Behind the Scenes: System Architecture

A detailed look at how ShopNova uses a hybrid AWS architecture, combining deterministic low-cost NLU with Generative AI for scalable, intelligent customer service.

The Call Flow

ShopNova Hybrid Contact Center Architecture A clean left-to-right and top-down architecture diagram for ShopNova using Amazon Connect, Amazon Lex V2, AWS Lambda, Amazon Q in Connect, S3 FAQ content, human agent transfer, Contact Lens, and CloudWatch. ShopNova - Hybrid Contact Center Architecture Amazon Connect voice orchestration + Lex/Lambda deterministic automation + Amazon Q self-service and agent assist Core voice flow AI knowledge path Support service Data or loop Dashed arrow: lookup, telemetry, or loopback Region: eu-west-2 London AWS production demo environment Customer Inbound voice call from the public demo number Amazon Connect ShopNova-MainFlow-Q-v8 IVR, voice prompts, queue routing, Connect Assistant block Amazon Lex V2 ShopNovaBot - intent detection and slot filling Orders, returns, inventory, FAQ fallback, goodbye, agent transfer Deterministic automation Conversation control Generative AI and agent support AWS Lambda Dispatcher shopnova-lex-dispatcher Order status, returns, inventory Goodbye and escalation routing Flow Decision Layer Goodbye disconnects, complaints escalate, and successful answers loop back to "anything else?" Amazon Q in Connect Q Self-Service Bot - AmazonQinConnect Generative FAQ answers for fallback and knowledge questions Mock Commerce Data Orders, returns, stock, and product catalog Human Agent BasicQueue transfer Voice Response Answer and loop S3 FAQ Policies and help Q Agent Assist Suggested replies data lookup resolved answer escalate prompt / disconnect Q answer knowledge lookup agent assist context anything else? loop Contact Lens Transcript, sentiment, categories CloudWatch Dashboards, logs, budget alerts speech analytics logs and metrics

How the Call Flow Works

ShopNova uses a hybrid contact center architecture where Amazon Connect controls the voice experience, Amazon Lex V2 detects customer intent, AWS Lambda handles deterministic business logic, and Amazon Q in Connect supports generative FAQ answers and agent assistance.

In the diagram, solid arrows represent the active conversation path, while dashed arrows represent supporting lookups, analytics, or loopback behavior.

1. Voice entry and orchestration

The customer calls the public ShopNova demo number. Amazon Connect answers the call, plays the IVR prompts, enables Contact Lens analytics, and sends the customer input to Amazon Lex V2 for intent detection.

2. Deterministic automation

When Lex detects a structured request such as order status, return initiation, or inventory availability, the request is routed to the AWS Lambda dispatcher. Lambda looks up the relevant mock commerce data and returns a clear response back into the voice flow.

3. Conversation control

The Connect flow handles control decisions such as goodbye, retry prompts, complaints, and human-agent escalation. If the customer asks for an agent or expresses frustration, the flow routes the call to BasicQueue.

4. Generative self-service

For FAQ-style questions or fallback cases, Lex routes the conversation to Amazon Q in Connect. Amazon Q retrieves policy information from the S3 FAQ knowledge source and generates a natural answer for the customer.

5. Voice response and loopback

Successful answers from Lambda, Amazon Q, or the Connect decision layer are delivered through the Voice Response step. After answering, the flow can ask whether the customer needs anything else and loop back to Lex for the next intent.

6. Human agent assist

When a call is transferred to a human agent, Amazon Q Agent Assist can provide suggested responses and relevant knowledge articles inside the Agent Workspace, helping the agent resolve the issue faster.

7. Observability and monitoring

Contact Lens captures transcripts, sentiment, and interaction categories, while CloudWatch provides logs, dashboards, and budget monitoring. These services observe the call flow without changing the customer conversation path.

Core AWS Services Breakdown

Amazon Connect

Telephony Backbone

Manages the IVR logic (ShopNova-MainFlow), queue management (BasicQueue), and hosts the Agent Workspace for human agents.

Amazon Lex V2

NLU Brain

Configured with specific intents for e-commerce (tracking, returns, inventory) and multi-turn dialogue slot filling (ShopNovaBot).

AWS Lambda

Serverless Logic

Uses a dispatcher pattern (shopnova-lex-dispatcher) to route requests to specific Python 3.14 handlers for deterministic intents.

Amazon Q in Connect

Enterprise AI Layer

Uses S3 as a managed Knowledge Base to power both Q Self-Service and Q Agent Assist (recommending responses based on live transcripts).

Amazon Contact Lens

Observability Layer

Provides real-time speech analytics, transcription, and triggers the ShopNova_Negative_Sentiment rule when customer sentiment drops to <= -3.

Amazon S3 & CloudWatch

Storage & Monitoring

S3 hosts the FAQ/Catalog assets and stores call recordings, while CloudWatch provides dashboarding (ShopNova-Monitoring), logging, and billing alerts.