Enhance agent productiveness with Salesforce integration for Dwell Name Analytics

As a contact heart agent, would you fairly give attention to having productive buyer conversations or get distracted by having to search for buyer data and data articles that would exist in varied methods? We’ve all been there. Having a productive dialog whereas multitasking is difficult. A single detrimental expertise could put a dent on a buyer’s notion of your model.

The Live Call Analytics with Agent Assist (LCA) open-source resolution addresses these challenges by offering options akin to AI-powered agent help, name transcription, name summarization, and way more. As a part of our effort to fulfill the wants of your brokers, we try so as to add options based mostly in your suggestions and our personal expertise serving to contact heart operators.

One of many options we added is the power to put in writing your individual AWS Lambda hooks for the start of call and post-call to customized course of calls as they happen. This makes it simpler to customized combine with LCA structure with out advanced modification to the unique supply code. It additionally permits you to replace LCA stack deployments extra simply and shortly than should you have been modifying the code instantly.

Right this moment, we’re excited to announce a function that permits you to combine LCA together with your Buyer Relationship Administration (CRM) system, constructed on high of the pre- and post-call Lambda hooks.

On this publish, we stroll you thru organising the LCA/CRM integration with Salesforce.

Resolution overview

LCA now has two further Lambda hooks:

• Begin of name Lambda hook – The LCA Name Occasion/Transcript Processor invokes this hook in the beginning of every name. This operate can implement customized logic that applies to the start of name processing, akin to retrieving name abstract particulars logged right into a case in a CRM.
• Publish-call abstract Lambda hook – The LCA Name Occasion/Transcript Processor invokes this hook after the decision abstract is processed. This operate can implement customized logic that’s related to postprocessing, for instance, updating the decision abstract to a CRM system.

The next diagram illustrates the beginning of name and post-call (abstract) Lambda hooks that combine with Salesforce to search for and replace case data, respectively.

Listed below are the steps we stroll you thru:

1. Arrange Salesforce to permit the customized Lambda hooks to search for or replace the case data.
2. Deploy the LCA and Salesforce integration stacks.
3. Replace the LCA stack with the Salesforce integration Lambda hooks and carry out validations.

Stipulations

You want the next conditions:

Create a Salesforce related app

To arrange your Salesforce app, full the next steps:

1. Log in to your Salesforce org and go to Setup.
2. Seek for App Supervisor and select App Supervisor.
   
3. Select New Related App.
4. For Related App Title, enter a reputation.
5. For Contact E mail, enter a legitimate e mail.
6. Choose Allow OAuth Settings and enter a price for Callback URL.
7. Beneath Out there OAuth Scopes, select Handle person information by way of APIs (api).
8. Choose Require Secret for Webserver Movement and Require Secret for Refresh Token Movement.
9. Select Save.
   
10. Beneath API (Allow OAuth Settings), select Handle Shopper Particulars.
11. Confirm your id if prompted.
12. Copy the buyer key and shopper secret.

You want these when deploying the AWS Serverless Application Model (AWS SAM) software.

Get your Salesforce entry token

For those who don’t have already got an entry token, you want to acquire one. Earlier than doing this, just be sure you’re ready to replace any functions which can be utilizing an entry token as a result of this step creates a brand new one and will invalidate the prior tokens.

1. Discover your private data by selecting Settings from View profile on the highest proper.
2. Select Reset My Safety Token adopted by Reset Safety Token.
   
3. Make be aware of the brand new entry token that you just obtain by way of e mail.

Create a Salesforce buyer contact report for every caller

The Lambda operate that performs case look-up and replace matches the caller’s cellphone quantity with a contact report in Salesforce. To create a brand new contact, full the next steps:

1. Log in to your Salesforce org.
2. Beneath App Launcher, seek for and select Service Console.
   
3. On the Service Console web page, select Contacts from the drop-down listing, then select New.
   
4. Enter a legitimate cellphone quantity underneath the Cellphone discipline of the New Contact web page.
5. Enter different contact particulars and select Save.
6. Repeat Steps 1–5 for any caller that makes a cellphone name and check the combination.

