Skip to content

Introduction

Converses is Fluid Attacks’ AI-powered assistant product which is designed to answer questions about Fluid Attacks in general. It’s a Retrieval-Augmented Generation (RAG) based solution, which means it uses actual documentation along with advanced AI to provide context-aware responses.

Public Oath

  1. Converses can provide users with relevant answers to questions about Fluid Attacks by retrieving the most up-to-date information based on our knowledge base.
  2. The assistant does not currently store or use any real customer data, focusing on delivering helpful responses based on Fluid Attacks’ documentation.
  3. Fluid Attacks is committed to constant learning and enhancement, refining Converses’ retrieval and response capabilities by looking for new stack that better aligns with such goals.

Architecture

Architecture-light Architecture-dark

Converses architecture is focused on using Fluid Attacks’ detailed knowledge base to enable AI-based assistants to help users with swift and relevant responses to their questions about the company. This process is made possible by the following points:

  • Jobs are programmed to run periodically using AWS batch. These jobs use Zoho Desk’s API to retrieve Fluid Attacks’ documentation and send it to OpenAI’s vector stores. Thus, the assistants are ready for user questions.
  • AWS Lambda is used to enable a smooth communication between the user and OpenAI assistant.
  • DynamoDB is used for storing the conversation unique identification which allows the assistant to remember all the messages of the conversation.
  • Google Chat is utilized for the internal use of the assistant by Fluid Attacks, however any other application can use the endpoint to communicate with the assistant with proper authorization.

Data Security and Privacy

Converses does not use any Personally Identifiable Information (PII) from Fluid Attacks’ customers. The information used is all the documents present in Fluid Attacks knowledge base which can be accessed by anyone looking for information about Fluid Attacks’ services and usage of its platform.

Contributing

Please read the contributing page first.