Mario Pérez

@davidalvarezdlt Zinco AI 😉

Querida red: conocéis a directivos de gestorías de buen tamaño? Sigamos gestorías que facturen varios millones al año. Cualquier ayuda es bienvenida ✌️

Key design decisions: sanitize_text() normalizes whitespace, case, accents Inner COALESCE converts NULL → empty string Outer COALESCE on CONCAT handles all-NULL rows to_hex() converts binary MD5 to readable string NULL-safe hashing = consistent results.

MD5(COALESCE(CONCAT( COALESCE(sanitize_text(column1), ''), COALESCE(sanitize_text(column2), ''), COALESCE(sanitize_text(column3), '') )))

Content-addressable deduplication at scale: MD5 hash all columns (minus metadata) → find hash collisions → save duplicates to _log table → keep one record. Implemented as BigQuery stored procedures. Track everything, delete nothing permanently. Easy rollback if needed.

The AI doesn't replace human judgment - it triages at scale. Humans focus on the 5% that truly needs expertise, not the 95% that's tedious pattern matching. This is the future of data cleaning: semantic understanding + programmatic validation + comprehensive audit trails.

Traditional ETL: Write 50+ regex rules, maintain edge case dictionary, manual QA team reviews thousands of records. LLM-powered ETL: One prompt template, automatic fuzzy matching, quarantine pattern for edge cases, 95%+ automation rate

Using LLMs for data standardization at scale: Send messy province names to Claude with an official list → get back a mapping dictionary → validate programmatically → quarantine unmappable records to separate tables.

AGI?

Un gran parte del revenue de la compañía proviene de vender datos a aseguradoras. Una demostración más de la importancia del data en este sector.

Interesante entrevista sobre Codeoscopic, compañía que ha creado varias soluciones SAAS en el ecosistema como avant2, bcover, versus y tesis.