10k view: voice -> parse (via API.AI) -> fullfillment (via API.AI or Lambda)
voice -> parse (via API.AI) -> fullfillment (via API.AI or Lambda)
Detail view: Voice -> API.AI -> Intents -> Entity (similar to enum) + Action (ex, 'list.tasks') -> Response: in API.AI or webhook (-> Lambda)
Voice -> API.AI -> Intents -> Entity (similar to enum) + Action (ex, 'list.tasks') -> Response: in API.AI or webhook (-> Lambda)
For fullfillment, you can use local machine with ngrok or, you can deploy Lambda directly to staging.
Componenet:
https://github.com/actions-on-google/conversation-components-nodejs/blob/master/api-ai/index.jsarrow-up-right
https://developers.google.com/actions/reference/nodejs/Carouselarrow-up-right
Sample with Lambda:
https://github.com/bradyholt/google-action-tiger/blob/master/lambda-function/index.jsarrow-up-right
the doc is outdates, UI is different now
https://docs.api.ai/docs/concept-eventsarrow-up-right
Get Started page: https://developers.google.com/actions/distributing-your-appsarrow-up-right
https://developers.google.com/actions/components/arrow-up-right
Deployment guide: https://developers.google.com/actions/apiai/deploy-fulfillmentarrow-up-right
Last updated 7 years ago