent instead of built. Every confident wrong answer draws down a balance you never explicitly topped up. Products that survive show their work early: where the answer came from, what it's unsure about before they need the credit.
None of these show up in your evals. They show up in churn.
I've just opened a 5-day audit that looks specifically for this class of failure: https://contra.com/s/3ZBRWBck-conversational-ux-audit-for-ai-products-in-5-days?r=PereXDesign
Happy to argue about any of the three
contra.com
Conversational UX Audit for AI Products — in 5 Days by Josue Perez
Read more about Conversational UX Audit for AI Products — in 5 Days by Josue Perez on Contra.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
Problem → Solution: Where UX Thinking Creates Real Value.
Beautiful UI is only the beginning.
Real design starts with understanding what the problem is, why it matters, and how the experience can be improved.
For this CARBEX concept, I explored how a sports e-commerce experience could move beyond a transactional shopping journey into a more focused, discoverable, and story-led digital experience.
→ Better Product Discovery
→ More Intentional Navigation
→ Stronger Brand Storytelling
→ A Consistent Web & Mobile Experience
CARBEX is a self-initiated concept project created for my portfolio However, the UX thinking, design process, and execution were approached the same way I would approach a real-world product project.
Question:
When you review a UX project, what matters more to you — the visual execution or the thinking behind the solution?
Looking to improve a digital product or website?
Let’s talk about the problem first — then design the right solution.
@Arif khan The thinking matters most to me, especially how product discovery shapes intentional navigation. I’d be curious to see where the web and mobile journeys diverge.
AI can compress production time, but it does not remove the work between a convincing interface and a dependable web product. Start with one important user task, inspect the systems supporting it, then confirm the finished pages are accessible, measurable, and understandable to search engines. Which layer do you review least often after an AI-assisted build?
A useful automation does more than connect tools. It also limits authority, preserves the reason behind each action, and gives the operator a practical way back when an output is wrong. Before shipping your next workflow, trace one failure from detection to recovery. Can a person identify the change and safely undo it?
