Legacy Transfer Solution

Website AI Chatbot Assistant

Legacy Transfer Solutions partnered with Futuralis to build a secure, website-integrated AI chatbot on AWS. Using Amazon Bedrock, AWS Lambda, API Gateway, Amazon S3, and Bedrock Guardrails, the solution delivers real-time, context-aware responses grounded in approved business content. The chatbot improves customer engagement, response accuracy, scalability, and operational visibility.

Challenges

LTS required a responsive chatbot experience that could be embedded into the existing website and support bidirectional communication.

The solution needed to maintain conversation context, manage user sessions, and reliably process messages across multiple interactions.

The chatbot needed to generate intelligent answers while relying only on approved internal documents, FAQs, and business information.

Strong guardrails and filtering mechanisms were required to prevent unsafe, irrelevant, or out-of-scope responses.

The solution required comprehensive logging, monitoring, tracing, performance testing, security validation, and deployment documentation before launch.

Benefits

Website visitors can receive immediate answers to frequently asked questions without waiting for manual assistance.

RAG-based retrieval grounds chatbot responses in approved LTS documents, FAQs, and knowledge-base content.

The serverless AWS architecture minimizes infrastructure management and automatically scales based on demand.

Bedrock Guardrails and filtering controls restrict responses to secure, appropriate, and domain-relevant topics.

The chatbot architecture can be extended to support multilingual conversations, CRM integration, analytics, live-agent escalation, and additional knowledge sources.

The Challenge

LTS needed to improve website-based customer interaction by introducing an AI assistant that could answer common customer questions in real time while staying within approved domain boundaries. The chatbot needed to integrate with the website, retain conversation context, use internal documents for retrieval, and include filtering mechanisms to prevent irrelevant or unsafe responses.

Why Futuralis
& AWS

LTS partnered with Futuralis because of its experience building AWS-native generative AI applications, serverless APIs, Bedrock Agent architectures, secure cloud deployments, and customer-facing digital experiences.

AWS provided the managed services required to deliver the chatbot quickly and securely without requiring LTS to operate custom AI infrastructure. Futuralis used AWS services to combine real-time APIs, Bedrock foundation models, RAG-based knowledge retrieval, guardrails, frontend integration, and operational monitoring into a production-ready chatbot foundation.

Futuralis designed the solution around:

  • Real-time chatbot communication using Amazon API Gateway WebSocket APIs
  • Serverless backend processing using AWS Lambda
  • AI orchestration and response generation using Amazon Bedrock Agents and foundation models
  • Knowledge base document storage using Amazon S3
  • Domain-relevant response control using Bedrock Guardrails and content filtering
  • Global website delivery and routing support using Amazon CloudFront and Amazon Route 53
  • Operational visibility using Amazon CloudWatch and AWS X-Ray

Our Solution

The AWS-centered solution to meet PCI compliance included:

Futuralis designed and implemented a website AI chatbot assistant on AWS using Amazon Bedrock, Bedrock Agents, Bedrock Guardrails, API Gateway WebSocket APIs, AWS Lambda, Amazon S3, Amazon CloudFront, Amazon Route 53, CloudWatch, and X-Ray. The implementation covered discovery, architecture, backend development, frontend integration, testing, deployment, and handover.

Discovery, Planning, and AWS Setup:

  • Conducted discovery sessions to understand chatbot goals, expected user journeys, knowledge base requirements, and deployment dependencies
  • Collected required AWS account access details and permissions for implementation activities
  • Prepared the project plan, milestones, implementation tasks, and production readiness activities

Real-Time API and Serverless Backend:

  • Developed WebSocket APIs to enable real-time bidirectional communication between the chatbot interface and AWS backend
  • Configured Amazon API Gateway to securely handle chat traffic and route messages to backend processing logic
  • Built AWS Lambda functions for request handling, Bedrock integration, session management, and chatbot workflow orchestration
  • Designed API logic to support message flow, context retention, and reliable interaction processing

Bedrock, RAG, and Guardrail Integration:

  • Configured Amazon Bedrock foundation model access for intelligent and context-aware response generation
  • Configured Bedrock Agent orchestration to handle user queries and response workflows
  • Created an Amazon S3-based knowledge base location for chatbot documents such as PDFs and FAQs
  • Enabled Retrieval-Augmented Generation patterns to enhance responses using approved internal knowledge sources
  • Implemented Bedrock Guardrails and filtering controls to restrict responses to safe and domain-relevant topics

Frontend, Observability, Testing, and Go-Live:

  • Designed and developed a modern responsive chatbot interface aligned with the website user experience
  • Integrated the chatbot frontend with WebSocket APIs for end-to-end interaction capability
  • Configured CloudFront and Route 53 to support performance, routing, and availability of the API endpoints
  • Enabled CloudWatch and X-Ray for logging, metrics, monitoring, and tracing across the chatbot workflow
  • Performed unit, integration, guardrail, performance, and production smoke testing before go-live
  • Delivered documentation, administrative guidance, handover support, and final signoff materials

Results & Benefits

Real-Time AI-Powered Customer Support
LTS now provides website visitors with immediate, intelligent responses through a fully integrated AI chatbot. The solution improves customer engagement by answering common questions in real time while maintaining conversation context across each session.
Accurate and Knowledge-Grounded Responses
The chatbot uses Retrieval-Augmented Generation to retrieve approved information from internal documents, FAQs, and knowledge sources stored on AWS. This improves response accuracy and helps ensure that answers remain relevant to LTS services and customer needs.
Secure and Scalable AWS Architecture
The serverless architecture built with Amazon API Gateway, AWS Lambda, and Amazon Bedrock provides a scalable foundation without requiring LTS to manage dedicated AI infrastructure. The solution can automatically support changing website traffic while reducing ongoing operational overhead.
Improved Safety and Operational Visibility
Amazon Bedrock Guardrails and content filtering help prevent unsafe, irrelevant, or out-of-domain responses. Amazon CloudWatch and AWS X-Ray provide centralized logging, monitoring, metrics, and tracing for troubleshooting and continuous improvement.

Legacy Transfer Solutions (LTS), founded by Gabrielle Eskin, operates in the professional services and legacy planning industry. The company provides legacy transfer and estate planning services to individual and corporate clients. LTS needed to modernize their client engagement by providing instant, AI-powered assistance to website visitors seeking information about their services.

Ready to discover how Futuralis can elevate your cloud journey?

Get in touch today and let’s explore the full power of AWS together.