Speakers

ANKIT ZAVERI

ANKIT ZAVERI

Solution Architect,

Softweb Solutions

DHAVAL SAHIJA

DHAVAL SAHIJA

Manager - Enterprise Solutions,

Softweb Solutions

About Webinar

2016 has become the year of bots. People are abandoning their mobile apps and switching over to using bots for business, shopping, work, entertainment and news. The average American today downloads very few new apps every month. This means that unless the app you are developing is going to be the next Uber or Tinder there is a small chance of you being able to achieve a million downloads quickly.

Bots can be deployed for several purposes such as customer service, shopping assistants, virtual assistants and even medical advice. In this webinar we will talk about how enterprises can build bots and how they can use them to not just reach out to more customers but also increase the productivity of their organizations.

Webinar agenda

  • Introduction to bots
  • Messaging apps are the new platform
  • Why enterprises need bots
  • Chatbots are the future of conversational commerce
  • Industry specific use cases
  • Bot Frameworks and Natural language processing (NLP)
  • Demo
  • Q&A

Questions & Answers

The following are the answers to the questions that were asked during the live webinar.

Question 1: Does a bot remember a question or a conversation and learn more about you from them?

Answer 1: The AI-based bot can remember the conversation and can learn more about you from dialogue. The same can be achieved by integrating the bot with Machine Learning.

Question 2: Why is the app boom dead? Isn't it just changing so that apps sit on top of bots and are called skills instead?

Answer 2: The app boom is not over. It is actually the evolution of IT. And if we go back in history and understand evolution of IT; mainframes were used from late 1950s till early 70s , and then going forward in the 80s people were using desktop applications such as IBM OS2, Delphi, etc, and if we talk about early 90s, people starting using web applications after launch of the WorldWideWeb.

Mobility started gaining traction in 2007, which changed the way how businesses works. Now in 2016 we see there is a major transformation and people are spending more and more time chatting on messengers for collaboration with friends, employees and relatives. So basically messaging applications are the new platforms for bot and they work on top of web applications.

Question 3: In the pizza ordering bot demo and the banking bot demo, how do we know that it was the bot giving answers and not a human?

Answer 3: We would be more than happy to email you with the link of the bots. You can add these bots as contact in your messenger and have a hands on experience with chatbots. Feel free to drop an email at info@softwebsolutions.com.

Question 4: In what kind of use-cases/scenarios does it make sense to not use a bot?

Answer 4: As of now the bot may not be the best option in which the user experience is the primary objective of the application or in case the application has very exhaustive features and a large database. Most of the bot frameworks and platforms are recently launched and as the technology evolves, we are hopefull that all these limitations will be overcome.

Question 5: What is your experience in this field?

Answer 5: Softweb's experience with bots includes pizza ordering bot for consumers, order tracking bot for B2B, workplace productivity bot, customer care bot for eCommerce, to name a few.

Question 6: Are the ruled-based bots able to answer questions based on how good the rule is and how extensive the database is?

Answer 6: We can have a rule-based bot that understands the value that we supply. However, the limitation is that it won’t understand the intent and context of the user’s conversation with it.

For example: If you are booking a flight to Paris, you might say “Book a flight to Paris” and someone else might say that “I need a flight to Paris” while someone from another part of the world may use his native language to have the same context.AI-based or NLP-based bot identifies the language, context and intent and then it reacts based on that. A rule based bot only understands a pre-defined set of options.

Question 7: How do I build a HoloLens application for my business?

Answer 7: If you are planning to develop a HoloLens application for your business, then you should go for a HoloLens pilot project. This is because when you are building a HoloLens app for a specific business requirement, a pilot project on HoloLens will give you a clear idea about expectations, deliverables and estimated time for development.

Question 8: What kind of a bot was shown to us in the demo? Was it a rule-based bot or NLP-based bot?

Answer 8: The demo of bots that we have showcased were a hybrid of rule-based and AI-based bot with LUIS Integration.

Question 9: Do you use NLP in bots?

Answer 9: Yes, the bot demo of the pizza ordering bot and banking bot that you saw have been implemented using LUIS.

LUIS is Language Understanding Intelligent Service offered by Microsoft and can be integrated with the majority of databases or backend applications.

Question 10: In my experience, NLP is not yet this advanced and cannot recognize all typed or spoken language. Especially the Dutch language is difficult in this case. Would there be a possibility to combine rule-based and NLP techniques?

Answer 10: Yes, we can combine rule-based bot and NLP techniques to achieve an optimum end-result. The overall technology of NLP and bot is evolving. We can combine bots, ML algorithms and LUIS to achieve the best results. NLP is very wide area and we can have a dedicated webinar on that; however you can drop us AN email to schedule a call for further discussion.

Question 11: Where and how to use NLP?

Answer 11: NLP is natural language processing and can be used in scenarios where static or predefined answers, options and questions may not work. In fact, if you want to understand the intent and context of the user, then it is advisable to use NLP.

For example: If we talk about pizza ordering bot in which you can give pre-considered options of pizza topping using rule-based bot then that’s possible, but if in case you want to understand the intent of the user where one person is saying “I am hungry” and another person is saying “I am starving”, so it would make more sense to use NLP, so that the bot can understand what the user is trying to convey.

Question 12: What is the difference between a framework and a platform? Can these terms be used interchangeably?

Answer 12: The difference between a framework and platform is that–

A framework consists different components to develop a bot using SDKs and connector services and other frameworkS. E.g.Microsoft or Java etc.

A platform is something where the application is built, such as iOS and Android where we create our applications and install on these platforms.

The best thing about the bot service is that it is platform independent, all you need is a chat messenger. You can start using the bot by adding it as a contact.

Question 13: How popular is LUIS and what are the other NLP platforms?

Answer 13: LUIS is in preview mode but you can visit the Microsoft website for more details on it. Microsoft is also evolving the NLP platform and over time the technology will mature.

Question 14: How much does it cost to develop a food delivery bot for a restaurant or a bot for FB Messenger?

Answer 14: We need to understand the use cases that you wish to implement with the bot and based on that we will be able to provide an estimated cost.

Question 15: Are bots required to sit on messaging apps?

Answer 15: Yes, chatbots work on top of instant messengers such as Slack, Skype, Telegram, Facebook Mesenger, WeChat and Kik. Whereas for voice-based bots, we need to use services of Siri, Alexa, etc.

Question 16: Can one bot be built for all platforms?  Are there cross-platform bots?

Answer 16: Yes, our consultants can build a bot that can be deployed across multiple channels and messengers.

Question 17: How can I go about building a chatbot that improves customer engagement and increases productivity?

Answer 17: If you are planning to develop a chatbot for your business needs, then select our chatbot development package. We have a team of chatbot developers who can build AI-powered or rule-based chatbots to seamlessly reach your customers as well as automate several tasks.