About the Client: Fibe
Fibe, formerly EarlySalary, is a leading consumer lending app in India. It focuses on young professionals underserved by traditional lenders. Its mission is to create a financial ecosystem supporting mid-income groups’ aspirations. Offering short-term cash loans, personal loans, and Buy Now Pay Later plans, Fibe aims to enhance customer lifestyles and affordability at scale.
Industry:
FinTech
Offering:
GenAI Solution
AWS Services
Amazon S3, Amazon Bedrock, Amazon API Gateway, AWS Lambda, Amazon DynamoDB, Amazon EKS, Amazon VPC, Amazon EC2, Amazon ECR
Business Need:
Customer was using traditional dialogue driven chatbot to answer the loan related queries. The queries range from simple FAQ to customer specific questions related to payment due dates etc. Because the customer was using dialogue driven approach, lots of questions from end users were restricted to receive answers only for predefined questions. This caused an increase in the number of calls to their call center which in turn increased the operational cost. The customer was looking for a context based free flow chatbot to interact with the end users.
Implementation:
To address the identified shortcomings and enhance the chatbot’s capabilities, a GenAI-based solution is proposed. This solution will integrate several key features to ensure improved performance and adaptability:
- Develop a centralized system to manage FAQ sheets, APIs, and other business documents, streamlining information access and updates.
- Utilize advanced LLMs to generate tailored responses based on user queries, enhancing accuracy and usefulness.
- Leverage existing data for the chatbot to engage in natural, personalized conversations with users, improving user experience
- Incorporate a Retrieval Augmentation & Generation system to dynamically retrieve real-time data, enriching chatbot responses with up-to-date information.
- A robust data pipeline was established to manage FAQs stored on Vector DB deployed on Amazon EKS, ensuring continuous updates without disrupting chatbot functionality.
- Another pipeline was created to interact with Customer APIs, retrieving crucial details such as payment dates and due dates specific to a user.
- The switch from Claude 2.1 to Claude Instant significantly improved response times, enhancing overall user experience.
- Parameter tuning and the addition of XML tags and placeholders within prompts refined response generation, leading to more accurate and contextually relevant answers.
- A bespoke logic was developed to enable agents to discern whether a query should be addressed through FAQ or necessitated a customer API call, resulting in optimized response times.
- Administrators were provided with parameter tuning options through API headers, granting control over parameters such as Top P, token length, and temperature for tailored chatbot responses.
Reaping Rewards:
- With rapid response generation clocking in at an impressive 2-3 seconds, users experienced minimal wait times, significantly enhancing overall user experience.
- The enhanced chatbot with its accurate responses for the end users, resulted in 18% reduction in the number of calls made to the call center than before, hence contributing to saving operational cost.
- Implementation ensured better maintenance of the knowledge base and an easy-to-update pipeline, further optimizing resource utilization, and reducing operational overheads for the customer.
