Project Case Study

DNDMind AI Copilot

Full-stack AI Dungeon Master copilot with RAG, memory retrieval, structured outputs, tool calling, and deterministic evaluation workflows.

Gemini 2.5 Flash Next.js ASP.NET Core FastAPI PostgreSQL pgvector Docker RAG

Demo GitHub

DNDMind command center encounter workspace

Problem

Tabletop role-playing sessions create a lot of changing context: character state, campaign memory, rules references, prior decisions, and narrative continuity. A simple chatbot can respond creatively, but it does not reliably preserve memory, retrieve relevant context, or keep outputs structured enough for repeatable gameplay support.

Solution

Built a full-stack AI Dungeon Master copilot using Gemini 2.5 Flash for generation, plus application workflow, backend APIs, retrieval, memory, and structured AI responses. The system uses a Next.js interface, ASP.NET Core services, FastAPI inference support, PostgreSQL with pgvector, Docker Compose, embeddings, memory retrieval, tool/function calling, and deterministic evaluation workflows.

Proof

Implements RAG and vector retrieval through PostgreSQL + pgvector instead of relying only on prompt history.
Separates frontend, backend, inference, and database responsibilities across a multi-service Docker Compose setup.
Uses Gemini 2.5 Flash with structured AI outputs and tool/function calling patterns to make responses easier to validate and integrate.

Result

The project demonstrates production-style AI application architecture beyond a prompt-only demo: persistent memory, retrieval, structured outputs, backend orchestration, and evaluation-ready workflows.