Test Your Interaction Model

As you build your custom skill, you can test and improve your voice interaction model before your write any skill code.

  • Find utterance conflicts that might cause Alexa to send the wrong intent to your skill.
  • Use the utterance profiler to test individual utterances. You can enter utterances to see how they resolve to intents and slots.
  • Use the Natural Language Understanding (NLU) evaluation tool to create and run a set of tests against your model. With this tool, you create a set of utterances mapped to the intent and slots you expect to be sent to your skill. Then you run an evaluation to test how your NLU model performs. Use the NLU evaluation tool for regression testing as you iterate on your interaction model.

These tools don't call your endpoint. You can use them any time after you build your interaction model.