Live data from Hacker News

The Kik Bot Platform

avc.com

51–54 of 54 posts

Re: The Kik Bot Platform

#51

Earlier quoted context omitted.

to have a bot be available to other bots is the same as having an API and letting a general purpose bot connect to the API. The only advantage a BOT would then have over the API would be NLP and some personalization data and device sensor data. No matter how I look at it general purpose bots prevail but they require connecting to all those APIs like you mention. Personally I don't think BOTs in chat is the future of…

what do you think the future of chat is? I am not an engineer, so I don't know enough about integrating with APIs, but I would think a bot could use natural language to talk to another bot without integrating or even know about the other bot prior to the user needing it. Essentially, the user is talking to one bot that is finding and passing along the message to the other bot and vice versa. Bot A > finds bot b > add…

Bot A finds bot B via (marketplace search, keyword search, published functionality search or manual settings?) This is very difficult to do accurately especially when there are 100 other bots that provide same functionality as Bot B.

Let's assume user selected Bot B to be added as friend for Bot A.

Bot A asks Bot B for a list of commands > This is essentially making an API call or Bot A sending a chat message to Bot B "Please send me all your public commands" (which is a simplified NLP API call)

However Bot B might not want to expose all its NLP command keywords (that is after all their Intellectual property) or it is too complex to send all commands because of myriad of ways an NLP query can be structured.

I like your idea of a conversational API. Maybe there is a better way to do that and definitely something worth thinking about.

Regarding the future of chat, the problem is these chat apps are trying to become task help apps. What is the purpose of chat/group chat? Communication, discussion, planning, sharing between "friends/contacts" (not between me and a bot) Communication with a friend or contact does not require a bot. Discussion with a friend, group of friends or contacts does not require a bot Sharing content with a friend, group of friends or contacts does not require a bot.

The only thing that requires a bot is planning an outing, trip, dinner, etc. with a friend or group of friends or contacts. For that I think it is better to have a general purpose bot. Here's how I envision that use case with a bot called JEEVES.

ME: Hey have you guys watched Zootopia yet?

FRIEND 1: Nah I want to but didn't have the time. I'm free tonight if you want to go.

FRIEND 2: Yeah count me in too

ME: JEEVES find us a movie theater close to us that's playing Zootopia tonight.

JEEVES: There are 3 theaters close to all of you that's playing Zootopia tonight. Theater 1 at (map)Location 1 is playing it at 9PM, Theater 2 at (map)Location 2 is playing it at 8:30PM, Theater 3 at (map)Location 3 is playing it at 10:PM

ME: you guys wanna get dinner before the movie?

FRIEND 1: Sure

FRIEND 2: Nah having dinner with GF's parents today.

ME: JEEVES find us some chinese restaurants near Theater 3.

so on and so on.

JEEVES can then book tickets, make a reservation, put the event on calendars, send restaurant location to just the 2 people who agreed to have dinner, etc.

Re: The Kik Bot Platform

#52

Earlier quoted context omitted.

i pimp everything, so i guess that means everything is a dud. i am an equal opportunity pimper. i plan on pimping again tomorrow on AVC

I read your blog a lot. Thanks for writing it. But some of the conclusions you're trying to draw in this post feel forced. The "websites -> apps -> bots" deal especially jumps out to me as odd.

The "websites -> apps -> bots" deal was actually lifted from a recent Ben Evans (a16z) presentation.

http://www.slideshare.net/a16z/mobile-is-eating-the-world-20...

Re: The Kik Bot Platform

#53
post #7

Can anyone explain how a chat-based interface can possibly be generally successful except briefly as a novelty? Surely an UI with controls specific to the task at hand is much better than having the user guess what the bot responds to and what it can do? In the restaurant use case, for instance, a QR code + text URL that points to a website where you can advertise the restaurant with whatever graphics and UI you want…

Ultimately as with so many trends the underlying thing here seems to be "Go where the users are". Users are using lots of chats and chat apps, so now we all need bots to meet them there.

That's why this fascination with bots and conversational UIs seems particularly cyclical, as various chat rooms/chat apps come and go in popularity. Just the other day, I was pointing a colleague to The Jack Principles, a book/presentation/best practices compendium whose lineage traces back to the 90s (and I think now is a great time for Jellyvision to sell us all a new edition in bookstores).

The reason this is particularly exciting this time coming back around in the zeitgeist is that we have better tools than ever (NLP has come a long way, machine learning and deep learning are doing exciting things, the "platform" level concierge/assistants of Cortana, Siri, Alexa). Maybe this time it might be more than a passing novelty.

Re: The Kik Bot Platform

#54
post #7

Can anyone explain how a chat-based interface can possibly be generally successful except briefly as a novelty? Surely an UI with controls specific to the task at hand is much better than having the user guess what the bot responds to and what it can do? In the restaurant use case, for instance, a QR code + text URL that points to a website where you can advertise the restaurant with whatever graphics and UI you want…

> Surely an UI with controls specific to the task at hand is much better than having the user guess what the bot responds to and what it can do? A well-designed and well-implemented UI is better, yes. But I think where this could be useful is for the many customers who don't have the cash to make a decent app. A stripped down chat interaction could end up more usable than what they'd build from scratch.

The value is in making a legitimate platform for the lowly CLI app then. I like it :)
Post reply on HN