Login- Consulting
- Training
- Partners
- About Us
x
Banking and Financial Services
AWS Lambda, Amazon API Gateway, Amazon S3, Amazon Bedrock, Amazon CloudWatch
Enhanced Customer Service with AWS and Anthropic Claude v2 for Automated Email Responses
Kotak Mahindra AMC serves as the asset manager for a mutual fund, offering 261 schemes for different risk levels, mainly investing in AAA and AA-rated companies. As of 31st March 2024, the assets under management of the AMC exceed 3.81 lakh crores. Over 25.9 lakh investors are served across different schemes. The client aims to become a responsible player in the mutual fund space by offering best-in-class products and focusing on delivering consistent performance across all products to ensure customer satisfaction.
Accurate email replies
Reduction in query resolution time
Less manual input
The client was encountering difficulties in managing the high flux of incoming emails that is resulting in delayed responses to the customer’s inquiries. To streamline their email management process and enhance response times, the client aims to integrate an advanced GenAI model into their existing system that enhances customer satisfaction and engagement through personalized email replies using customers data.
• The raw data from the client contained inconsistencies, missing values, or irrelevant information. Hence, preprocessing steps are carried out to ensure the quality of the dataset.
• The preprocessing steps include setting up an Amazon SageMaker instance, understanding the data, and writing a script for data acquisition, data cleaning, data transformation, and validation.
• Once data preprocessing is completed, we store the processed data in Amazon DynamoDB, which serves as the customer data for the model.
• Building the automation to fetch the latest data from the customer database using the AWS lambda function.
• Using Power Automate, which enables us to create automated flows, two flows were created to retrieve newly arrived emails and reply to them.
• Amazon API Gateway is integrated with AWS Lambda to trigger the new mail arrival flow in Power Automate through an API.
• A validation layer was added in AWS Lambda to validate the customer email and verify the customer using PAN Number or FOLIO number using the customer data stored in Amazon DynamoDB.
• For text generation to respond to customer emails, we have chosen the “Anthropic Claude v2” model to generate human-like text in response to the customer’s email.
• Parameters are set to optimize the model’s performance and reduce randomization and probability for text generation.
• We have created an Amazon DynamoDB Table to record the previous conversation using the conversation ID of the email chain so the model can find the point of continuity and respond to the customer’s continuous queries using the previous conversation.
• Configured AWS Lambda function to make API calls to the model to generate the response of the email and process prior to transmitting responses to the reply flow in Power Automate through REST API.
We developed end-to-end Gen AI solutions using Amazon serverless services, automating customer email replies with personalized, accurate responses in 5 minutes, leveraging customer data for insights and improving engagement, and achieving 90% accuracy with Amazon Bedrock.
SHARE
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!
