Posted on

Contextual Design With Google Actions

One of the most complex tasks while designing a conversation is to create natural interactions with our users. However, there is one process called a contextual design that helps us to create these natural conversations. With the contextual design, you can design your conversation depending on the current situation of our users. 

For example, if the user is a first-timer using our Google Action, we will tell him/her a different welcome message than if he/she access it for the second time. Another example is the following one: if the user is from one City, we will provide information related to that city accessing geoinformation. Contextual design is one of the keys of Conversational AI.

Posted on

Multimodal Design With Google Actions: Rich Responses Using Cards

Creating conversations is a really hard task. This is an entire design process that can take a lot of time. In terms of voice assistants, this process is even more complex due to the ability to interact with the user using sound and a display. When you mix those 2 interactions, you are creating a multimodal experience.

In this article, we will learn how to create engaging conversations using multimodality in our Google Action thanks to its Rich Responses using Cards.

Posted on

Multimodal Design With Google Actions: Visual Selection Responses Using Collections

Creating conversations is a really hard task. This is an entire design process that can take a lot of time. In terms of voice assistants, this process is even more complex due to the ability to interact with the user using sound and a display. When you mix those 2 interactions, you are creating a multimodal experience.

In this article, we will learn how to create engaging conversations using multimodality in our Google Action thanks to its Visual Selection Responses using Collections.

Posted on

Local Debugging on a Google Action

Google Actions can be developed using Firebase Cloud functions or a REST API endpoint. Firebase Cloud Function function is Googles's implementation of serverless functions available in Firebase. Google recommends using Firebase Cloud Function functions for Google Action development.

This is a very lightweight and powerful approach to developing our Google Action. However, it is complex to work locally with serverless functions like Firebase Cloud Functions.

Posted on

Google Action With Node.js

Google Actions can be developed using Firebase Cloud functions or a REST API endpoint. Firebase Cloud Function function is Googles's implementation of serverless functions available in Firebase. Google recommends using Firebase Cloud Function functions for Google Action development.

In this post, we will implement a Google Action for Google Assistant by using Node.js, yarn, and Firebase Cloud Functions. This Google Action is basically a Hello World example.

Posted on

Google Action Type Importer

This CLI allows you to transform your Alexa Custom Slots into Google Action Types.

Preface

Natural Language Understanding

NLU or Natural Language Understanding is one field of AI that allows us to understand the users' input in the form of voice or text.