FinCare AI — Customer Support & Sales Intelligence

FinCare AI is a reference open-source example showing how MemoryModel can be used to power multiple autonomous agents over a shared memory layer. The project demonstrates how long-term, structured memory can transform customer support conversations into actionable sales insights — without interfering with the user experience.

What this example shows

This example focuses on memory orchestration, not just retrieval. Specifically, it demonstrates how to:

• Share the same memory cluster across multiple agents.
• Combine MemoryModel based customer support with autonomous insight extraction.
• Persist structured commercial signals during conversations.
• Separate who talks from who observes.

Architecture overview

The system is composed of three main components, all connected to the same MemoryModel cluster:

1. Customer Support Agent

Answers user questions using Retrieval-Augmented Generation (RAG). It retrieves information from product documentation and user profiles, while storing long-term user preferences and contextual data.

2. Spy Node (SalesInsight)

Runs silently in parallel with the conversation. It never answers the user; instead, it observes messages and extracts structured sales signals, such as implied needs, sentiment, and potential upsell opportunities. These are written directly into memory.

3. Operator Dashboard

Reads only the structured memories generated by the Spy Node. It displays real-time sales insights to a human operator and scores leads based on estimated conversion probability.

Memory nodes used

The example uses multiple memory nodes, defined explicitly by the developer:

• AppKnowledge: Stores official documentation and product manuals ingested via batch upload.
• UserProfile: Stores persistent user-level information such as preferences, constraints, and past interactions.
• SalesInsight: A structured node designed to capture commercial signals inferred from conversations.

Note

Core Concept: All nodes are defined in nodes.txt and created explicitly. This highlights a fundamental MemoryModel principle: you decide what is memory-worthy, not the system.

Running the example

The full source code is available as an open-source project:

FinCare AI — GitHub Repository Explore the full source code for the Customer Support & Sales Spy orchestration logic.

To run the example locally:

1. Create a MemoryModel cluster.
2. Define the nodes using nodes.txt.
3. Ingest documentation into the memory layer.
4. Run the customer and operator applications in parallel.

Detailed setup instructions are available in the project README.