Well, I successfully tried out my first conversational action in our Google Home Device using API.AI

API.AI lets you build and deploy Conversation Actions directly within an easy-to-use, web GUI. I started with the “Hello World” type of simple action from this Getting Started article. Once I understood how it work I was able to create my own conversational action that speaks out my kids name after asking couple of questions and the kids are so excited to hear their name.

An important learning during this testing – Make sure that when you are testing via the web simulator, you fully test both your intents and your invocation, using voice commands by clicking the “mic” icon in the command entry text box. I was confused when my voice commands didn’t work in Google Home device and understood that my voice invocation was not resolving correctly when testing in the simulator with voice command. Once I found this, I tested the invocation in web simulator and adjusted it a bit to make sure it is resolved correctly. The web simulator is pretty helpful with this because of the JSON response that can be seen in the same screen.

Next step is to try the Action SDK, of course that will be more powerful and the one that I will like to my taste as a developer 🙂

Leave a Reply

Your email address will not be published. Required fields are marked *