pelumi

Great points @redmaverick. Your ideal interaction described above is what I called a 'meta-chatbot' i.e. a chatbot that interfaces with other bots and interacts on your behalf with them.

This bot receives input from you, based on its knowlwedge of available bots, routes your requests to them and pipes the response back to you.

The problem with the current bot arms race is that we end up shifting the app fragmentation issue from the device home screen to the messaging app screen.

We bot enthusiasts love to claim that one of the advantages of using bots is that the user is already within the messaging app. But when you have lots of bots for different 'small' tasks then there is still a huge fragmentation as you switch context from the taxi bot to the pizza bot.

I shared some thoughts on the 'meta-bot' here: https://medium.com/@pelumi/chatbots-igniting-division-of-lab... it will be great to know your thoughts

Yeah, we should indeed take this offline. I can't see your email, you can reach me on lumzor [at] gmail [dot] com.

Your description is what I had in mind. The user won't be the one to add the bots, the meta-bot has a strong knowledge of the 'chatbot community' and knows who is good at solving problems in different categories.

The proposition of allowing the user 'add' bots is also quite interesting but I've not given much thoughts to that.

I totally agree with you, not all tasks are best suited for bots. As your point suggests, we need an insane level of Natural Language Understanding handle and correctly execute tasks with many deegres of freedom.

Thanks for the thoughtful questions. Here are my thoughts on your questions

1. The incentive for a developer is to get better exposure. This is working with the assumption that the metabot has a larger userbase than individual chatbots. In general, the incentive is similar to what causes an online store to setup a 'store' on amazon's market place or retail sites to list on a price comparison engine.

2. As regards the second point, my thoughts when writing the was that it will infact be a direct pass through i.e. the metabot will not need to bother about the structure or nature of the requests/response but will instead focus on knowing about the bots and their capabilities. If it does this effectively, it theoretically pipes all requests for a specific task to the same bot to complete. This comes with it's own complexities as well.

3. To rank bots in the same doamin, an option is to guage the satisfaction of multiple users of the bots. For instance if a bot is faster to complete a flight reservation and the 'user' confirms to the metabot that it is satisfied with the service, that's a positive signal. This can be compared across multiple bots to measure the effectiveness of each bot.

4. Indeed, I agree it will be challenging. But I think the challenge is less of structuring the queries. If the meta-bot acts primarily as a pipe, its most important task is to identify who handles what and know the state of the conversation.

There are a lot of kinks to be worked out though...

this is interesting and hardcore!

lool... i feel your pain :(

hey, thanks for the feedback. Voyando looks cool, great job! At http://travel.ai.instapage.com/ our aim is to delegate the search process to machines so that humans can spend their time on other tasks that machines cannot handle effectively.

Our service can be useful for Voyando as well. Let me know if you're interested in discussing this further. You can reach me on lumzor [at] gmail dot com.

Thanks

very true, google is doing a lot of work in that space. However, the additional advantage we have is that we manage group bookings for businesses which means no repeated filling of forms by the support staffs. The current model often involves a lot of back and forth between travellers and the travel agencies or company travel department. Our service will significantly reduce this since the preferences of each traveller is known.

thanks for the feedback

Thanks for your comment, yes you can save time by getting humans to conduct the search for you. However, we believe assigning the search and filtering process to humans is inefficient especially as regards time spent. Abstracting that process will provide time for other more important tasks that cannot be done by machines.

Thanks for the feedback, from talking to frequent travellers, we realised they often have preferences like preferred airlines, airports, flight time and such information.

Our aim is to learn this information based on their travel history which forms the personal travel profile. The travel profile also consists of biodata information.

This helps PAs/EAs save time on time spent incorporating user preferences when searching on traditional flight comparison engines. The difference is that it reduces the clutter on generic platforms and presents you with what you will be most interested in.