Hey Google, Here We Go!

Merve Başak
Hey Google!
Published in
5 min readOct 22, 2018

--

Hello everyone,

In this article, I will give general information about Google Assistant and Action on Google, which is a little more involved in our lives every day and I find quite amusing. You can visit official websites for more details. 😊

In order to better understand the subject, let’s proceed by explaining some terms. So let’s answer these questions before Action on Google (AoG) and Google Assistant. 😊

Actions on Google is a developer platform that let’s us create software to extend the functionality of the Google Assistant. As a developer, we can use Actions on Google to easily create and manage delightful and effective conversational experiences between users and our own 3rd-party fulfillment service.

Google Assistant is a smart personal assistant first announced in May 2016 in Google I / O. Google’s virtual personal assistant, across more than 500 million devices, including smart speakers, phones, cars, TVs, headphones, watches, and more.

I’m going to leave the following explanations to replace some more basic stones. 😊

  • Intent: A goal or task that users want to do, such as ordering coffee or finding a piece of music. In Actions on Google, this is represented as a unique identifier and the corresponding user utterances that can trigger the intent.
  • Action: An interaction you build for the Assistant that supports a specific intent and has a corresponding fulfillment that processes the intent.
  • Fulfillment: A service, app, feed, conversation, or other logic that handles an intent and carries out the corresponding Action.

Devices

Smart Displays

Smart Displays : Devices with screens make it easy for users to quickly scan lists or make selections, in common use cases like shopping or product browsing. Enhance your Action to provide rich visual responses that make these tasks easier.

Smart Speakers

Smart Speakers : These devices use only voice and audio for their user experience that make hands-free interactions and multi-tasking easy for users. Consider using SSML and the sound library to enrich your Action’s audio experience.

Smartphones

Smartphones : Phones are multimodal, combining voice and visual interactions like Smart Displays, but with the added benefit of mobility. Enhance our Action with rich visuals, and consider on-the-go use cases for these devices.

Setup and Developing

Let’s start by explaining the two terms below. 😊

  • Actions Project : A project we create to manage, test, and publish a collection of Actions; Google maintains our Actions project in a cloud backend.
  • Actions Console : A web-based tool that Google provides to simplify your Actions development; we can create, maintain, test, and publish our Actions using the console.

Here’s how we can do the installation for a simple project. First, we need to create an ‘actions project’ to be able to perform our actions.

  1. Open the Actions Console.
  2. Click on Add/import project.
  3. Let’s name the project. This name is for our own internal reference; later on, we can set an external name for our project.

4. Click Create Project.

5. Rather than pick a category, click Skip on the upper-right corner.

6. Click Build > Actions in the left nav.

7. On the Create Action dialog, select Custom Intent and click Build. This will open the Dialogflow Console’ in another tab.

Now let’s take a look at how our actions work with Dialogflow. 🙂

I also share the keywords because I think it will make it a little clearer here :

  • Dialogflow : A web-based service provided by Google that uses an agent to process user input. This service allows you to integrate conversational apps with the Assistant, as well as with other conversation platforms.
  • NLU : Acronym for “Natural Language Understanding”. This refers to the capability of software to understand and parse user input. Developers can choose to use Dialogflow or their own NLU solutions when creating Actions.

Create a Dialogflow agent :

  1. We need to be in the dialogflow console with Action project name. With our Google account, we can log in by accepting the terms of service.
  2. Click Create.
If the agent creation is successful, you will be in the Intents page.

I tried to give information about a project installation with Dialogflow.

In addition, in some cases we use the Action SDK. In such cases, the SDK offers two fundamental components. These are Action Package and Node.js web service. Action packages are JSONs where information such as how to trigger actions and which fulfillment will be called. The Node.js client library helps us to process the data from the user and to produce the required output. You can find more detailed information about these articles in the next articles.

Community Program

Stack overflow : You can ask your questions under the title ‘action-on-google’.

Actions on Google Developers G+ Community : You can share information about this platform and learn the latest news.

Twitter : Join conversations, stay tuned!

Github : You can browse the codes of the projects.

Thanks for reading !

Also, I have GitHub repository for my Google Assistant series. I will share codes, links, and posts there. 👇

--

--