Echo Dot (3rd Gen) - Smart speaker with Alexa - Charcoal

Use your voice to play a song, artist, or genre through Amazon Music, Apple Music, Spotify, Pandora, and others. With compatible Echo devices in different rooms, you can fill your whole home with music.

Buy Now

Wireless Rechargeable Battery Powered WiFi Camera.

Wireless Rechargeable Battery Powered WiFi Camera is home security camera system lets you listen in and talk back through the built in speaker and microphone that work directly through your iPhone or Android Mic.

Buy Now

Why businesses are not adopting chatbots as expected?

0
340


Arun Bhat

Chatbots can be built for various business processes. But most of the businesses use it just for lead generation. And the reason for this is because lead generation bots are easiest to implement.

Bot building limitations: Most platforms provide flow based bots, which has its own limitations. A lead generation bot will have few flows, But what about a customer service bot where it has to answer based on user queries? It is not possible to set up a predefined flow there. Most of the lead generation bots are setup to gather information of user such as email, phone, name etc, and later you broadcast them offers and discounts, which is a kind of replacement of email marketing.

Here is a video of a more complex bot deployed in HR process

Driving conversations: In a flow based bot we create a flow which a user has to follow. This can be achieved by setting up quick responses and not enabling option for user to ask queries. This is a huge setback because there can be n number of flows. You may have created a flow e.g for pricing related queries. But what if a user wants to know more about your product other than an endless list of products?

A customer facing bot should ask the right questions and display results based on the responses. When was the last time you went to the store to buy something… and the sales guy dumps all the products in their inventory and allows you to choose from it?

A good salesperson asks right questions to understand your preferences

  • What colour shoe are you looking for?
  • Do you know the size of shoe that fits you?
  • Are you looking for formal or casual shoes?

Based on the responses, we will have to extract certain words from the sentences and filter out the results displayed to the user. Most Chatbot developers don’t consider this because of the limitations in the platform they are using.

Best bots are the 1’s which can drive the conversation with a user rather than forcing a user to follow a pre defined flow.

Consider another scenario where you want to book appointments using a chatbot. So you setup a date and time field and add validations so that user enters in the defined format. how is this different from a form on your website?

What if user types sentences like

“Book an appointment tomorrow for 4pm”, “Do you have an appointment for next Tuesday?”. The user would expect the bot to understand such sentences, because that is what Chatbots are all about right?

Here is a video demonstrating how date, time, email etc.. are being extracted from user queries.

This can be extended to extract custom entities and connect with your CRM through API’s.

Cost: To build bots shown in the above videos will cost you $$$. Since you need to hire a developer/agency to build NLP chatbots that can connect with Dialogflow or Watson and also build an interface for you and maintain the bot. Hence most companies stay away from it. With Rakebots you can build such bots with less time and money.

Integrations: Since most of the platforms available now are focused on lead generation. They are heavily dependent on Facebook. But what if you want to build a bot that does not require a facebook page? What if you want just a widget to be on your site for internal purpose? I have come across various clients who had built a chatbot on Facebook because they had no other options, even though they don’t use most features like broadcasting.

Recently I came across a client who was searching to build a chatbot that can integrate with his loyalty program and cart notifications from past 1year!

Language Support: When was the last time you found a platform using which you could build a chatbot in your native language?

Businesses do not want to invest much on a tech which they are not sure if it works or not. A bot which can solve some problem of business process can save a lot of time and money and help the business owners to focus on the core of their business. If you are stuck with some of the above mentioned points or want to know more about NLP Chatbots, then do reach out to us at Rakebots, and we can help you out.



Read More

LEAVE A REPLY

Please enter your comment!
Please enter your name here