Download the case study

SolvPath: An AI-powered chatbot solution to assist E-Commerce customers

Category: E-commerce

Services: Gen AI Development, Cloud Architecture Design and Review, Managed Engineering Teams

  • 95% or more accuracy in understanding user queries by leveraging Amazon Bedrock
  • 90% accuracy and contextually relevant responses to user queries using RAG
  • 99.9% uptime and real-time user interaction using Amazon OpenSearch
  • 85% enhancement in the chatbot’s semantic understanding by integrating Amazon Titan
  • 60% reduction in manual customer support ticket resolution

About SolvPath

SolvPath is an AI-powered chatbot that aims to assist E-Commerce customers and end users with Frequently Asked Questions (FAQs). It uses the Large Language Model (LLM) capabilities to excel in natural language understanding and generation, ensuring that it comprehends user queries and provides contextually relevant responses to improve customer and user experience.


  • SolvPath wanted to ensure the chatbot understood all user queries, regardless of mistakes in spelling, grammar, or variation in sentence complexity, and generate contextual responses relevant to the user queries, considering the language and intent. 
  • The client wanted the chatbot to remain available to users 24/7 to respond to their queries. They also wanted to ensure real-time user interaction to offer a seamless and natural conversational experience with accurate and prompt responses to user queries. 
  • SolvPath also wanted to enhance the chatbot’s semantic understanding to generate context-aware responses by understanding the context and intent behind user queries. 
  • The client wanted to design an effective architecture for the chatbot that could handle user growth and a vast amount of user queries without compromising peak performance.
  • The client wanted to store and manage vast amounts of data, including FAQ databases and chatbot training data. They also wanted to ensure that the data stored is handled securely to safeguard sensitive user information and privacy.


  • Simform helped SolvPath create an AI-powered chatbot that assists E-Commerce customers and end users with FAQs to improve user experience. 
  • Our experts leveraged natural language processing using LLM capabilities to ensure the chatbot understood all user queries, irrespective of spelling or grammar mistakes.
  • We integrated Amazon Bedrock Claude-2 as the chatbot’s core language model to ensure it generates contextually relevant responses to user queries by understanding nuances. 
  • Our developers used Amazon OpenSearch to ensure the chatbot remains available 24/7 and responds to user queries in real-time with low latency. 
  • We also implemented Retrieval Augmented Generation (RAG) with LLMs using Amazon OpenSearch to provide accurate information with citations or references. 
  • Our team utilized Amazon S3 to ensure scalable and secure storage and management of the vast data, including FAQ databases and chatbot training data. 
  • We embedded Amazon Titan to refine the chatbot’s semantic capabilities, help it understand the intent behind queries, and generate more context-aware responses. 
  • Our knowledgeable developers utilized Amazon OpenSearch for easy setup, deployment, and management of large language models like Claude-2. 
  • We enforced stringent security measures such as encryption and access control to protect the privacy of sensitive information stored on Amazon S3. 
  • Our developers used scalable solutions like Bedrock Claude-2 and AWS OpenSearch that could accommodate user growth without compromising peak performance. 
  • We used LangSmith to continuously track and monitor the analytics related to various LLM models, such as token usage, LLM Performance, latency, etc.

Architecture Overview

Solvpath Chatbot Architecture

AWS Services

  • Amazon Bedrock: We used Amazon Bedrock as a foundational framework for building and deploying AI-powered applications. It also ensures AI models’ reliability, scalability, and performance and facilitates seamless integration with other AWS services.
  • Amazon Bedrock Claude-2: Our experts used Bedrock Claude-2 as the core language model for the chatbot to ensure it generates contextually relevant responses to user queries. It helps understand nuances in user queries and provides accurate information.
  • Amazon Titan: We used Amazon Titan to enhance the chatbot’s semantic understanding and generate more context-aware responses. It also helps the chatbot understand the intent behind user queries, leading to accurate and relevant responses.
  • Amazon S3: We used Amazon S3 to provide a scalable and secure storage solution for vital chatbot data such as FAQ databases and training data. 
  • Amazon OpenSearch: Our developers used Amazon OpenSearch to deploy and manage large language models like Claude-2 easily. We also used OpenSearch to enable real-time user interaction and provide timely and accurate responses to users. 
  • AWS EC2: Our AWS experts used EC2 to host the chatbot app and provide computing power to process user queries and generate relevant responses. 
  • AWS Fargate: We used AWS Fargate to run and deploy the chatbot application as a container to ensure scalability and efficiency in resource allocation. 
  • AWS ECS: Our developers used AWS ECS to manage and scale containerized components of the AI-powered chatbot ecosystem.
  • Amazon RDS (PostgreSQL): We used RDS to store structured data related to a chatbot, such as user queries, interactions, logs, and feedback, to improve performance.

Related Case Studies

ONA dating - case study
Freewire - case study

Speak to our experts to unlock the value of Cloud!