Josh’s tutorial shows you how to enable a robot with speech recognition and tone analysis then explains how to create a simple conversation using Watson Conversation. Finally, you’ll learn how to get TJBot to speak. Once all the services are put together, your bot is complete. You can give your bot a name, too.
Companies worldwide are investing in chatbots to create great digital experiences for their customers. Now, with a chatbot powered by Watson Services, digital experiences can go beyond ordinary transactions and become fun interactions between brands and customers. For instance, Elemental Path used Watson to enable Dino, a chubby toy dinosaur, to converse with its owner. As the child grows, Dino’s character becomes more personalized. In the medical field, 1Doc3 used Watson to build a bot that interacts with patients to route their questions to the right specialists.
Want to build your own chatbot that cares? Check out Josh’s tutorial here.
Imagine, you are in a conversation with a chatbot and you feel that the human angle is completely missing because the bot starts it's dialog with a usual "Hi" or "Hello". You may want to personify the conversation by adding the name of the person (who's logged in) to the boring "Hi" or "Hello". Ever thought of this? It's not just personification, How about wishing appropriately based on the time of the day someone invokes your chat application? Also, how about passing values back and forth during a conversation between the nodes or from application to a node?
Creating and maintaining chatbots in multiple languages can be costly, error-prone, and not easily scalable. Each change in a bot needs to be manually replicated across each language the bot supports. The manual nature of maintaining multilingual chatbots can have a real impact on continuous delivery as the language-specific changes must be performed by language experts and this takes time. Moreover, we need to pay for every single change – intents, entities, and bot output. This can get expensive very quickly — so, what's the best way to translate chatbots into different languages without impeding continuous delivery and disrupting DevOps?