USP – Educational RAG Application
Retrieval-Augmented Generation application for Universidade de São Paulo enabling intelligent question-answering for educational content.
Context
USP needed intelligent system allowing students and faculty to interact conversationally with vast academic materials, lecture notes, and research papers.
Challenge
Building accurate question-answering system with document processing pipelines, semantic search, and optimized retrieval for educational queries.
Solution
Implemented LangChain with large language models and vector databases (Pinecone/Weaviate). Built document processing with AWS Textract and React-based natural language search interface.
Technology Stack
ai
processing
search
frontend
Impact & Results
Intelligent question-answering with conversational interaction for educational queries
Document processing pipelines for academic materials and research papers
Advanced embedding strategies improving response relevance by 40%
Natural language search interface for students and faculty
Technologies
Links
More Projects
Aegis Protocol – AI Agent Accountability Layer
Lead Developer
On-chain accountability layer for AI agents built at ETHGlobal Open Agents (Ghent, May 2026). Any agent can prove what it decided, why it decided it, and face consequences if it was wrong — using 0G Storage, Gensyn AXL mesh, ENS CCIP-read, and KeeperHub automation.
View ProjectProduction URL Shortener – MLH PE Hackfest 2026
Production Engineer
Production-grade URL shortener built for the MLH Production Engineering Hackathon, demonstrating SRE practices: horizontal scaling, Redis caching, observability, load testing, and incident runbooks.
View ProjectInterested in similar work?
Let's discuss your project requirements