Deploy the LCA stack

Full the next steps to deploy the LCA stack:

1. Observe the directions underneath the Deploy the CloudFormation stack part of Live call analytics and agent assist for your contact center with Amazon language AI services.
2. Just be sure you select ANTHROPIC, SAGEMAKER, or LAMBDA for the Finish of Name Transcript Abstract parameter. See Transcript Summarization for extra particulars.

The stacks take about 45 minutes to deploy.

3. After the primary stack reveals CREATE_COMPLETE, on the Outputs tab, make a remark of the Kinesis information stream ARN (CallDataStreamArn).

Deploy the Salesforce integration stack

To deploy the Salesforce integration stack, full the next steps:

1. Open a command-line terminal and run the next instructions:

https://github.com/aws-samples/amazon-transcribe-live-call-analytics.git
cd amazon-transcribe-live-call-analytics/plugins/salesforce-integration
sam construct
sam deploy —guided

Use the next desk as a reference for parameter decisions.

2. After the stack efficiently deploys, make a remark of StartOfCallLambdaHookFunctionArn and PostCallSummaryLambdaHookFunctionArn from the outputs displayed in your terminal.

Replace LCA Stack

Full the next steps to replace the LCA stack:

1. On the AWS CloudFormation console, replace the primary LCA stack.
2. Select Use present template.
3. For Lambda Hook Perform ARN for Customized Begin of Name Processing (present), present the StartOfCallLambdaHookFunctionArn that you just obtained earlier.
4. For Lambda Hook Perform ARN for Customized Publish Processing, after the Name Transcript Abstract is processed (present), present the PostCallSummaryLambdaHookFunctionArn that you just obtained earlier.
5. Guarantee that Finish of Name Transcript Abstract just isn’t DISABLED.

Validate the combination

Make a check name and ensure you can see the start of name AGENT ASSIST and post-call AGENT ASSIST transcripts. Discuss with the Discover reside name evaluation and agent help options part of the Live call analytics and agent assist for your contact center with Amazon language AI services publish for steerage.

Clear up

To keep away from incurring prices, clear up your sources by following these directions when you’re completed experimenting with this resolution:

1. On the AWS CloudFormation console, and delete the LCA stacks that you just deployed. This deletes sources that have been created by deploying the answer. The recording S3 buckets, DynamoDB desk, and CloudWatch log teams are retained after the stack is deleted to keep away from deleting your information.
2. In your terminal, run sam delete to delete the Salesforce integration Lambda features.
3. Observe the directions in Deactivate a Developer Edition Org to deactivate your Salesforce Developer org.

Conclusion

On this publish, we demonstrated how the Dwell-Name Analytics pattern challenge can speed up your adoption of real-time contact heart analytics and integration. Quite than constructing from scratch, we present how one can use the present code base with the pre-built integration factors with the beginning of name and post-call Lambda hooks. This enhances agent productiveness by integrating with Salesforce to search for and replace case data. Discover our open-source project and improve the CRM pre- and post-call Lambda hooks to accommodate your use case.

Concerning the Authors

Kishore Dhamodaran is a Senior Options Architect at AWS.

Bob Strahan is a Principal Options Architect within the AWS Language AI Providers group.

Christopher Lott is a Senior Options Architect within the AWS AI Language Providers group. He has 20 years of enterprise software program improvement expertise. Chris lives in Sacramento, California and enjoys gardening, aerospace, and touring the world.

Babu Srinivasan is a Sr. Specialist SA – Language AI companies within the World Large Specialist group at AWS, with over 24 years of expertise in IT and the final 6 years centered on the AWS Cloud. He’s keen about AI/ML. Exterior of labor, he enjoys woodworking and entertains family and friends (typically strangers) with sleight of hand card magic.