Nathan Lara
ProjectsExperienceRésuméContact
Selected Work

Projects

Five case studies in building and deploying AI — each written up as a problem, a solution, and what shipped.

01 AI Blocks An open-source visual programming environment for AI/ML pipelines — compose LLM, agent, RAG, vision, and fine-tuning steps as typed block graphs, then generate runnable Python. 1st place, vibeFORWARD. React · Vite · Python 02 M&A Deal Intelligence A deployed M&A intelligence platform for PwC — an agentic daily pipeline across 51 live sources with structured deal extraction, SEC financial enrichment, and an analyst dashboard. GPT-4o · LangChain · Next.js 03 AEGIS Browser-native multimodal threat detection — motion-gated Claude Vision with a voice/gesture confirmation flow and simulated dispatch. 1st place, Grayscale Hackathon. Claude Vision · WebRTC 04 UN-LEX Enterprise legal AI adopted by the UN Office of Legal Affairs — query 9,000+ UNDT/UNAT tribunal cases with paragraph-level citations, deployed inside Microsoft Teams. Copilot Studio · Azure AI 05 AI Wealth Strategy A Board-level strategy case for a RAG-grounded wealth assistant — $9.6M NPV and Year-1 break-even across 10,000 Monte Carlo scenarios, with a standing bias-audit protocol. Azure · RAG · Monte Carlo