| Customer | Due | Amount | Status |
|---|---|---|---|
| Sample Customer A | Oct 3 | R$ 4,210 | Overdue |
| Sample Customer B | Oct 12 | R$ 9,875 | Paid |
| Sample Customer C | Oct 18 | R$ 2,340 | Upcoming |
| Sample Customer D | Oct 25 | R$ 7,600 | Upcoming |
I work the Forward Deployed Engineer way: I get inside the operation, understand the business problem and ship a working system. Finance, data and AI agents.
Internal web app for an industrial distributor. It reads the company ERP in read-only mode and brings together what used to be scattered across reports.
| Customer | Due | Amount | Status |
|---|---|---|---|
| Sample Customer A | Oct 3 | R$ 4,210 | Overdue |
| Sample Customer B | Oct 12 | R$ 9,875 | Paid |
| Sample Customer C | Oct 18 | R$ 2,340 | Upcoming |
| Sample Customer D | Oct 25 | R$ 7,600 | Upcoming |
I set up a team of 5 agents that works from a Kanban board, talks to me on Slack and ships code through pull requests, only when tests pass.
I ask for features in plain language. Registro confirms the scope, opens the cards and tells me when the PR is ready for my approval.
Registro has its own pixel-art avatar so the coordinator stands out on Slack.
I want to filter receivables by period: a date range or a single date.
Got it. I split this into 3 cards: API, screen and tests. The builder starts now.
I deployed the dashboard and the agents on a VPS that only my family can reach, over a private network.
I dug into the ERP database so every number on the dashboard matches the business.
SELECT n.natureza, COUNT(*) AS notas FROM notas_saida s JOIN naturezas n ON n.codigo = s.natureza WHERE s.cfop IN ('5102', '6102') -- sales only GROUP BY n.natureza;
A daily job that searches Brazil's national procurement portal (PNCP), filters for the products the company sells and posts a summary on Slack at 7 a.m.
3 new matching tenders today:
Every month, 3 PDFs of about 60 pages each arrived with the data for an outsourced-services contract. Extracting it by hand took 2 days.
Fixed rules for what has to be right every time, like what counts as a sale or how a payment matches an invoice. AI only where judgment helps.
First the format: required fields present and well formed. Then the business rules: the numbers have to make sense. Anything that fails goes to a person.
Automations draft, match and flag. A person reviews and decides, and the history stays recorded.
I start with a small proof of concept on real cases and measure accuracy and the review work left for the team, not just the model's hit rate.
Python, FastAPI, TypeScript, Next.js, React, REST APIs, automated testing, Git and CI.
SQL, MySQL, SQLite, ERP integration, data modeling and analysis, dashboards.
Agent orchestration, prompt engineering, cost-aware model selection, reviewing AI-generated code.
Docker, Linux, Tailscale, firewalls, least privilege, backups and leak audits.
Internal audit, internal controls, risk assessment, credit risk, accounts receivable, public procurement.
Agentic AI and AI Python for Beginners (DeepLearning.AI), Forward Deployed Engineer (Udemy, in progress).
In AI, fintech and B2B software. Remote or in the EU: I'm an Italian citizen, no visa needed.
All screens and messages on this page use sample data. The real systems run on a private network and hold confidential company data.