Projects

AI Enabling Company for regulated organizations in LatAm: training, custom skills, multi-agent systems.

Infrastructure for rigorous investment research in LatAm: software, analytics, on-demand research and quantitative training.

Cross-sectional risk-on/risk-off classifier from the realized return-vs-volatility slope across 64 country index series — segmented into 10 cuts and validated against FRED proxies.

Multi-agent mortgage underwriting demo — six LangGraph agents collaborate to render APPROVED / CONDITIONAL / DENIED with risk score and decision memo. Live SSE stream on Hugging Face Spaces.

Educational platform that centralizes knowledge through knowledge graphs and designs lifelong study trajectories spanning university and career.

A family of vertical agents that materialise the «multi-agent systems» theme into concrete builds: equity research, LinkedIn writer, credit underwriting.

Reusable Obsidian-vault scaffold and Claude Code skill set for running a structured personal knowledge base.

Multi-asset portfolio optimization engine — mean-variance, risk parity, HRP, Black-Litterman, CVaR — with a Streamlit UI and CLI.

Python toolkit for Nelson-Siegel yield-curve modeling on Treasury and TIPS curves, with a single-page browser app.

Solow-Swan growth → CAPM → Gordon Growth → Monte Carlo: move the sliders, watch the justified forward P/E update in real time.

LangGraph agent with Claude Sonnet 4.6 + RAG that produces institutional-grade research briefings on AI-sector companies.

Multi-agent system that discovers, evaluates, and ranks arXiv papers, then generates LinkedIn posts from top findings.

Plugin-distributable knowledge base of role-based AI agents, framework skills, and engineering process discipline.