Ai-engineering

Published on
April 20, 2025
Model Context Protocol (MCP) in Practice
llms agents model-context-protocol ai-engineering
MCP is an open protocol for connecting LLM applications with external data sources, tools, and systems. This project implements an MCP Server for the NewsAPI, allowing to easily perform retrieval and analytics on news articles with frontier models.
Published on
December 19, 2024
MINERVA - A Multi-Agent LLM System for Digital Scam Protection
llms agents function-calling ai-safety autogen rdi-berkeley ai-engineering
As reported by the FBI IC3, digital scams inflict devastating impacts on our society. In this project, developed for RDI Berkeley LLM-Agents Course (CS294/194-196), I built a multi-agent system with AutoGen to help users identify scam attempts. This agentic solution achieved higher accuracy compared to a prompt baseline (88.3% vs. 69.5%).
Published on
September 9, 2024
Enhancing RAG Reasoning with Knowledge Graphs
llms rag embeddings Knowledge-graphs langchain neo4j ai-engineering
Published on
October 20, 2023
Function Calling & In-Context-Learning in OpenAI
llms rag function-calling in-context-learning openai ai-engineering

Model Context Protocol (MCP) in Practice