Skip to main content

Guidance for Driving Operational Excellence with Conversational AI on AWS

Overview

This Guidance demonstrates how to build a seamless conversational interface between guests and customer service agents. Through voice, chat, and text channels, customer interactions can be retrieved by customer service agents, securely saved, and tracked for errors or exceptions, all through a secure, SSL connection. 

How it works

This diagram shows how to build a conversational interface between travel guests and customer serviceagents. Create a seamless and personalized experience for customers who interact with agents throughvoice, chat, and text channels.

Download the architecture diagram PDF

Well-Architected Pillars

The architecture diagram above is an example of a Solution created with Well-Architected best practices in mind. To be fully Well-Architected, you should follow as many Well-Architected best practices as possible.

The Guidance is deployed using AWS CloudFormation. You can add it to your own development pipeline to deploy in a test environment. 

CloudWatch provides observability through the collection of metrics and logs, as well as customizable dashboards. 

Read the Operational Excellence whitepaper

Amazon Cognito user pools use an identity provider (IdP) for built-in user management. 

Lambda only allows users access to the services they need with the least-privilege roles. 

The customer's data in DynamoDB is encrypted at rest.

Read the Security whitepaper

The serverless elements such as Lambda functions, DynamoDB, Amazon Cognito, and Fargate have high availability and automatically scale based on demand. DynamoDB deploys with cross-Region failover for higher availability.

Read the Reliability whitepaper

The serverless elements allow you to provision the exact resources that the workload needs. CloudWatch Alarms and Lambda metrics allow monitoring for expected performance. For more unexpected traffic, configure DynamoDB as on-demand, as this service is originally provisioned for consistent traffic. 

Read the Performance Efficiency whitepaper

Serverless elements use a pay-per-value pricing model and scale based on demand. 

If you want to further optimize cost, you should share the same key-value tag for assets that belong to the project programmatically and create custom reports in AWS Cost Explorer based on the tags that you have created.

Read the Cost Optimization whitepaper

Using only the resources that the workload needs, you minimize the environmental impact of the backend and storage services.

Read the Sustainability whitepaper

Disclaimer

The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.