Data, such as speaker sentiment analysis and how well a customer’s internal compliance rules are met, is used to identify how effective contact center agents are at handling customer calls. The same data identifies the topics and entities discussed in the call. All of this data can be visualised in QuickSight to help business analysts identify trends from a customer’s perspective and potential training needs for agents. 

All data is encrypted both in motion and at rest, and can use customer-controlled AWS Key Management Service (AWS KMS) keys for this encryption. The solution is entirely serverless, but the AWS Lambda components can optionally run within a customer’s VPC, accessing external services such as Amazon Transcribe and Amazon S3 only through a customer’s approved endpoints.

The solution is entirely serverless, and each of those services (Amazon Transcribe, Amazon S3) operate using multiple Availability Zones in a resilient fashion.

The solution scales usage of its serverless components as it needs to, both up and down, in order to handle the concurrent processing of potentially thousands of calls or those times when there are no pending calls to process.

The solution only uses serverless components when there is an active call audio file to process, minimizing the incurred costs as much as possible. If required, the original audio files can be archived to lower cost long-term storage on a customer-specified schedule in order to minimize storage costs. 

By using managed services and dynamic scaling, we minimize the environmental impact of the backend services.