Just purchased a Google Home and created an app using API.ai, which works fine in the 'Actions on Google' simulator. I don't plan to publish this app (it's very specific to me - it just calls a webhook on my webserver with a couple of entities taken from the command)...but I'd ideally like to use commands (intents) without having to confirm each time that I want to use my app.
I realise I can set my intents as 'triggers', but Google Assistant still asks if I'd like to use [my app name] and I have to confirm. Is there any way to automatically make it use my app if my voice command matches a trigger?
Related
I am trying to develop an agent using DialogFlow. When doing this, it is possible to debug the agent via the link https://console.dialogflow.com/api-client/#/assistant_preview .This (sort of) works as far as it allows me to interact with my agent etc. On the DialogFlow integrations page I can create a "Web Demo". Typing in exactly the same interactions with the web demo when trying to perform user sign in fails, where as on the simulator it works.
This may be similar to Dialogflow Agent works in Google simulator, failed in console and web link
Surely both methods of interaction should work the same way otherwise this is impossible to test with any level of confidence.
User sign-in is an Assistant feature that Dialogflow supports, but it is not a Dialogflow feature.
The Web Demo is just that - a demo. You can use the Dialogflow Detect Intent API and provide your own authentication system through that if that's what you're trying to do.
If you're looking to test just the Dialogflow interaction, you can test that using the simulator on the right hand side of the page.
I have created a custom cortana skill using bot frame work.My channel name or invocation phrase is "S********O".When I tried to invoke Cortana skill in Windows Phone, it doesn't invoke the skill. Instead, it keeps directing me to Bing results.
I invoke skill using Ask Keyword Ask "S********O" and it redirects to bing search. Its is working fine in Andriod. Is anyone have idea about this.
There are a few reasons why you get directed to Bing instead of a skill.
The account you are using on the device is not the same one used for development (self publish / default settings)
Your region and/or language settings are not US / en-US in the App
The account you are using is an AAD joined account, not Microsoft account
You've discovered a bug
I have created a Google Home app in DialogFlow and have since had the app published by Google. I am assuming that I can change the fulfillment endpoint address in Dialogflow and this won't affect my live app - my assumption being that a packaged version of the app together with the endpoint at submission time is what is running on the Google Assistant.
Does anybody know if this assumption is correct?
No, this assumption is not correct.
By default, changing the fulfillment URL in your Dialogflow project will change it for the live Action.
Although there is some information that is generated when you release an Action built with Dialogflow (the Intents and Entities, for example, get turned into entries for the Assistant), the fulfillment URL is not one of them. The Assistant sends it to a special URL on Dialogflow's servers, and Dialogflow then sends it to the URL you've specified.
However, you can look into the Dialogflow Beta feature that supports versions and environments to see if that will do what you want.
Is it possible to change the name of the bot during runtime. Current the name which i have added in portal is getting displayed under bot message. Is it possible to update it in run time using node.js rather than displaying the name configured in portal.
You can change the display name of the bot, in bot's settings page. Following is a screenshot where you can do this.
How do you store permanent data in a Slack Application?
For example, the Opsidian slack app has a command to add your AWS keys. Where does it store those keys and how does it know to use specific keys for specific teams?
Is this on the Opsidian side? If that's the case does it just use the team.info endpoint and use that every command to match it up?
I have searched their documentation and Google with no luck.
A slack app usually consists of program code (e.g. PHP) and a database (e.g. MySQL) that runs on a server and interfaces with Slack through one of the APIs. All Slack team specific information is stored in a custom datadase using the unique team ID as key. The server needs to be accessible from the Internet, so that Slack can communicate with it. The server to run the program code of the app and the custom database for the app is not provided by Slack, but needs to be setup and maintained by the Slack app developer.
Slack itself only stores the basic configuration for an app (everything you see under "Your apps", e.g. Validation token) and some basic configuration per team after installation (e.g. That an app is installed and who installed it). Any other application specific information has to be stored by the app itself in its database.
The Slack app developer also needs to provide a custom website to allow installation of a Slack app for a team. See this answer for more info about the installation process and how to obtain a team specific access token.