I think Luka has done a great job of exploring a lot of different approaches to this space. We've bet pretty heavily on the idea that most people will want one bot, not a family of them. But it's exciting to see so many people working to make this happen!
If Google works for you, stick with it! Ozlo is for those questions where using Google would make you do all the work - like finding the best place for a burger in SOMA or automatically remembering restaurants you wanted to try.
Hi - we developed our suggestions UI quite some time ago. I think variations are becoming more popular because it's a way of solving the "invisible UI" problem for conversational systems.
Note that with Ozlo, however, our suggestions are just shortcuts. You can also text Ozlo anything you like by tapping on his avatar in the bottom left corner.
Many people who build these are actually just doing menu systems.
Hey! I'm one of the co-founders of Ozlo. Excited to finally to get to share him with you today. If you want early access, sign up here and we'll let you in:
What's the timeline for an android release? The examples all focus on food. Probably a good call for a focus (everyone eats), but is that the primary focus? ie is it a current limitation? Also agree with rohanpai, an api would interesting.
Android is on our list, but for not for a few months yet. Eventually Ozlo will be in a lot of different channels - including messengers, the web, and Android.
Ozlo can work over any topic area we let him learn about. We focused on food for the reason you said, but expect to open him up to many new topics soon!
Oh, whoops. I signed up but didn't realize it was only for iOS. That's unfortunate, I was interested in checking it out. I should have read more before clicking the link, that's on me.
So, I'm curious about this. Does a waitlist with a referral system help increase signups? I'm wondering how's it better than wait lists that don't push you up the line for referring people. Is it worth dedicating resources to build it out?
Referrals don't change your position in line. We are letting people in generally first come, first-served.
We use the VIP code because there are some times when you need to let someone in immediately (important partner, people that might be able to help us test a specific feature, etc.)
I think that in general incentivizing people to share by giving them a bump in line feels unfair.
Hi - I am the creator SproutCore. Thought it might help to provide some context around this.
It's not that you can't make a fast UI with a template-oriented system. The problem HTML makes it very easy for you to do a lot of things - some are very fast, others are very slow. There is no clear line which is which since it has more to do with how you use the DOM than anything else. To make matters worse, the fast paths are different on different browsers.
What this means is that if you want to build really fast UI in the browser using a DOM-centric, template-based system, you are basically taking on all the responsibility to do everything in a fast way yourself. (Which means you also need to know all the little tricks to doing this - many of which are not obvious.) The framework won't be able to really help you.
This is why a JS-based API that takes ownership over the DOM instead of exposing most of it directly to you can be much faster. We can take this crazy world and turn it right side up again with a cogent API that makes it easy to do fast things and harder to do slow things.
Thanks very much for taking the time to reply. I was unclear on the fact that it was the DOM configuration itself that was causing the performance issues.
