Oracle × Scuderia Tor Vergata hackathon · 2026

AURIGA

An AI race engineer: it reads the telemetry, cites the rulebook and simulates the race before recommending a pit stop.

Role
Design and development
Period
2026
Stack
PythonFastAPIReactTypeScriptNumPyMCPOracle OCI

live demo Simulated console + original Strategy Lab

The race is the simulated one provided by the hackathon. The demo exposes the Strategy Lab with the original engine on the server; agents, prompts and Oracle services remain private.

AURIGA · pit wallSimulation · sample data
AURIGAVallelunga · simulated endurance · 50 laps

Session live · lap 23 of 50

Race engineer

The model never does maths in its head: numbers come from typed tools, and every answer cites its source.

Lap
23/50
Front-left wear
—
Pit window
—
Cost of the answer
—
Agentsidle
RACEENGINEERTelemetryRulesStrategyMediaMemory
Ask the pit wall
Tool calls0
  1. Pick a question to see which specialists are called and what they return.

A — The problem

In an endurance race, decisions happen in seconds: pit now or in three laps? Is that part legal? What do I tell the driver? The data exists — telemetry, rulebook, technical dossier — but it is scattered, and nobody can read it all while the car is on track.

B — What I built

For Oracle’s AI Race Engineer Challenge with Scuderia Tor Vergata I built AURIGA: a supervisor that routes every question to five specialists — telemetry, rules, strategy, communications and team memory. Each works with its own tools, and the interface shows live who is doing what. What comes back is a single recommendation with its sources: the laps analysed, the rule article, the simulation that was run.

6agents: 1 supervisor + 5 specialists
16MCP tools
50laps of simulated race
5.000simulations per run in the demo

C — How it works

  1. 01

    The question

    The pit wall asks in plain language: “Should we box?”

  2. 02

    Routing

    The supervisor picks the specialists it needs and runs them together.

  3. 03

    Tools, not hunches

    Wear per lap, pit windows, component checks: numbers come from typed tools, never from the model’s imagination.

  4. 04

    Simulation

    A Monte Carlo engine runs thousands of races with the competition’s scoring rules and compares strategies.

  5. 05

    The call

    One answer, reasoned and cited: “box between lap 24 and 26”.

D — The system

A simplified map of the components: not the technical documentation, but it shows how the parts talk to each other.

E — Why it works

The model never does maths in its head

Strategy and fuel always go through a simulator using the real scoring formulas.

Every verdict cites the rule

A component check returns the measurement, the limit, the rule section and the outcome.

Everything visible live

Agent constellation, tool calls and costs stream in real time.

Honest about scope

Built and tested on the hackathon’s simulated race, not on real track data.