Table of Contents (🔎 Click to expand/collapse)
Google Assistant is a personal voice assistant that offers a host of actions and integrations. From sending texts and setting reminders, to ordering coffee and playing your favorite songs, the 1 million+ actions available suit a wide range of voice command needs. Google Assistant is offered on Android and iOS, but it can even be integrated with other devices like smartwatches, Google Homes, and Android TVs.
As you will soon find out, Actions is the central platform for developing Google Assistant applications. Actions work with a number of human-computer interaction suites, which simplifies conversational app development. Out of all the platforms, the most popular is Dialogflow, which uses an underlying machine learning (ML) and natural language understanding (NLU) schema to build rich Assistant applications.
Before we start building our quotation generator, let's review the following terms:
- Google Assistant is the virtual assistant that's found on smartphones, homes, and a host of other devices. It's the application that takes in voice commands and completes tasks based on user input.
- Actions on Google is the developer platform that allows you to build applications for Google Assistant. This is going to be the central console for conversational application development.
Let's build the Actions Project.
- Open Actions Console.
- Click New Project and agree the Terms of Service.
- Select Project ID and click IMPORT PROJECT.
Dialogflow is a platform that abstracts the complexities of NLU and ML to build conversational applications. Follow the step to setup Dialogflow:
- Go to Build your Action > Add Action(s).
- Click Get started.
- Select Custom Intent > BUILD.
- Click CREATE in the top right corner in the Dialogflow agent page.
In Dialogflow, there're some terms should be known:
- Action: an interaction built for Google Assistant that performs specific tasks based on user input.
- Intent: the goal of the Action (e.g. generate quotes). An intent takes user input and channels it to trigger an event.
- Agent (Dialogflow): a module that uses NLU and ML to transform user input into actionable data to be used by an Assistant application.