An advanced chabot that was build to order food online. The Natural Language Understanding was trained on Chinese cuisine first (most popular cuisine in online food portals) and achieved 86% accuracy against tests sourced from MTurk. The app...
Blog
This is a bot that asks a simple array of questions that lets the bot fire an API request on RightMove to fetch results and display. A little NLP and spelling mistake detection was used for better detection of location names, developing a tolerance for spelling mistakes or slang.
Smarter.Codes is in its 3rd generation now and things are looking exciting now. Here is a pilot run we did where we were provided with some less than 100 documents shared among customer support department of a company (essentially their knowledgebase compiled over years of operation). The Problem: This company has 4,000 clients, actively calling […]
This is an Email bot that we are designing for a client that lets you automate lead qualification for the sales team. Powered by Natural Language Understanding, the system makes sense of incoming emails (not based on keywords) and asks them followup questions and warms them up to make them ready for an actual human […]
RECENT POSTS
Facebook Hotel Booking Chatbot
A natural sounding advanced chatbot that uses well developed understanding of Natural Language and can understand multiple parameters in a single sentence, no matter how it was said. Follows all 3 type of conversations on can have with a bot as a human. Hotelsify...
Designing a Chatbot: Making a Chatbot sound stupid (how to test a chatbot)
Is your chatbot designed for those curveballs that some notorious users may throw at it? Humans are... well... humans and you can't impose an HR policy on the them saying: "Abusing chatbots is a punishable offence. You might hurt its self confidence". There are...
