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
Related posts
Exploring the listening state for an AI voice interface.
Which direction would you ship, A or B?
23 votes
Ends in 12h
The particle field looks more polished and beautiful🔥
This year’s YC Fall batch is for us creatives. 🎯
As a product designer, I’ve never felt like our field was changing as rapidly as it is right now. Tools emerge, you adapt, they disappear. Processes that took hours can now be largely automated, and overall, I feel like a big part of the fun gets lost because of a communication issue: I struggle to tell the tools exactly what I want in enough detail.
I recently stumbled across a few interesting and promising startups that might bring some of that joy back and take the pain out of parts of our work.
Proto is building an IDE specifically for product designers, bringing design and AI workflows closer together. 👩🏻💻
Simulithic uses AI agents to test your app across devices, browsers, and account types, automating test creation and maintenance. 🤳🏼
Composal uses swarms of AI agents to explore product flows and edge cases, finding what breaks before release. 🕵🏻♂️
Native helps marketers decide what to create by ranking ideas based on brand context, performance, trends, and creative feedback. 🦖
The edge case testing sounds promising.
Missed calls = lost bookings. So I built an AI receptionist that answers the phone, books appointments, and saves every call with a transcript and summary for your staff.
This is a real working system, not a mockup. In the video: an actual test call, then the staff dashboard and transcript. (Demo uses a fictional dental clinic.)
Try it live: https://receptionist.hamzaabubakar.dev/
I build these for clinics, salons and other appointment-based businesses. If you're losing customers to missed calls, message me here on Contra.
