Skip to content
Igor FerreiraBack to the lab

Igor Ferreira

Engineering

Graduating in Control and Automation Engineering (Dec 2026), I work with industrial systems, solution development and technology integration. I like to understand how things work, question processes and find ways to improve them, especially when an idea leaves the page and starts working in the real world.

Artificial Intelligence

My relationship with AI began with the curiosity to understand how far this technology could go. Today I explore intelligent agents, machine learning and systems that integrate different tools and models. I like to experiment, build my own projects and find out how to turn technological possibilities into practical solutions. I still have a lot to study, and maybe that is exactly what motivates me most.

Music

Before engineering came music. I hold a bachelor’s degree in Music from UFES and spent years working as a musician and teacher. That is where I developed my creativity, sensitivity and discipline and, above all, the ability to teach and learn from other people. Changing careers did not mean leaving music behind. It is still part of who I am and of how I see the world.

The piano plays along with the background music, which the button at the top of the page turns on and off.

Projects 09

  1. 3D and virtual realityImmersive Electrical Room (VR)The drainage pump stopped. In the VR room, the trainee finds the drawer, reads the PLC ladder and the relay, warns the electrical team before touching anything and decides whether it can be restarted, away from an energized panel and as many times as needed.
  2. Industrial automationI/O Addresses: Quick Access to Remote I/OA Power Apps app that makes it easy to find, in the field, the equipment information and the address of each signal in the remote I/O panels, and shortens the time between the control room's call and the answer. Registered as a Kaizen.
  3. LLMs and agentsMesa dos 28Who reviews what the AI wrote? Lenses based on the public work of 28 experts read the project and cite file and line; the code checks every citation, and the final decision is human.
  4. LLMs and agentsVIX: assistente de voz para rotinas de escritórioVocê fala, um modelo planeja, o código preenche. Um personagem 3D que vive na área de trabalho e preenche um formulário web campo a campo, na sua frente.
  5. LLMs and agentsOrquestra StudioThree coding agents, one request. Orquestra plans, splits the work into tasks, runs the independent ones in parallel, each in its own Git copy, tests, asks an agent from another vendor for a review and integrates one at a time. The person approves the plan and the delivery.
  6. Machine learning and dataSolar generation loss, from inverter telemetry aloneOne string of panels stopped, and the inverter did not report it. From its telemetry alone, the study estimates how much the system should generate and finds the loss; Sunny explains the result in plain words.
  7. Industrial automationGNSS/RTK anti-collision for stockyard machinesI am responsible for the software and the field tests of a GNSS/RTK anti-collision system for stockyard machines in mining, as part of a team. The rule is to test before installing: a GNSS signal simulator, a virtual environment that replicates the field computers, and acceptance and failure tests, such as signal loss and reconnection.
  8. Industrial automation3D Bulk Stockyard SimulatorA simulator to test a stockyard machine's positioning software before installing it, with no machine, no field and no antenna. It plays the part of the antennas and the gateway: the positions go to the software 10 times per second, the 16 words it computes come back every half second, and each write is checked against the model. Five machines in 3D and faults on command.
  9. 3D and virtual realityIron Ore Pelletizing in VRWalk into a pelletizing plant with your hands only. The fines yard is ready, with the reclaimer working the pile; the plant comes station by station, in process order, towards voice-guided training.