Hands-on A2A (Agent-to-Agent) protocol project: 3 interoperable agents (trending + analyzer + host) orchestrated via JSON-RPC using Google ADK.

Streamlit chatbot for Fetii Austin rideshare analytics using Rule-based queries + RAG (MiniLM embeddings + SQLite)

Hands-on customization of DeepAgents (LangGraph/LangChain): a Research Agent demo (Python + notebook) with planning, subagents, tool loops, and report writing.

🚀 Hands-on exploration of GraphRAG with Neo4j — building and comparing retrievers (Vector, Vector+Cypher, Text2Cypher) and wrapping them as conversational agent tools (Schema, Hybrid, Text2Cypher).…

This repository documents my learning journey from the AWS Data-Driven Everything workshop on Mastering Enterprise Gen AI: Building production applications with Amazon Bedrock.

Image captioning model using EfficientNetB0 as encoder and a custom Transformer decoder, trained on the Flickr30k dataset. Demonstrates full model architecture, preprocessing, and BLEU-based evalua…

A Gemini-powered explainable AI assistant that analyzes and interprets anomalies in IoT power signals using RAG, few-shot prompting, and embeddings. Built during the 2025 Google GenAI Capstone.

A Streamlit-based semantic search app for movies built with Pinecone, Hugging Face, and LLMs (Hackathon6 Project)

Repo from AWS GenAI workshop—build cost-efficient agentic LLM systems using SageMaker, Bedrock, and Strands.

AI-powered profile matching agent using structured Excel data and unstructured LinkedIn-style resumes. Combines dynamic prompting and hybrid filtering with Gemini LLM for expert recommendation. Bui…

My problem solving questions