Raul Rodriguez

About

I am Raul Rodriguez Lopez and I have spent more than 12 years getting my hands dirty with data. I did not arrive at Artificial Intelligence because it was trendy — I arrived because after a decade moving millions of records by hand, designing ETLs, migrating banking cores, and building highly complex pipelines, I understood there was a radically better way to do things. My path started from the deepest level of data: I migrated the entire core of major products with DataStage, built data warehouses and dimensional models for the financial sector at companies like Banco Popular, Banco de Bogota, and Corredor Empresarial, automated ETL processes with Spark on AWS, and designed data architectures at Colfondos. Then I spent 3 and a half years at Banco de Bogotá, where I scaled from Data Engineer Lead to DataOps and MLOps Manager — leading teams, managing cloud budgets, implementing CI/CD, and taking data culture to another level. Today I am Technical Lead at Mercado Libre, one of the largest tech companies in Latin America. I design multi-cloud architectures, build multi-agent systems with Generative AI using LLMs, ADK, LiteLLM, and Model Context Protocols (MCPs), and lead research into new technological capabilities for the business. But what truly transformed me was not a promotion — it was a mindset shift. I adopted an AI-First philosophy: if a task can be enhanced, delegated, or automated with AI, there is no reason to do it the traditional way. That mindset led me to create NORTH, a methodology I have been iterating in real production, where Claude is not a chatbot I ask questions to — it is a copilot that maintains the context of my projects, proposes architectural decisions, manages backlog, and synchronizes the state of everything I build. I develop custom skills, automate flows with agents, and every day I find a new way to amplify what I can do as an engineer. This is my first time as a speaker and I am not afraid to say it. I come with something no veteran speaker has: a real transformation story, from moving data with shell scripts in 2011 to orchestrating intelligent agents in 2026. I am not here to talk theory — I am here to show how a Colombian engineer, trained at SENA and Universidad Panamericana, came to lead AI at Mercado Libre by adopting a mindset anyone in this room can replicate. If you think AI is only for Silicon Valley, I am proof that you are wrong.

Workshop

Artificial Intelligence

NORTH: Claude as a Real Copilot

FORMAT: WorkshopLEVEL: All levelsLANGUAGE: Spanish

We all use AI to program. Few use it well. Most developers interact with Claude or any LLM as if it were Google with superpowers: they ask a question, receive an answer, copy and paste, unstructured prompts. The next day, the AI has no idea who you are, what project you are working on, or why you chose PostgreSQL over MongoDB last week. Every session starts from zero. Every time you re-explain the same thing. And the result is brilliant answers that do not know your code. How serious is this? I measured it. I asked Claude exactly the same thing — "give me the complete project context" — with and without methodology. Without structured context, Claude detected 3 of 5 team members, found 3 different versions of the project without knowing which was real, could not identify technical debt, and had no idea about the current sprint. With NORTH, the answer was precise: complete team with roles, correct canonical version, 3 technical debt items with severity, defined sprint with priorities, and pending PR to merge. Usefulness score: 7/7 with NORTH vs 2.5/7 without it. Same tokens. Same cost. The difference is not money — it is useful information vs noise. What if with a single command — /north — Claude knew exactly where you left off and what comes next? That is NORTH. A methodology that turns Claude into a real development copilot. Not a chatbot that answers questions — an agent with live memory of your project.

Raul Rodriguez

Technical Lead @ Mercado Libre

View talk