We're building an AI tutor that doesn't give instant answers. Is that a bad UX decision?
While building Matheum, an AI math tutor, we kept coming back to one question:
Should AI always give users what they ask for, even when it might work against their long-term goals?
Most AI tools are designed to remove friction. You ask a question, and you get an answer immediately.
But learning works a little differently.
Sometimes struggling with a problem is exactly what helps you understand it.
That's why we're taking a different approach with Matheum. Instead of immediately revealing the solution, it guides students with hints and step-by-step explanations.
But there's an obvious trade-off.
Students might learn more by working through problems themselves. Or they might get frustrated and switch to a tool that gives them the answer in seconds.
We haven't resolved that tension yet, and it's something we're thinking about as we build.
I'd love to hear from other makers, especially those working on AI or educational products:
How do you balance giving users what they want immediately with helping them achieve better long-term outcomes?
Would you prioritize a faster experience, or deliberately introduce friction if you believed it could improve the result?
For context, here's what we're building: https://matheum.ai

p/htmldrag
p/runevr
p/producthunt
p/google-cloud-platform
p/kodlo
p/ai-context-flow
p/jot-2-0
p/beamfy
p/dex-by-exmergo
p/refs
p/reso
p/duckfightclub
p/seshka
p/talanoa-2
p/nudgeforme
p/dino-kids
p/nexupira
p/many-displays
p/murror
p/operum
Replies
Be the first to reply
Have a question or a thought to share? Add a comment above to start the conversation.