Hear from CIOs, CTOs, and other C-level and senior execs on data and AI strategies at the Future of Work Summit this January 12, 2022. Learn more

Google’s business platform services just became a lot more conversational.

Google Cloud has announced yesterday a new AI-powered product product, Bot-in-a-Box. This is a Google Cloud Platform Business Messages feature that assists enterprises in starting conversations with customers. GCP Business Messages allows organizations to communicate with customers and answer their questions through Google Search, YouTube or Google Maps.

Bot in a Box uses natural language understanding and Google’s Dialogflow software. This allows chatbots to understand customer questions and respond without the need for code. Bot-in-a Box uses machine learning to understand a customer’s request. It also features Custom Intents that find the customer’s information without any human intervention.

DialogflowCX is a virtual agent which handles simultaneous conversations between users of a company. This module was designed to comprehend the subtleties of human language. Dialogflow converts audio and text from a conversation to structured data that can be understood by apps and services. Users of Bot-in-a Box can create and customize a Dialogflow agent for the type of conversations they need. Google says that Dialogflow agents can be trained to handle common conversation scenarios. Training does not have to be too detailed.

[ Related: How Zowie Diagnostics aims to refresh customer service chatbots with AI ]

Custom Interests is a Google product which allows marketers to target specific topics, products and solutions to people who are currently searching the internet using YouTube video or display ads.

A Bot-in-a Box can also display an existing customer FAQ from a web site. This will make the customer service easy and simple.

Beta customers of Bot-in-Box include Walmart, Tango Technology and Levi’s. Since February’s launch on all platforms, Bot-in-Box has been used by many beta users, including Walmart, Tango Technology, Levi’s, and Albertsons. They report that AI-powered Business Messages have helped employees save time through the automation of customer conversation.

Technology What’s new with this bot

Jay Akkad, product manager at Google Group, stated that

Bots-in-a Box is the first-party integration between Dialogflow ES (Google’s Business Messages) and Dialogflow ES. This integration will reduce the time and effort required to create an automated experience in Business Messages. Akkad stated that this integration makes it easy for businesses to respond to a part of customer support inquiries.

[ Related: Equipping AI with emotional intelligence can improve outcomes ]

Bot-in-a-Box is ideal for companies who have line-of-business employees that create bots. A series of UI forms allows a non-expert to connect a Dialogflow automated conversational agents to Business Messages using a first-party integration. After the connection has been established, an existing FAQ will be used to initialize the conversational assistant. Dialogflow’s web console can be used to expand the conversational agent to address more complicated questions or user journeys. It is easy to create new intents to match or respond to user questions. This can all be done without the need to write any code.

Dialogflow offers a low-code solution for dynamic responses that are based on backend data. Akkad stated that the intention creation and matching can still all be done through a web-based console.

Technology Helping customers in ‘moment of need’

Businesses can communicate with customers at their most urgent time, using AI-enabled Business messages. This allows them to connect with customers where they are looking, such as Google Search and Google Maps. Akkad also wrote that businesses can use any brand-owned channel.

People turn to Google when searching for answers, buying something or trying to complete a task using one of our many tools. In fact, 68% of all online experiences begin with a search engine,” Akkad said. We know how important it’s for brand interactions to be personal, helpful, and simple .”

Technology How the AI components come together

These data points are from Akkad to help technologists better understand how Google uses AI to enable Bot-in-a-Box. GCP is the place where everything is stored and operated.

VentureBeat: What AI and ML tools are you using specifically?

Jay Akkad: Dialogflow is used to handle intent matching and configuration of responses. Dialogflow’s knowledge connectors feature can be used to upload FAQs and manage them.

VentureBeat: Are you using models and algorithms out of a box — for example, from DataRobot or other sources?

Akkad: We use Dialogflow’s built-in ML and NLP technology as well as their knowledge connectors feature.

VentureBeat: How are you labeling data for the ML and AI workflows?

Akkad: This is handled automatically by Dialogflow.

VentureBeat: Can you give us a ballpark estimate on how much data you are processing?

Akkad: This is dependent on the conversational agent that a business creates.


VentureBeat’s mission to become a digital hub for technical decision-makers is to provide information and tools that enable them to transact with transformative technology.

This site provides essential information about data technologies and strategies that will help you guide your organization. To access:

  • up-to-date information on the subjects of interest to you
  • our newsletters
  • gated thought-leader content and discounted access to our prized events, such as Transform 2021: Learn More
  • networking features, and more

Become a member