Case Study

Automated Email Replies for a FinTech Firm Enhancing Customer Engagement and Resolution Time

Download the Case Study



Amazon SageMaker, Amazon Bedrock, Amazon S3, Amazon OpenSearch, Amazon Translate, Amazon Comprehend, AWS Lambda, Amazon API Gateway, AWS IAM, AWS CloudTrail, Amazon CloudWatch


Streamlined infrastructure management and the use of customer data for personalized email responses resulted in quicker query resolution and improved engagement.

About the Client

Kotak Mahindra Asset Management Company serves over 1 million investors across various schemes, striving to offer top-notch products and ensure consistent performance to achieve customer satisfaction while aspiring to be a responsible player in the mutual fund sector. 


End-to-end Gen AI Solutions

Streamlining the Deployment

Enhanced Insights

Informed Strategic Decisions

Quicker Resolution of Customer Queries

Automation of Customer Email replies

The Challenge

The client is an asset management firm and faces delays in responding to customer inquiries via email due to manual handling. To streamline this, they wanted CloudThat to help integrate AWS services, aiming for faster response times and enhanced user experience by leveraging customer data for relevant replies. 


  • The raw client data undergoes preprocessing to ensure quality, addressing inconsistencies, missing values, and irrelevant information. 
  • Preprocessing involves setting up an Amazon SageMaker instance, understanding the data, and scripting data acquisition, cleaning, transformation, and validation. 
  • Processed data is stored in Amazon DynamoDB, serving as the customer data source for the model. 
  • Two automated flows are created using Power Automate to retrieve newly arrived emails and reply to them. 
  • Amazon API Gateway integrates with AWS Lambda to trigger the new mail arrival flow in Power Automate through an API. 
  • A validation layer in AWS Lambda verifies customer emails using PAN Number or FOLIO number against stored customer data in Amazon DynamoDB. 
  • The “Anthropic Claude v2” model is chosen for generating human-like text responses to customer emails. 
  • Parameters are set to optimize the model’s performance and reduce randomization and probability for text generation. 
  • An Amazon DynamoDB Table records previous conversations using the conversation ID of the email chain, enabling the model to find continuity and respond to continuous queries. 
  • AWS Lambda functions are configured to make API calls to the model for email response generation and processing before transmitting responses to the Power Automate reply flow through REST API. 

The Results

We implemented end-to-end Gen AI solutions utilizing Amazon serverless services, enhancing customer engagement through personalized email responses, streamlined query resolution, and human-like text generation, ultimately reducing infrastructure costs and improving operational efficiency. 

Download the Case Study

AWS Partner – Data Analytics Services Competency

Pioneering Data Analytics space by being an AWS Partner – Data Analytics Services Competency.

Learn more

An authorized partner for all major cloud providers

A cloud agnostic organization with the rare distinction of being an authorized partner for AWS, Microsoft, Google and VMware.

Learn more

A house of strong pool of certified consulting experts

150+ cloud certified experts in AWS, Azure, GCP, VMware, etc.; delivered 200+ projects for top 100 fortune 500 companies.

Learn more

Get The Most Out Of Us

Our support doesn't end here. We have monthly newsletters, study guides, practice questions, and more to assist you in upgrading your cloud career. Subscribe to get them all!