Beyond the Hype: Real-World Lessons and Insights from Working with Large Language Models at Mercado Libre
Mercado Libre lacked a centralized system to answer developer questions about internal tooling, half of their 4,000 productive data tables had no adequate documentation, and their internal expert-booking platform required structured manual input that natural language queries could simplify.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Developer queries RAG system
Users pose questions to a Question-Answering system that generates personalized answers from relevant documents.
Tools used
Function Calling
Outcome
LLM-generated table documentation was well-received by 90% of stakeholders with only minor adjustments needed, documentation gaps were iteratively identified and addressed to improve RAG accuracy, and function calling enabled structured extraction from natural language booking queries.
What failed first
The initial RAG prototype built with Llama Index hallucinated responses when documentation gaps existed, and the documentation generation produced output that 10% of stakeholders did not accept, citing missing structure and internal acronyms.