What is Shashwat Prakash's area of expertise?

Shashwat Prakash is an AWS Conversational AI & Contact Center AI Engineer specializing in enterprise Voice AI, IVR Automation, Amazon Connect, Generative AI applications, RAG Pipelines, AI Agent systems with Tool Calling, Nova Sonic real-time voice AI, and Prompt Engineering. He has 6+ years of experience delivering production-grade AI solutions for enterprise clients.

Which AWS services does Shashwat Prakash specialize in?

Shashwat Prakash specializes in Amazon Connect (IVR & Contact Center), AWS Bedrock (Generative AI & LLM), Amazon Lex (NLP & Chatbots), Nova Sonic (Real-time Voice AI), Amazon Q in Connect, AWS AgentCore (MCP Server), AWS Lambda (Serverless), AWS DynamoDB, AWS API Gateway, AWS S3, AWS CloudFront, AWS Cognito, and AWS EventBridge.

What is Shashwat Prakash's experience with IVR and Voice AI?

Shashwat Prakash has extensive experience as an IVR AI Developer and Voice AI Engineer, building production Amazon Connect IVR flows, Nova Sonic real-time conversational voice AI, AI voicebots, Speech-to-Text pipelines, Text-to-Speech systems, and full contact center automation solutions for enterprise clients at PwC US and Genpact India.

Does Shashwat Prakash offer Generative AI and RAG Pipeline development?

Yes. Shashwat Prakash is an experienced Generative AI Engineer and RAG Pipeline Developer. He builds retrieval-augmented generation systems, vector database integrations, semantic search, LLM-powered applications, Prompt Engineering frameworks, and Agentic AI systems with Tool Calling using AWS Bedrock and other foundation models.

Is Shashwat Prakash available for hire as a Conversational AI consultant?

Yes. Shashwat Prakash is available as a Conversational AI Consultant and AWS Contact Center AI Engineer for enterprise projects. He can be reached through the contact form at shashwatprakash.com for consulting, collaboration, and full-time opportunities.

How can a business rules engine be replaced by an AI chatbot?

Instead of hardcoding rules into application logic, business rules are stored in a database (DynamoDB in this case) and surfaced dynamically through a conversational AI layer (Amazon Lex + Lambda). Admins edit rules via the existing admin console; the chatbot reads the same database at runtime. This means rule changes take effect instantly — no redeploy, no downtime.

What is DynamoDB DAX and how does it reduce latency?

DynamoDB Accelerator (DAX) is an in-memory caching layer for Amazon DynamoDB that delivers microsecond read latency. In this project, frequently accessed business rules are cached in DAX, so Lambda functions retrieve them in under 1 ms instead of making a full DynamoDB read. This was the primary driver of bringing end-to-end response time under 2 seconds.

How does Amazon Lex handle dynamic business rules at runtime?

Amazon Lex handles intent detection — understanding what the customer is asking. Once an intent is identified (e.g., 'check my eligibility'), the associated Lambda fulfilment function queries DynamoDB for the current rule set, evaluates the customer's input against it, and returns the appropriate response. The entire rule evaluation happens server-side in the Lambda function, making the Lex bot itself stateless and rule-agnostic.

Can the same rule engine serve both voice IVR and web chat?

Yes. Amazon Connect handles voice calls and web chat via its omnichannel contact flows, both of which funnel through the same Amazon Lex bot and Lambda backend. The rule engine is channel-agnostic — a rule updated by an admin is immediately available across voice IVR, web chat widget, and any other channel connected to the same DynamoDB source of truth.

PwC USAug 2024 – Sep 2025AWS Conversational AI & Contact Center Engineer2 min read

Business Rules Engine Migrated to AI-Powered Chatbot on AWS

Replaced a rigid web admin console with a real-time conversational layer — no redeployments needed.

The Business Problem

A legacy web-based Business Rules Admin Console required code deployments for every rule change, causing delays and operational overhead. There was no self-service channel for customers — all queries were handled by live agents reading from the same static rule set.

Solution & Technical Overview

Migrated a business rules Web Admin Console to an AI-powered chatbot using Amazon Lex, Lambda, DynamoDB, and Amazon Connect. Designed a real-time architecture where admin-edited business rules and text prompts are instantly available to customers via voice and chat — no deployment required.

The solution uses Amazon Lex for intent detection, AWS Lambda for dynamic rule resolution, Amazon DynamoDB (with DAX caching) as the shared source of truth, and Amazon Connect for omnichannel access across voice and web chat. The existing admin console was kept intact; a conversational layer was added that reads from the same database. When an admin publishes a rule change, the IVR flows reflect it within seconds.

Response latency was brought under 2 seconds through Lambda caching and DynamoDB DAX, enabling real-time, responsive customer interactions at scale.

Key Outcomes & Results

Response latency under 2 seconds via Lambda caching and DynamoDB DAX
Zero-deployment rule updates — admin publishes once, IVR reflects changes in seconds
Omnichannel support: voice (Amazon Connect) and web chat from a single rule engine
Preserved existing admin console; conversational layer added non-intrusively
Intent-driven architecture via Amazon Lex for accurate rule resolution

Technologies & Skills Used

Amazon ConnectAmazon LexAWS LambdaAmazon DynamoDBDynamoDB DAXAmazon S3Amazon SESContact Center as a Service (CCaaS)

Frequently Asked Questions

Written by

Shashwat Prakash

AWS Conversational AI & Generative AI Developer with 6+ years building enterprise contact center solutions, voice AI agents, RAG pipelines, and AI-powered applications on AWS. Currently at PwC US, previously at Genpact and Agenty Analytics.

LinkedIn GitHub Book a Free Consultation

Voice AIAmazon Connect