Passing the app state to the dialog script (React Native)

To provide relevant responses to users, the voice agent must know what is happening in the app: what screen is currently open, what options are enabled and so on.

To get information about the app state, you can use Alan AI’s visual state functionality. The visual state allows you to send an arbitrary JSON object informing about the current app context to the dialog script. You can access this data in the script through the visual object.

In this tutorial, we will continue working with the simple counter example and provide users with a possibility to ask about the counter state with voice.

What you will learn

  • How to get the information about the app visual context

  • How to access the data passed with the visual state in the dialog script

  • How to filter intents depending on the app state

What you will need

To go through this tutorial, make sure the following prerequisites are met:

Step 1. Send the app state to the dialog script

To send the information about the app state to the script, we first need to call Alan AI’s setVisualState() client API method on the client app side.

  1. To access the Alan AI’s client API, in the App.js file, update the following line to add AlanManager:

    App.js
    const { AlanManager, AlanEventEmitter } = NativeModules;
    
  2. Add the useEffect() hook to call the setVisualState() method and send count to the dialog script:

    App.js
    const App = () => {
      useEffect(() => {
        AlanManager.setVisualState({count});
      })
    }
    

Step 2. Add a voice command to ask about the counter state

We want the voice agent to give the correct answer when the user asks about the counter state. In the code editor in Alan AI Studio, add the following command:

Dialog script
intent('What is the current count?', p => {
    let count = p.visual.count;
    if (count > 0) {
        p.play(`You clicked the button ${count} times`);
    } else {
        p.play('Please click the button at least once');
    }
});

Here we are using the p.visual.count variable to access the data passed with the visual state. Depending on the counter state, the AI agent will play back different responses.

Step 3. Filter voice commands by the app state

It may be necessary to add voice commands that will work in specific circumstances. In Alan AI, you can create such commands with the help of filters added to intents. The filter in an intent defines the conditions in which the intent can be matched.

Let’s add a voice command that will work only if the counter value is greater than 0:

Dialog script
const vCounter = visual(state => state.count > 0);

intent(vCounter, 'How do I reset the counter?', p => {
    p.play('Please restart the app');
});

The filter comes as the first parameter in the intent. Now this intent will be matched only if the counter value is greater than 0.

You can test it: run the app, tap the Alan AI button and ask: How do I reset the counter? The AI agent will not reply since the filter condition is not met. Then increment the counter and ask the same question again.

What’s next?

Have a look at the next tutorial: Triggering activities without voice commands.