Behind Bot-in-a-Box by Google: It’s No-Code Conversational AI Tool

Google’s ‘Bot-in-a-box’ tool brings developers and non-developers on the same page, opening the scope for new and faster innovations in conversational AI.

Conversational AI is developing fast, and the pandemic only gave a boost to the technology – especially enterprise conversational AI, as people needed answers and the staff at companies was not present. The customers embraced the technology with open arms. Conversational AI is a huge market at USD 6.8 billion in 2021 and is expected to reach USD 18.4 billion by 2026 (CAGR of 21.8%)

Conversational AI is in high demand as it provides AI-powered customer support services and can be deployed across multiple channels. Also, the reduced costs of chatbot development have increased the use of this technology that combines speech-based technology, NLP, and ML, into a single platform.

While it is a no-brainer for larger companies to integrate AI in their customer chat services, SMBs are still lagging in leveraging AI. Last week, in its Business Messages solutions, Google launched what it calls a ‘Bot-in-a-Box’ tool that lets companies integrate conversational AI without any coding.

Bot in a box

Google utilized its existing AI tool – Google Cloud Contact Center AI’s Dialogflow to create Bot-in-a-Box within Business Messages. It supports ‘Custom Intents’ that allows the chatbot to understand multiple ways in which similar questions are asked and respond accurately using ML capabilities. This new tool in Google’s Business Messages allows organizations to deploy it on their own business channels and even on Google Search and Google Maps. The new no-code solution uses the existing customer FAQ document and Dialogflow’s technology to create chatbots that can understand and respond to customer questions. The beta users of Bot-in-a-Box were Walmart, Levi’s, Tango Technology, and Albertsons.

How it works

Bot-in-a-Box can be enabled in Google’s Dialogflow and currently supports only the Dialogflow Essentials (ES) version. It can be integrated with Dialogflow Customer Experience (CX) by calling the CX APIs directly from a configured Business Messages webhook and programming the conversion to and from the Business Messages APIs.

In the integrations section of the console, the person has to click ‘Enable integration’ and is prompted to create a new Dialogflow project or connect to an existing project. Then, the system will prompt each step to set up the authentication between the Dialogflow project and Business Messages agent. The person has to then add an FAQ document which can be a URL or CSV file, to initialize Bot-in-a-Box. Dialogflow then processes the document using ML and recognizes questions similar to what exists in the FAQ. And, done – a sophisticated digital agent within a few minutes without writing any code.

Future lies in low-code & no-code development

The no-code feature is one of the most interesting and forward-looking ones that Google has launched in this chatbot making. According to Gartner, the worldwide low-code development technologies market is at a total of USD 13.8 billion in 2021. Of course, low-code application development has always been there, but now, increased digital disruptions, more composable business and hyper-automation have led to the rise of no-code tools. Gartner has also predicted that by the end of 2025, 50% of all new low-code clients will be non-IT organization buyers. All of the major SAAS vendors provide capabilities to incorporate low-code development technologies. With it growing every day, the low-code market will see high growth in LCAPs and process automation tooling.

Google’s Dialogflow v/s Amazon Lex v/s Microsoft’s Azure Bot Service v/s IBM Watson Assistant

Dialogflow with a web interface helps build basic Q&A bots in a few hours, and with Bot-in-a-box, this time has been reduced to minutes. It allows both developers and non-developers to create bots. Google’s Dialogflow also allows integration within many platforms like Google Assistant, Slack, websites, Skype, Facebook Messenger, Twitter, and in 20 languages.

Amazon Lex is powered by the deep learning technologies that are used in its Alexa. It is used for building conversational interfaces using voice and/or text. Lex integration support is limited to Facebook, Slack, Kik and Twilio SMS and only supports US English.

Microsoft’s Azure Bot Service has a fairly easy-to-understand web interface used to create intelligent bots. Bot Service with Bot Framework is used to build chatbots using open source tools, SDKs, and services – this enables developers to make bots easily. There is also a visual interface that non-developers can use. Bot Service can be integrated into Cortana, Skype, Facebook Messenger, Kik, Telegram, and Twilio and supports over 15 languages.

IBM Watson Assistant does not just provide support for an answer from the knowledge base but can also hand over further questions to a human. The offering for building conversational interfaces can be integrated into any application, channel or device. There are ready to use samples and even video tutorials to get started.  The assistant first requires creating a skill and then integrating it with other channels like Facebook Messenger, Voice Agent (Telephony), Slack, WordPress plug-in, and even custom applications using APIs. Watson does support over 10+ languages where some of them are still in beta stages.

Wrapping up

With increasing no-code & low-code chatbot development, professionals from multiple backgrounds like marketers, customer support agents, sales representatives, and health professionals will be able to build chatbots. Ideas coming from a varied skill set of people than the usual developers will result in increased innovation and push conversational AI technology forward. While using any platform to develop Conversational AI, it is essential to understand the important use cases and ensure that the basic foundational architecture can support the bot’s current and future use cases.

More Great AIM Stories

Meeta Ramnani
Meeta’s interest lies in finding out real practical applications of technology. At AIM, she writes stories that question the new inventions and the need to develop them. She believes that technology has and will continue to change the world very fast and that it is no more ‘cool’ to be ‘old-school’. If people don’t update themselves with the technology, they will surely be left behind.

More Stories

OUR UPCOMING EVENTS

8th April | In-person Conference | Hotel Radisson Blue, Bangalore

Organized by Analytics India Magazine

View Event >>

30th Apr | Virtual conference

Organized by Analytics India Magazine

View Event >>

MORE FROM AIM
Yugesh Verma
A beginner’s guide to Spatio-Temporal graph neural networks

Spatio-temporal graphs are made of static structures and time-varying features, and such information in a graph requires a neural network that can deal with time-varying features of the graph. Neural networks which are developed to deal with time-varying features of the graph can be considered as Spatio-temporal graph neural networks. 

Yugesh Verma
How is Boolean algebra used in Machine learning?

Machine learning model with Boolean algebra starts with the data with a target variable and input or learner variables and using the set of rules it generates output value by considering a given configuration of input samples.

3 Ways to Join our Community

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Telegram Channel

Discover special offers, top stories, upcoming events, and more.

Subscribe to our newsletter

Get the latest updates from AIM