AI Interfaces of the Future (YC video w/ Rafael from Notion Calendar)
I really enjoyed this breakdown by @raphaelschaad and @aaron_epstein (YC partner):
https://www.youtube.com/watch?v=DBhSfROq3wU&ab_channel=YCombinator
They walk through some cutting edge AI apps:
@Vapi - voice api for devs
@Retell AI - build voice agents
@Gumloop - AI zapier
@AnswerGrid - outbound research
@Polymet - AI product designer
Zuni - ai in your chrome sidebar
and @Argil - video clone generation
They talk about some recurring themes:
- When prompts take a long time, give the user something engaging to do while they're waiting.
- Canvas is a powerful UX paradigm for understanding workflows. I appreciated Rafael's insight that zooming in / out can allow for understanding a complex workflow at multiple levels of fidelity.
- Voice interfaces - latency and interruptibility are the main factors in a good user experience.
- Discoverability / templates. The problem with LLM prompts is they're so open - I don't know what I can do with them. Have some easy templates at your users' fingertips as a starting point.
One big area I found missing is the subtleties of code assistants - In particular, I feel like the cutting edge of LLM interfaces is being explored by the likes of @Cursor , @Windsurf - and other code assistants that are being used in high-stakes production code.
The other reason code assistants are interesting to me is that it appears these products are winning based on the interface, not the underlying models (since those are fungible).
If you use Windsurf, Cursor, I'd love to hear what about the UX design feels new / superior.
Replies
Finding the right UX for AI beyond basic chat interfaces is such an interesting topic. Especially when it comes to AI agents that act autonomously in the background, you need to find ways to bring human subject matter experts in the loop. At gotoHuman we went for an inbox-based approach where we list pending items that need approval or feedback. But it's an interesting challenge to find a good balance in a UI that's easy to use, but provides fine-grained controls for editing, feedback and instructions, and also allows to drill down into what the AI agent was doing.
The future of AI-powered interfaces is exciting! One thing we’re seeing: business automation tools that simplify UI/UX tend to have higher adoption. How do you think AI interfaces will impact the way teams automate workflows in the next 5 years?
Totally.
When I switched from @Cursor to @Windsurf , my jaw dropped.
I was using the exact same models, but the UX was an order of magnitude better. During my first experience with it, my editor searched our codebase for similar code, found a re-usable component, and plugged it in. Windsurf doesn't get it right all the time (not even close) but it's pretty clear that the agentic approach is going somewhere.
And then, when a new model comes out, they appear in my editor in days. There can be hiccups of course (like @Claude by Anthropic 3.7 burning through Windsurf credits). But the models themselves are becoming a commodity.
Product Hunt
@andrew_g_stewart what stood out in terms of UX? Are there specific interactions that really impressed you?
Recall
Sharing a summary here in case you couldnt squeeze in the 36minute watch.