I've built a custom integration for Dialogflow CX which allows the user to send multiple messages to the Agent. However, the Agent doesn't understand what the user is trying to say when it receives more than one message.
How can I configure my Agent to wait a predetermined amount of time (allowing the user to send as many messages as possible) before trying to reply so that the Agent can make sense of all the text that was sent?
Unfortunately, that's not how Dialogflow-CX agents work. You can't wait a predetermined amount of time before answering: to each prompt from the user the agent will provide a fulfilment if it's specified.
The only way to achieve what you're asking is to develop an integration starting from the API they provide. You could develop an integration which waits a determined interval, joins all text received and sends it to the API via detectIntent request. This way you could have the user input multiple texts and only return a response when needed, but you'd need to handle the logic yourself (meaning a basic to intermediate knowledge of a programming language probably).
Related
I have a question regarding the effect of eventually consistent (EC) microservice systems.
Imagine we have a booking system - a user-service A and booking-service B. Each service has its own database. Imagine the system does a concurrent booking of the same resource for distinct users at the same time. Lets assume we have a Runtime Verification System checking the concurrent booking.
Would it be possible that the monitor does not realize the concurrent booking at B, because the update in the database is done delayed because of the EC mechanism?
In your example, the Booking Service is the source of truth (presumably) for whether or not the resource is available to book. So, that service should be pretty clear on allowing the first booking request to happen and rejecting the second.
In a case like this, where "first come first served" is the requirement, you'd want an intermediate state that would wait for a response from the Booking Service and update the User Service only when a response has been received.
If your architecture is set up right, User Service shouldn't be calling Booking Service directly anyway - it should be communicating through a messaging plane. As such, when the User clicks "Book Now," you could generate a resourceBookingRequested message and submit it to the queue. You'd acknowledge this request has been queued to the user and update their UI to "Awaiting Booking Confirmation..." or something similar.
Once the booking is accepted, or rejected, the User Service subscribes to the resulting message and updates the UI (and/or takes other actions like sending an email) to let the user know their request succeeded or didn't.
Is it possible to stop call recordings in Amazon Connect so the customer and agent can discuss sensitive material without being recorded?
I am aware of the set call recording behaviour blocks, but they don't seem to work on a call that has already been started with an agent with call recording enabled. Transferring to another contact flow with the recording type set to none doesn't seem to make a difference and the call carries on being recorded.
I am aware of the sample workflow Sample secure input with agent as outlined in this AWS blog https://aws.amazon.com/premiumsupport/knowledge-center/disable-recording-amazon-connect. This does work, however it relies on the customer entering payment details whilst the agent is on hold - preventing the agent and customer from having a sensitive conversation.
It seems the only way to stop recording once it has been enabled is to put the agent on hold?
Do not know if you have not solved your issue yet, but amazon has update their Amazon Connect API that would allow you to suspend the recording.
Boto3 implementation
response = client.suspend_contact_recording(
InstanceId='string',
ContactId='string',
InitialContactId='string'
)
https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/connect.html#Connect.Client.suspend_contact_recording
They have also allow you to Start, Pause, Stop. (
We have just started to review this for a POC, turn recording off be default for a group of queues. Allow to Agents to start and stop and pause recording as needed.
You can also read this in an Amazon Blog post that should be able to help you fully implement the solution.
https://aws.amazon.com/blogs/contact-center/pausing-and-resuming-call-recordings-with-a-new-api-in-amazon-connect/#:~:text=is%20not%20recorded.-,End%20the%20call.,you%20start%20and%20stop%20it.
After speaking with Architects at AWS, the desired and designed for solution is to have the customer automatically enter sensitive information with the agent on hold and call recording turned off to remain PCI compliant.
If that is not an option there are workarounds possible that go against the way Amazon Connect has been designed. In order to turn off call recording once it has been enabled on a call, a new contact ID must be established. To do this you would need to transfer the user to your external phone number again or transfer to a queue and disable call recording in that new flow.
This brings in extra issues around how to get the customer back to the original agent once the sensitive information has been discussed. It also means you would potentially have 3+ contact IDs for the same transaction, with call recording spread across them.
I'm trying to build an alexa skill that fires a custom alarm every set number of times per day (30 min intervals for example). I'm reading through their docs and not fulling understanding where to go to next.
Does anyone have some good Alexa skill apps that I can reference or an article? I couldn't find much online and it looks like it hasn't been an accessible feature for too long.
You cannot trigger Alexa to speak without user interaction. That means, the user has to say something to trigger your skill, which will in turn create a request to you skill's backend, and you can only respond (be it audio or speech) back to that request.
However, you can send Push Notifications.
Notification indicators inform end users that new content is available
from Alexa skills and domains. When a notification is delivered,
depending on what the product is capable of, the user is notified by
visual and audio indicators.
More on Push Notification here
I've been working on a Dialogflow chatbot that calls a webhook which can often take more than the 5s delay to process and answer the user's request. So, following this post, my webhook sends a response containing a followup event if the processing is too long, and will be able to answer the following request sent by the intent triggered by the event.
Now, while this approach is working great, I have two questions :
Is there any way to send a message ("Please wait, I'm processing your request") to the user on every followup event ?
Since I'm using the Dialogflow-Messenger integration, is there any way to display the three dots "typing" animation while the webhook is processing the request ?
Thanks !
When developing a chatbot, you should keep in mind that you are trying to duplicate how 2 humans interact. You are developing a conversation and in the conversation, we should not keep other person waiting. All your requests should be completed within 4-5 seconds (to avoid timeout by the platform) to have a better UX.
So there is no way to show either Please Wait or animated 3 dots!
Write a good backend code to fetch response faster or tweak and cache your response. Dialogflow is currently designed for 1-1 conversation and cannot provide multiple delayed responses. If you need it that way, you will require to develop your own NLP engine.
We have a BizTalk application which sends XML files to external applications by using a web-service.
BizTalk calls the web-services method by passing XML file and destination application URL as parameters.
If the external applications are not able to receive the XML, or if there is no response received from the web-service back to BizTalk the message gets suspended in BizTalk.
Presently for this situation we manually go to BizTalk admin and resume each suspended message.
Our clients want this process to be automated all, they want an dashboard which shows list of message details and a button, on its click all the suspended messages have to be resumed.
If you are doing this within an orchestration and catching the connection error, just add a delay shape configured to 5 hours. Or set a retry interval to 300 minutes and multiple retries on the send port if that makes sense. You can do this using the rule engine as well.
Why not implement an asynchronous pattern?
You make it so, so that the orchestration sends the file out via a send shape while initializing a certain correlation set.
You then put a listen shape with at one end:
- the receive (following the initialized correlation set)
- a delay shape set to 5 hours.
When you receive the message, your orchestration can handle it gracefully.
When you don't, the delay shape will kick in and you handle accordingly.
Benefit to this solution in comparison to the solution of 40Alpha will be that your orchestration will only 'wake up' from a dehydrated state if the timeout kicks in OR when the response is received. In the example of 40Alpha, the orchestration would wake up a lot of times, consuming extra resources.
You may want to look a product like BizTalk 360. It has those sort of monitoring and command built into it. I'm not sure it works with BizTalk 2006R2 though, but you should be thinking about moving off that platform anyway as it is going out of Microsoft support.