Pedro Furtado.
RésuméContact

Home / Work

Work

What I built at my last jobs and for clients. For each one: the problem, what I did and the result.

At companies

Ford and Bradesco

Ford via CI&T · 2026 · Squad Lead, promoted Feb 2026

Support tools for Ford's sales applications in Latin America

My squad supports 12 sales applications, all in Java, used by Ford dealers in 8 countries. When I took over, support was reactive: incidents were handled as they came in. After opening a ticket, business users only knew it had been created, nothing more.

I built two tools. A Support Portal, where business users open tickets and follow their progress. And a Support Manager integrated with Jira and AI, with reports, charts and automations for users, for the support team and for the people I lead.

Read the full case

Ford via CI&T · 2025 · Built alone

A codebase assistant inside Ford's developer portal

Support analysts, developers and business people needed answers about how the systems worked. The answers were in the code, spread across many repositories.

Working alone, I designed and built a chat inside Backstage in two months. It indexes the GitHub repositories with RAG on pgvector, answers questions and uses MCP tools I wrote, such as one that opens tickets. Teams could choose Ford's internal model or a Google model.

Read the full case

Bradesco via Wipro · 2023 – 2024 · Software Engineer

Generative AI in Bradesco's virtual assistant

BIA, Bradesco's virtual assistant, ran on predictive AI and was being moved to generative AI. The new models were in Python; the bank's services ran on Java.

I was part of the team that adapted the Python libraries so the Java services could use them. I also delivered features in the Core API, which coordinates more than 50 microservices, and built secured REST APIs with Spring Security and JWT, test-first.

Read the full case

For clients

Built alone, since 2024, and live

How I usually build these: Java 21 and Spring Boot for the API, Next.js for the frontend, PostgreSQL, file storage on Cloudflare R2, deployed on Railway and Vercel.