Skip to main content
RAG Use Cases

​
Use Case 1: Digital Accountant

An AI agent that answers questions about a user’s financial data. The sample application is Syncronix, a financial data aggregation SaaS. RAG is integrated into Syncronix, enabling the Digital Accountant agent to handle complex financial queries.
  • Chat Assistant Interface: Users interact through a chat interface, where they can ask questions such as “What is the total revenue for the last quarter?” or “What is the company’s balance sheet?”
  • Data Retrieval and Aggregation: The Digital Accountant can retrieve data from various sources, including internal financial databases and external sources like currency exchange rates.
  • Complex Queries and Calculations: The agent can perform advanced calculations, such as summing revenues or calculating financial ratios, using data retrieved from the system.
  • Visual Data Representation: The chat assistant can generate graphs and charts, providing users with visual insights into their financial data.
By leveraging the RAG framework, Syncronix offers users an efficient way to analyze and interpret their financial data, automating complex data aggregation and visualization tasks.

​
Use Case 2: Personalized Learning Journeys

An AI agent designed to generate customized learning paths for users. The sample application is the Peak Educational Platform, which supports the Financial Wellness program. RAG is integrated into the Educational Platform, allowing the Learning Journey agent to craft personalized educational experiences.
Please note: Financial Wellness is a software currently in production, but it uses a previous version of the RAG framework. We will update Financial Wellness by the end of 2024 to use the latest version.
  • Syllabus Generation: The RAG framework uses a static knowledge base within the Educational Platform to generate a structured syllabus. This syllabus includes lessons, quizzes, and scenario games tailored to the user’s needs.
  • Course Hyperpersonalization: Based on the generated syllabus, the agent personalizes the learning journey by selecting the most relevant material and adapting it to the user’s progress, preferences, and goals. Hyperpersonalization adjusts content in real time, providing an even more tailored experience by considering finer details, such as user engagement patterns and past performance.
  • Gamification Elements: The framework incorporates gamification, adding points, badges, and other motivational elements based on the user’s performance within the course.
  • Real-Time Adaptation: The learning journey dynamically adjusts as users progress, focusing on areas that need reinforcement or exploring new topics based on user achievements.
Through the RAG framework, the Peak Educational Platform delivers a hyperpersonalized learning experience, helping users advance at their own pace with content that uniquely addresses their educational needs and preferences.

​
Use Case 3: Loan Assistant

RAG is not yet integrated into any banking product, but it is an example of how it could be used.This hypothetical use case demonstrates how the RAG framework could support banking products, providing users with accurate, transparent, and verified information for complex financial decisions.All necessary capabilities are ready for integration.
An AI agent specialized in answering questions related to loan products.
  • Context-Specific Knowledge Retrieval: The Loan Assistant agent uses the RAG framework to access a knowledge base containing details about loan products, including terms, eligibility criteria, and interest rates.
  • User-Friendly Query Handling: Users can ask specific questions, such as “What are the requirements for a mortgage loan?” or “What is the interest rate for a personal loan?”
  • Accurate and Contextual Responses with Citations: The RAG framework synthesizes the retrieved information, allowing the Loan Assistant to provide concise, relevant answers. Additionally, it displays the relevant parts of documents that support each answer and includes citations, so users can verify the information and gain further context.