I write about data, AI and innovation — what I learn transforming organizations.
20 years building systems, leading teams, and working with data in changing environments. At Santander, I drive innovation and better data management; at ITBA, I teach Data Management and coordinate the AI Agent Developer program.
I care about turning technology into solutions that actually work: better-governed data, AI applied with judgment, and teams that can move even when the context changes. I write here about those tests, lessons, and decisions. If that resonates, subscribe below.
§ Recent writing
full archive →- Aug 2026Innovation
"Nothing to Ask"
ABI is an AI platform designed to mentor students outside the classroom by backing up its answers, proposing tailored learning paths, assessing understanding, and tracking student growth. This post details its origin story, why the project's key breakthrough was human rather than technical—students actually preferred being guided over just getting answers—how user questions reshaped the syllabus, and why the teacher remains irreplaceable.
- Jul 2026Data
Agentic Workflows in Production: Where Teams That Copy YouTube Tutorials Fail
Why agentic AI systems that work perfectly in demos collapse in production. Learn the engineering gaps that YouTube tutorials never cover—state management, error handling, human oversight, and cost control.
- May 2026Data
Why MCP Servers Are Going to Kill Traditional Data Pipelines (And That's a Good Thing)
MCP servers are replacing traditional data pipelines for real-time, context-aware applications. Learn why latency, rigidity, and maintenance costs make Airflow-style orchestration obsolete for AI agents while batch processing remains essential.
- May 2026Innovation
From REST to MCP: How AI Protocols are Changing Architectural Decisions in Startups
This article discusses the shift from REST to MCP in AI architecture and its implications for startups, with real-world examples.
- Apr 2026Data
The Data Quality Metrics You're Using Are from 2020. Here's Why Your Pipeline is Broken
Exploring why traditional data quality metrics are insufficient for modern AI applications and suggesting practical steps to improve data quality.
One idea a week, no noise.
Every Sunday I write a short note on data, AI and innovation. Things I learn teaching, managing teams, and building. No clickbait, no sponsors.
§ Projects
see all →
Data Modeler
A web tool built for ITBA's Data Management course: collaborative logical and physical modeling, instructor validations, and DDL generation for PostgreSQL and SQL Server.
ABI — Academic Brain Intelligence
AI-powered learning platform combining RAG-based tutoring, guided learning paths, adaptive assessments, and tools for instructors.
Transport companies management
Smart transport operations for ART providers: trips, drivers, billing, and insurer imports in one platform with real-time traceability.
Medical centers management
End-to-end management system for medical centers: appointments, clinical records, insurance billing, services, and operational reporting.
Payroll Laravel
End-to-end payroll and HR system for a medical center. Salary calculations, payslips, vacations, leave, and accounting reports. Three years in production.
Cupon3D / NextCupon
E-commerce for discount coupons and products. Frontend, backend, payment gateway, admin panel, and in-store coupon validation system.
Applied AI, with data and governance.
I help companies move from AI pilots to usable solutions: private RAG, agents over internal documentation, process automation, and governance criteria to operate with confidence in regulated environments.