This AI fact-checking system, built with LangGraph, dissects text into verifiable claims, cross-referencing them with real-world evidence via web searches. It then generates detailed accuracy reports, ideal for combating misinformation in LLM outputs, news, or any text.

The official implementation of "RouteExplainer: An Explanation Framework for Vehicle Routing Problem" (PAKDD 2024, oral)

An interactive dashboard for exploring mathematical research trends on arXiv

Automated LLM-based Prompt Engineering for Structured Data Processing

RAG enhances LLMs by retrieving relevant external knowledge before generating responses, improving accuracy and reducing hallucinations.

Powerful framework for building applications with Large Language Models (LLMs), enabling seamless integration with memory, agents, and external data sources.

CareConnect uses state-of-the-art large language models (LLMs) to provide rapid, reliable medical guidance. This project addresses increasing wait times and health misinformation, offering timely assistance and supporting informed decision-making to alleviate the burden on the healthcare system.

Semantic Retrieval Engine for Contrasting Ideas and Opposing Viewpoints.

AI-powered stock analysis and investment recommendation app using CrewAI agents, Gemini LLM, DuckDuckGo Search and real-time market data. Generates comprehensive reports, news summaries, and buy/hold/sell advice.

A Streamlit tool for analyzing Information Security Policies by classifying keyword occurrences as "Actionable Advice" or "Other Information" to measure policy effectiveness through the "Keyword Loss of Specificity" metric.

Master’s Thesis at TU Vienna, assessing state-of-the-art LLMs for automating BPO tasks. Features a custom Action Research-Based Compliance Testing (ARCT) framework, exploring LLM capabilities, context impact, and limitations in optimizing complex workflows.

Successfully developed an LLM application which generates a summary, a list of citations and references and response to a user's query based on the research paper's content.

Successfully developed an interview preparation guide using Langchain which can effectively guide users in their interview preparation process and job search journeys by providing valuable insights and feedback regarding their performance. It generates a comprehensive list of questions pertaining to a user query as well.

An interactive Jupyter Notebook demonstrating AI agent collaboration using CrewAI. This project explores how multiple AI agents can research, generate content, and automate workflows through task orchestration.

ScholarLens analyzes research papers using RAG with AI models from OpenAI, Anthropic, and Google. It identifies research gaps, assesses novelty, extracts key concepts, visualizes citations, and enables natural language queries of academic content. Features include PDF processing, arXiv/Semantic Scholar integration, batch processing, and intelligent

Medquery-assistant is an intelligent medical chatbot that supports natural, context-aware conversations through a sleek web interface, featuring nested query handling, real-time responses, and a user-friendly design.

Successfully developed an interview preparation guide using Langchain which can effectively guide users in their interview preparation process and job search journeys by providing valuable insights and feedback regarding their performance. It generates a comprehensive list of questions pertaining to a user query as well.