Live · SaaS · Tools · Agentic
Verificaa.com
Built because fraud in Latin America is common, and foreigners had no way to check who they were dealing with.
Founder, architecture, data pipeline, AI
- Category: SaaS
- Released: 2021
The problem
Fraud is common across Latin America, and foreigners doing business there have almost no way to check who they are dealing with. The data exists — police records, attorney general filings, business registries — but it is scattered, inconsistently formatted, and effectively unsearchable.
What it does
Verificaa normalises that data and puts a single lookup in front of it. Enter a person or a business, get back what the public record actually says.
An AI layer sits on top to flag patterns a human would miss: identities that appear across unrelated filings, businesses registered days before a transaction, documents that do not reconcile.
Engineering notes
- Data-mining pipeline that crawls open Colombian and LATAM data and normalises it
- Integrations with police, attorney general, and business databases
- REST API with key management for developer access
- Custom PHP dashboard with a complex user management system
- LLM-driven fraud detection infrastructure
Result
Users have reported the platform helping in two cases where someone's safety was at risk, alongside a steady stream of prevented financial loss.
Skills applied
Engineering
- REST API design
- API key management
- Custom PHP dashboard
Data
- Data mining
- Crawling
- Normalisation pipelines
AI
- LLM fraud detection
- Pattern analysis
Built with
- PHP
- REST API
- LLM
- Data mining
- Stripe
More work
Nova
2026 to present
The platform this site runs on. Nova is a team of AI agents that handles the repetitive work behind digital marketing, rank tracking, local SEO, citations, competitor research, content, QA, small site fixes, so that the hours I spend go to strategy instead. It runs my own projects and client websites in production.
Crawller
April 2026 to present
A crawler I built because the existing ones were not good enough for what I needed, large-scale collection, knowledge extraction, and indexing that AI can actually use.
Medellin.co
2022 to present
A city platform for travelers, expats and local businesses. It is where I learned RAG and autonomous content generation properly, at a scale where getting it wrong was visible.