Artificial Intelligence Machine Learning Data Science Core Python

PDF Data Extraction at Scale: When to Trust an LLM

FORMAT: WorkshopLEVEL: All levels LANGUAGE: Spanish

LLMs read chaotic documents like no one else, but when money or legal liability is on the line, the question is not "can it?" but "when should I trust it, and how do I catch it when it is wrong?". In this hands-on workshop we build, step by step, a real extraction pipeline for legal PDFs with variable formats, orchestrated with Airflow, using a hybrid extractor (deterministic + LLM) and deterministic guardrails in Python. You will leave with a framework for deciding which tool to use and a reliable pattern for production environments.

Workshop requirements

https://github.com/factoredai/factored-pycon-workshop-2026-data-engineering

Speaker

Douglas Ardila Garcés

Engineering Manager & Data engineer @ Factored

Engineering Manager & Data engineer with strong experience in architecting, developing, and maintaining highly reliable analytical data infrastructure and data pipelines that move data in and out to enable better decision-making and create business value primarily within the Fintech sector. Proficient in AWS, Google Cloud, Snowflake’s data ecosystem, Airflow, dbt, and other tools. Cares about other team members and is invested in empowering them to grow personally and professionally. Works cross-functionally with stakeholders (software engineers, data scientists, business analysts, etc), to ensure that the data infrastructure meets their evolving needs. Currently, working as a Data Engineering Manager at Factored (one of the fastest-growing data science companies in the Americas, we build very high-caliber teams of rigorously vetted data scientists for top US companies).

View speaker

Want to know more?

Join PyCon Colombia newsletter and get a complete overview of our events, speakers and community participation.