Data Science · Applied AI · Automation
I'm Marcelo Santos. I build data systems, automation and artificial intelligence for real-world operations.
From ERP integrations to autonomous agents, semantic search and large-scale monitoring, I design every solution to fit each company's business rules.
Not prototypes. Production systems — running processes, connecting information and turning data into action.
Real system, fictitious data. A 30-minute trial, with the link sent by email. The link arrives by email; best opened on a computer.
00Who answers
She is the MJS agent: she reads the ERP, acts through the API and, when money is involved, asks before signing. The systems in this portfolio are what she operates.
See the Pandora case →
01 Areas of expertise
Every skill points to the production systems that prove it.
Resilient pipelines that extract, transform and unify data from legacy ERPs, SQL Server databases, TOTVS RM and spreadsheets — with incremental loads, watermarks and replica resilience.
Python · PostgreSQL · SQL Server · ETL incremental · pandas · Airflow-style jobs
Proven in
~2,7M processes in the historical pipeline — AppTech
Semantic search and RAG systems in production: embeddings, full-text, rank fusion and an MCP server acting as a "second brain" over 58,000 emails and thousands of documents.
RAG · Embeddings · Busca híbrida · MCP · LLMs · Bancos vetoriais
Robots that run the ERP on their own: they approve payment processes, import invoices, monitor publications from 91 courts, reconcile payments and settle instalments — and notify on WhatsApp whoever needs to know.
Agentes autônomos · WhatsApp API · Integração de APIs · Jobs agendados
Proven in
15 autonomous robots in production — Robot Fleet
Complete web apps in Flask + React, packaged in Docker and served in production with Docker Swarm, Traefik, Nginx and rolling deploys with healthchecks.
Flask · React · Docker Swarm · Traefik · Nginx · REST APIs
02 Projects & Case Studies
Production systems solving concrete business problems.
Flagship case
A satellite platform unifying sales, receivables, tax, legal and HR for a construction company.
More than twenty incremental pipelines consolidate the source systems into Postgres; on top of it, thirteen modules and the outputs operations actually use — including legal filings back into the ERP. Payroll comes in over a VPN, opened only during extraction. Drawing a single Postgres is a simplification: it stands for AppTech’s own database plus the legal database it reads and enriches.
Systems index
An agent orchestrator that operates the ERP — and, where money is involved, asks before it signs.
8 min from defect to delivered brief (before: 1 day)
Reads the official gazettes of 91 courts every night and delivers to each client only what is theirs — as a PDF, shielded against false positives.
1,1 mi+ publications read per day
A persistent-memory MCP server with semantic search over APIs, code, emails and schemas.
58k+ emails indexed
15 robots in production that operate the ERP on their own — tax, receivables, legal and infrastructure.
15 autonomous robots in production
An autonomous agent that reconciles payments against open instalments and settles them in the ERP on its own.
6 chained pipeline stages
WhatsApp messaging automation platform integrated with the ERP.
3 databases integrated
Finances for someone who is both an individual and a business owner, with an analyst that reads the numbers and tells you what to do.