SQL Server

AI academic Q&A chatbot for HUSC students, built with Flask, FastAPI, SQL Server, and Docker. It uses hybrid RAG with BGE-M3 embeddings, Qdrant/FAISS vector search, BM25 retrieval, RRF fusion, reranking, and Gemini to answer regulation questions with structured PDF parsing, citations, caching, intent detection, and rate limiting.

An AI-powered Hospital Triage System built with Flask, Python, SQL Server, HTML, CSS, and JavaScript. Features secure authentication, AI-assisted patient triage, JAANO medical chatbot, patient management, dashboard analytics, PDF/Excel reporting, and a responsive hospital-themed interface.

An AI-Powered Resume Screening System built on an enterprise ASP.NET Core Web API with .NET 8 and C#. It features an in-memory PDF text extraction engine using PdfPig and a code-first Microsoft SQL Server architecture. It parses resume workflows and aligns candidate metrics against specific job matrices flawlessly.

Trust-audited Voice-of-Customer risk scorecard — SQL Server vector search with measured precision/recall, not assumed. MS SQL AI Promptathon 2026.

An intelligent FinTech RPA agent built with Python and Streamlit to automate merchant dispute triage. It uses a dynamic decision engine to evaluate fraud risk, executing instant auto-refunds (STP) or routing anomalies to a Human-in-the-Loop portal while streaming live compliance logs to SQL Server.

End-to-end FMCG salesman performance analytics system — SQL Server data warehouse, Power BI dashboards, Excel VBA report automation, and Claude-powered executive summaries, built on 2 years of simulated UAE field-sales data.