Provide real-time agent assistance to your chatbot users through Amazon Lex and Talkdesk cloud contact centers

Amazon Lex gives superior conversational synthetic intelligence (AI) capabilities to offer self-service help to your group’s contact middle. With Amazon Lex, you possibly can implement an omnichannel technique that lets clients work together through cellphone, web site, and messaging platforms. Bots can reply continuously requested questions, present a self-service expertise, or triage buyer requests earlier than being transferred to a human agent. Amazon Lex integrates with essentially the most superior contact facilities, together with Amazon Join, Genesys Cloud, and Amazon Chime SDK, to facilitate a seamless omnichannel expertise.

That is the second article in a two-part sequence. The mixing of Amazon Lex with Talkdesk cloud contact middle was impressed by WaFd Financial institution’s (WaFd) digital innovation journey to boost buyer expertise. In our earlier article, we described how Amazon Lex integrates with Talkdesk Cloud Contact Heart to allow voice channels. On this article, we concentrate on chat pipelines to indicate how you need to use Amazon Lex and the Amazon Lex Net UI to allow reside brokers to work together along with your clients immediately. For instance, the picture beneath reveals a screenshot of a chatbot that converts a buyer to talk with a reside agent (courtesy of WaFd Financial institution).

Resolution overview

The diagram beneath reveals the structure of the answer.

Within the earlier structure, the next sequence of steps happens in a reside buyer/agent dialog:

1. Utilizing the Amazon Lex Net UI, the client requests a connection to the agent. The related Amazon Lex chatbot is configured with an escalation intent to deal with incoming agent help requests.
2. The Amazon Lex implementation of the AWS Lambda operate retrieves the Talkdesk touchpoint ID and Talkdesk OAuth key from AWS Secrets and techniques Supervisor and makes a request to Talkdesk Digital Join utilizing the Begin Dialog API. Within the payload, the operate consists of data which may be helpful to the agent, similar to buyer sentiment or the historical past of beforehand traversed intents.
3. If the request to the Talkdesk API is profitable, the Talkdesk dialog ID shall be returned to Amazon Lex.
4. Amazon Lex implements a Lambda operate to retailer the dialog ID within the Amazon Lex session property, permitting the Amazon Lex Net UI to entry the dialog ID.
5. The Amazon Lex Net UI opens a communication session with an agent on the Talkdesk contact middle by the WebSocket API within the Amazon API Gateway.
6. The Lambda related to the WebSocket API first shops the Talkdesk session ID equivalent to the WebSocket shopper ID in Amazon DynamoDB. Then, by the Talkdesk Ship Message API, the Lambda operate sends the client’s message to the Talkdesk contact middle agent.
7. Your agent responds to the shopper by sending a message through the callback Relaxation API in API Gateway. The payload consists of the dialog ID of the lively dialog.
8. The Callback Relaxation API is configured to help proxying incoming messages and proxying out of conversations. With a purpose to ship the agent’s message to the shopper, a Lambda operate is supported to learn the WebSocket shopper ID related to the session ID from a DynamoDB desk. This ensures that the agent’s messages are delivered to the suitable WebSocket shopper ID.
9. The agent’s response is displayed by the Amazon Lex Net UI, and the client responds or closes the chat as acceptable. Steps 6-9 are repeated so long as the dialog stays lively. If the agent ends the dialog, the client is notified and the WebSocket connection is closed.

Within the following sections, we stroll you thru the steps of constructing an answer structure. Dependencies between every step are cross-referenced.

conditions

To implement the answer described on this article, it’s best to first turn into aware of the next AWS providers and options:

Moreover, you ought to be aware of the next Talkdesk providers:

Put together your Talkdesk occasion for Amazon Lex Net UI chat with an agent

This part outlines the fundamental steps required to arrange a Talkdesk chat expertise with an agent utilizing the Talkdesk Digital Join channel. Please assessment the Talkdesk API for extra particulars on any further duties which may be required throughout implementation.

Full the next steps:

1. Allow Talkdesk Digital Join in your Talkdesk occasion.
2. Configure your agent account and assign it to an agent’s queue.
3. Construct the Talkdesk Studio course of.

This shall be used to ship chat customers to the inbox for task by brokers. This answer gives an instance.

4. To construct the mixing to your Amazon Lex Net UI occasion, choose Combine.
5. superior motion tab to configure three operations utilizing the enter and output schemas supplied on the following hyperlink:

6. Set up Talkdesk Digital Join touchpoints.
7. Identify the touchpoint Lex Net UI Chat and document the touchpoint ID.

This shall be saved in Secrets and techniques Supervisor dev/talkdesk/touchpoint/ids.

8. In Talkdesk Builder, choose OAuth shopper Arrange OAuth credentials within the navigation pane.
9. select Grant sort for Buyer credentials and set scope arrive digital-connect:write.
10. Report the shopper ID and key within the “Keys” tab.

These shall be saved in Secrets and techniques Supervisor dev/talkdesk/shopper/keys and used for authentication and communication with the Talkdesk API.

11. In your AWS account, retailer these two keys in Secrets and techniques Supervisor.

The next screenshot reveals the small print of the touchpoint ID that’s the Secrets and techniques Supervisor key.

The next screenshot reveals the small print of the Shopper ID that’s the Secrets and techniques Supervisor key.

Deploy the Talkdesk Amazon Lex CloudFormation template

The next AWS CloudFormation template establishes all of the sources for the answer structure. This consists of all IAM roles required to name API operations, run related Lambda capabilities, entry keys on the Secrets and techniques Supervisor, and retailer and retrieve session ID and WebSocket shopper ID pairs from DynamoDB.

