Solution available at: github.com/aws-samples/generative-ai-amazon-bedrock-langchain-agent-example
This technical solution guide provides step-by-step instructions for building Generative AI Agents using the powerful combination of Amazon Bedrock, Amazon Lex, and LangChain. Generative AI Agents are capable of producing human-like responses and engaging in natural language conversations by orchestrating a chain of calls to Foundational Models and other augmenting tools based on user input.
This sample creates a Generative AI-powered Financial Services Agent that can assist users with finding their account information, completing a loan application, or answering any natural language question. Instead of only fulfilling pre-defined intents through a static decision tree, we use an Anthropic Claude Foundational Model hosted on Amazon Bedrock and customer proprietary data stored on Amazon DynamoDB and Amazon Kendra to provide dynamic and improved responses to the user on each interaction.
The brains of our Agent are wrapped into a single AWS Lambda function, which allows our bot to act as a LangChain ConversationalAgent with the ability to process user input, index on previous chat history for contextual generation, and perform actions like accessing proprietary data stores, querying a Foundational Model, or selecting from a set of AI-driven tools to fulfill the user’s intent.
This solution is intended to act as a launchpad for developers to create their own personalized conversational agents for various applications, such as chatbots, virtual assistants, and customer support systems.
![](https://i.ytimg.com/vi/bv4XV7epeik/maxresdefault.jpg)