[SEO Subhead]
This Guidance demonstrates how organizations in the travel and hospitality (T&H) industry can build an intelligent virtual assistant that uses generative AI to streamline every aspect of travel planning. Through a personalized chat interface, the virtual concierge curates tailored travel itineraries, handles all bookings, and provides recommendations for flights, accommodations, activities, and local experiences based on individual preferences, budgets, and travel styles. Once bookings are made, the virtual concierge supports travelers with any questions or changes for a stress-free and flexible travel experience.
Note: [Disclaimer]
Architecture Diagram
[Architecture diagram description]
Step 1
Index FAQs and documents stored on Amazon Simple Storage Service (Amazon S3) using Amazon Bedrock Knowledge Bases to build vector knowledge stores for enterprise data.
Step 2
Use Amazon Cognito to authenticate the guest or traveler. Initiate the conversation using the chat interface from your existing web and mobile app. Amazon API Gateway serves as the entry point for client requests, routing to an AWS Lambda function that invokes Amazon Bedrock Agents.
Step 3
Amazon Bedrock Guardrails provides an external validation flow that allows you to check user inputs and large language model (LLM) responses against a set of topic denial rules, harmful content, text, or sensitive information before going back to the user. This helps protect your brand image and secure your applications.
Step 4
Amazon Bedrock Agents takes into account the task sent by the user, alongside the conversation history, available actions, knowledge bases, and provided instructions in the prompt to create a plan to retrieve the necessary data to craft a response. The action group actions will be defined in a Lambda function that will load an API schema from Amazon S3.
Step 5
The ideation action will use an identifier from the authenticated user to query a customer data and loyalty system and retrieve previous booking and interaction data, loyalty status, available perks and offers, and more. Based on this data and the user requirements, a customized travel destination and itinerary will be offered back to the user.
Step 6
Once the user has decided on a destination and a date, the availability action will query (such as available flights and hotels) and present the options to the user. When ready to book, the booking action will connect to booking systems to complete the booking and offer a summary back to the user.
Step 7
The existing bookings Q&A action retrieves the users existing bookings, and based on the question from the user, selects the appropriate metadata filters (such as airline or hotel) to query the knowledge base, confirming the response is based on the correct data.
Step 1
Index FAQs and documents stored on Amazon Simple Storage Service (Amazon S3) using Amazon Bedrock Knowledge Bases to build vector knowledge stores for enterprise data.
Step 2
Use Amazon Cognito to authenticate the guest or traveler. Initiate the conversation using the chat interface from your existing web and mobile app. Amazon API Gateway serves as the entry point for client requests, routing to an AWS Lambda function that invokes Amazon Bedrock Agents.
Step 3
Amazon Bedrock Guardrails provides an external validation flow that allows you to check user inputs and large language model (LLM) responses against a set of topic denial rules, harmful content, text, or sensitive information before going back to the user. This helps protect your brand image and secure your applications.
Step 4
Amazon Bedrock Agents takes into account the task sent by the user, alongside the conversation history, available actions, knowledge bases, and provided instructions in the prompt to create a plan to retrieve the necessary data to craft a response. The action group actions will be defined in a Lambda function that will load an API schema from Amazon S3.
Step 5
The ideation action will use an identifier from the authenticated user to query a customer data and loyalty system and retrieve previous booking and interaction data, loyalty status, available perks and offers, and more. Based on this data and the user requirements, a customized travel destination and itinerary will be offered back to the user.
Step 6
Once the user has decided on a destination and a date, the availability action will query (such as available flights and hotels) and present the options to the user. When ready to book, the booking action will connect to booking systems to complete the booking and offer a summary back to the user.
Step 7
The existing bookings Q&A action retrieves the users existing bookings, and based on the question from the user, selects the appropriate metadata filters (such as airline or hotel) to query the knowledge base, confirming the response is based on the correct data.
Get Started
Well-Architected Pillars
The AWS Well-Architected Framework helps you understand the pros and cons of the decisions you make when building systems in the cloud. The six pillars of the Framework allow you to learn architectural best practices for designing and operating reliable, secure, efficient, cost-effective, and sustainable systems. Using the AWS Well-Architected Tool, available at no charge in the AWS Management Console, you can review your workloads against these best practices by answering a set of questions for each pillar.
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.
-
Operational ExcellenceRead the Operational Excellence whitepaper
AWS Cloud Development Kit (AWS CDK) allows you to define AWS resources using traditional programming languages. By defining all AWS resources with AWS CDK, you can replicate deployments and safely deploy changes and updates to workloads. Amazon CloudWatch proactively monitors applications and infrastructure, helping identify anomalies, troubleshoot issues, and ensure peak efficiency.
-
SecurityRead the Security whitepaper
Amazon Cognito securely manages user identities and access for web and mobile applications, minimizing custom identity management code while enhancing security through multi-factor authentication. Amazon Bedrock provides data privacy and security through encryption at rest and in transit, access controls, and support for regulatory standards. Amazon Bedrock Guardrails implement safeguards for generative AI applications, filtering undesirable content and protecting against data leaks.
-
ReliabilityRead the Reliability whitepaper
Amazon Bedrock offers provisioned throughput, enabling application performance scaling to meet user base demands. This capability helps ensure reliable service delivery, handling fluctuations in demand.
-
Performance EfficiencyRead the Performance Efficiency whitepaper
Amazon Bedrock provides a wide range of foundation models, allowing selection of the most appropriate model for specific use cases and requirements. Additionally, Amazon Bedrock Knowledge Bases offers various vector database options, optimizing for factors like cost, operational overhead, and data location.
-
Cost OptimizationRead the Cost Optimization whitepaper
The S3 Intelligent-Tiering storage class automatically moves data to the most cost-effective access tier, reducing storage costs without impacting performance. This helps ensure that the raw knowledgebase files that you upload to your S3 bucket are correctly handled and moved to cheaper storage classes when they are no longer frequently accessed.
-
SustainabilityRead the Sustainability whitepaper
Lambda runs code without provisioning or managing servers, automatically scaling to meet demand, reusing execution environments, and optimizing resource utilization. This serverless approach contributes to a more sustainable architecture and minimizes energy consumption.
Related Content
[Title]
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.
References to third-party services or organizations in this Guidance do not imply an endorsement, sponsorship, or affiliation between Amazon or AWS and the third party. Guidance from AWS is a technical starting point, and you can customize your integration with third-party services when you deploy the architecture.