To facilitate monitoring and debugging, create a CloudWatch log group for every useful resource.

CloudFormation templates present further particulars for every useful resource.

Full the next steps to deploy the template:

1. Log in to the AWS Administration Console.
2. select Begin stacking to begin the CloudFormation stack creation course of to your AWS Area.
3. for stack titleenter a reputation.
4. for TDAUTHOSTenter the URL of your Talkdesk occasion.
5. Depart different parameters as default and choose Subsequent
   
6. Verify the Verify checkbox and choose Create stack.
   
7. After the CloudFormation template is accomplished, document the values ​​of the next keys in output Tabs to make use of in subsequent steps:
   • APIGatewayApiKey
   • BotAliasId
   • BotId
   • CallbackRestAPI
   • WebSocketAPIEndpoint

   

Replace Talkdesk occasion

Log in to your Talkdesk occasion and full the next steps to replace your occasion:

1. In Talkdesk Builder, choose Combine Within the navigation pane.
2. superior settings tab, discover base path And enter the callback Relaxation API URL you recorded earlier.
3. below Different settingsput x-api-key The worth of the API gateway key.

Deploy the Amazon Lex Net UI

The answer outlined on this article makes use of the Amazon Lex Net UI, a full-featured net shopper, to deploy the Amazon Lex chatbot in your web site. With the Amazon Lex Net UI, you possibly can rapidly allow chatbot-driven functions whereas minimizing time to worth.

1. select Begin stacking For the world the place you’ll use the chatbot:
2. for LexV2BotId,enter worth BotId.
3. for LexV2BotAliasId,enter worth BotAliasId.
   
4. Begin stacking.
5. After deployment is full, discover the Amazon Easy Storage Service (Amazon S3) URL WebAppBucket.
6. Navigate to the S3 bucket on the Amazon S3 console and obtain lex-web-ui-loader-config.json doc.
   
7. Open the file and modify or add the next parameters:
   1. Within the connection configuration part, add a brand new parameter talkDeskWebsocketEndpoint and set its worth to WebSocket endpoint.
   2. Within the UI configuration part, set enableLiveChat is true.

   

8. Add the modified lex-web-ui-loader-config.json file and overwrites the earlier model of the file within the S3 bucket.
9. Return to CloudFormation stack output tab and discover WebAppDomainName affiliation.

This can redirect you to the full-page model of the Amazon Lex Net UI. From right here, you possibly can check the Talkdesk integration and ensure that the bot is ready to connect with Talkdesk utilizing a WebSocket connection.

Take a look at answer

Now you are able to attempt Amazon Lex and Talkdesk chat interactions:

1. Begin your Banking Bot chat window utilizing the next command WebAppUrl Offered as output within the CloudFormation stack.
2. Log in to your Talkdesk Digital Join channel and navigate to dialogue.
3. Within the financial institution bot chat window, please chat with a customer support agent.
4. Watch buyer messages despatched to the Talkdesk dialog inbox.
5. Talkdesk brokers assign the dialog themselves and begin interacting with the client.

The next video demonstrates the chat expertise.

clear up

To scrub up your sources, full the next steps:

1. On the AWS CloudFormation console, select stack Within the navigation pane.
2. select LexTalkdesk Stack (or the stack title you present) and choose delete.
3. Delete stacked sources by deciding on Delete stack.

in conclusion

Amazon Lex brings the ability of conversational self-service to your clients’ most popular channels, similar to cellphone, net chat, and messaging apps. On this article, we reveal an answer that gives real-time customer support help in your web site by Amazon Lex, Amazon Lex Net UI, and Talkdesk Cloud Contact Heart. We offer a CloudFormation stack that features DynamoDB and Lambda sources, in addition to the Relaxation API and WebSocket API within the API Gateway to keep up communication periods with the Talkdesk Contact Heart agent.

The answer is designed to be a reference structure or fast implementation information that may be personalized to your group’s necessities. For those who need assistance establishing this answer, AWS Skilled Companies and Talkdesk can assist you and your workforce by the method of choosing the proper know-how to your cloud contact middle.

Concerning the writer

Grazia Russo Rasna is a senior advisor on the AWS Skilled Companies Pure Language AI workforce. She focuses on designing and creating conversational AI options for purchasers throughout a wide range of industries utilizing AWS know-how. Exterior of labor, she enjoys seashore weekends, studying the most recent novels, and household time.

Austin Johnson Is a options architect who helps keep the Lex Net UI open supply library.

Chris Brown is the Principal Pure Language AI Marketing consultant at AWS, specializing in digital buyer experiences – together with cell apps, web sites, advertising campaigns, and the most recent conversational AI functions. Chris is an award-winning strategist and product supervisor – working with Fortune 100 corporations to ship one of the best experiences for his or her clients. In his free time, Chris enjoys touring, music, artwork, and experiencing new cultures.

Bruno Matthäus is a Principal Engineer at Talkdesk. He has greater than 20 years of expertise within the software program trade, specializing in large-scale distributed methods. When not working, he enjoys spending time open air along with his household, climbing, mountain biking, and motorbike using.

Jonathan Diedrich is a Principal Options Marketing consultant at Talkdesk. He works on company and strategic initiatives to make sure know-how execution and adoption. Exterior of labor, he enjoys enjoying ice hockey and video games along with his household.

Chris Pimm Tribune He’s a senior software program engineer at Talkdesk, at the moment specializing in digital agent initiatives based mostly on synthetic intelligence. He has over 17 years of expertise in pc science, specializing in telecommunications, IPTV and fraud prevention. In his free time, he enjoys spending time along with his household, operating (he has accomplished three marathons), and using his motorbike.