💿 PS11997Polyphony DigitalBRUTAL

Gran Turismo rebuild deck

BRUTAL

Everything hard about it is the tyre model, and tyre models are a research field with a literature rather than a system you sit down and write.

The hard part is not game design at all.

An arcade racer is a weekend. A sim is not, and Gran Turismo is a sim: the product is a tyre model, and tyre models are a research field with a literature. One prompt gets you something that drives — which is already remarkable — but the gap between "drives" and "feels like a car" is the whole 25-year history of the series.

Difficulty: BRUTAL · 5 of 5
First playable: A project
The original: 40 team-years
Released: 1997 · PS1
Genre: Racing

The one-shot build prompt

Build a 3D racing game with a real vehicle physics model. three.js for rendering, custom physics — do not use a generic rigid-body car.

Requirements:
- Vehicle model: sprung mass on four wheels, each with its own suspension (spring plus damper), computing load transfer under braking and cornering. Longitudinal and lateral forces per tyre from a simplified Pacejka curve — slip ratio and slip angle in, force out, with a peak and a falloff past the limit. This falloff is what makes a car feel like a car.
- Engine torque curve by RPM, a gearbox with ratios and a final drive, a clutch, and rear/front/all-wheel drive options. RPM comes from wheel speed through the drivetrain, not from throttle position.
- Aids as toggles: ABS, traction control, stability control. With everything off the car must be genuinely hard to drive, and that must be a choice.
- Track as a spline with width, banking and elevation, generating both the render mesh and the collision surface. One circuit plus a skidpad for testing.
- Telemetry overlay: per-wheel slip, load, and a friction circle. You cannot tune a tyre model you cannot see.
- Camera: chase camera with lag and roll, plus a cockpit view. Speed-scaled FOV.
- Simple AI on the racing line with a speed-per-corner lookup, braking points, and basic avoidance.
- Fixed 120Hz physics tick, rendering interpolated.

Definition of done: I can hold a controlled slide with the throttle, and the telemetry shows the rear tyres past their peak slip angle.

Before you start🧰 The toolkit — models, MCP servers, art and 3D

What you lose

A tyre model that took Polyphony a decade — the entire reason the game exists
Licensed cars and real tracks, both legally and as laser-scanned data
The career progression and economy that made the driving mean something
Force feedback, which is where half the information in a sim lives

What to steal

Tyre force curve with a peak and a falloff

A curve that rises to a peak and then falls away is why a car breaks loose and why you can catch it; linear grip gives you a vehicle that is either stuck or spinning with nothing in between. It is the one idea worth taking from a decade of tyre research, and it fits on a single screen.

ScopeAbout a week— build just this, not the game

Build a top-down car handling toy as a single self-contained HTML file. Canvas 2D, no 3D, no build step.

- One sprung mass on four wheels, each with a static load. Compute longitudinal and lateral load transfer from acceleration and a centre-of-gravity height, so braking loads the front and cornering loads the outside.
- Per wheel, compute slip angle and slip ratio, then feed each into a simplified force curve: rising steeply to a peak at a few degrees, then falling away. The falloff past the peak is the entire point and it is exactly what a linear grip model cannot give you.
- Combine longitudinal and lateral demand through a friction circle scaled by that wheel's current load.
- Physics at a fixed 120Hz, rendering interpolated.
- Telemetry overlay per wheel: load, slip angle, and a dot inside its friction circle that turns red past the peak.
- Empty tarmac, one painted skidpad circle, some cones. No track, no lap timer, no scenery.

Definition of done: I can hold a steady drift and watch the rear dots sitting past the peak while the fronts stay inside it.

Make it different

Not a clone — Gran Turismo re-themed and cut down to something you can finish. The angle is the important reel: it is what turns a project into a weekend. 5,880 ways to land.

Orbital From Above

Gran Turismo, but a management sim of the same world, set in deep space. Rendered in N64 fog and vertex colour.

Themedeep space

Anglea management sim of the same world

LookN64 fog and vertex colour

Build a browser game called "Orbital From Above".

The pitch in one line: a racing in the spirit of Gran Turismo, but a management sim of the same world, set in deep space.

WHAT THIS IS
Take the SHAPE of Gran Turismo — its core loop, and whatever makes that loop good — and rebuild it as your own game in a different world at a smaller scope. Use your own names, art and audio, which you want anyway: a reskin of somebody else's game is less interesting than a new one that works the same way.

THE ANGLE — this is the important constraint, honour it above everything else
A management sim of the same world. The player never controls a character — they set policy and watch agents with visible needs succeed or fail at it.
This is what makes the project finishable. If a decision would push the scope back towards the original's, take the smaller option every time.

THE THEME
Deep space. Vacuum, delay and no help coming. Sound only travels through the hull.
The theme is not a coat of paint. Let it change what the mechanics mean — a reload, a health pack and a locked door should all be things that make sense in this world and nowhere else.

LOOK
N64 fog and vertex colour. Heavy distance fog, per-vertex lighting rather than per-pixel, bilinear-blurred low-resolution textures, and a wide-open draw distance hidden by the fog.

REQUIREMENTS
- Runs in a browser with no build step. Canvas 2D unless the angle genuinely requires 3D, in which case three.js.
- Fixed-timestep update loop with interpolated rendering, so it behaves the same at 60Hz and 144Hz.
- Every tuning constant in one CONFIG object at the top, exposed as live sliders in a debug panel. You will find the feel by dragging those, not by prompting.
- All content — levels, entities, balance numbers — in JSON or plain data files, never inline in the logic.
- Audio generated with the Web Audio API rather than asset files.
- Respect prefers-reduced-motion: keep the fades, drop the shake and the parallax.

BUILD ORDER
1. The core loop with placeholder rectangles, at the reduced scope the angle demands. No theme, no art, no audio. Make it fun as rectangles first.
2. The angle's consequences. Cutting to bots, or to turn-based, or to one level changes the design rather than just shrinking it — find out how and rewrite step 1.
3. The theme, as content and data.
4. The look, applied last as a rendering layer over a game that already works.

Start by writing a one-page plan: the core loop, what the angle removes and what that frees you to do properly, and what you are deliberately leaving out. Wait for me to approve it before writing code.

Prior art — read before you build

Half the time one of these already does what you wanted, and the other half it saves you a week of solving a problem someone documented in 1997.

Did you build it?

0Share on X

One count per game. No account — it is tied to a salted hash of your IP, which is not stored in a form anyone can reverse. Every build adds 40 team-years to the counter on the homepage.

Then try these

Or roll something nobody has built yet →

Questions

How hard is Gran Turismo to rebuild with an AI agent?

Yes — every game is buildable at some scope. The question is how hard, and Gran Turismo is BRUTAL (5 of 5). The hard part is not game design at all. Everything hard about it is the tyre model, and tyre models are a research field with a literature rather than a system you sit down and write. Reckon on a project to something you can actually play — not to something that matches the 40 team-years Polyphony Digital spent.

What makes Gran Turismo hard to rebuild?

Everything hard about it is the tyre model, and tyre models are a research field with a literature rather than a system you sit down and write. That is why it sits at BRUTAL rather than a tier either side of it. If you want the idea without the project, the transferable part is tyre force curve with a peak and a falloff — about a week of work.

How long does it take to build a Gran Turismo clone?

Wrong question, and it is worth saying why. Nobody rebuilds Gran Turismo — the original took Polyphony Digital on the order of 40 team-years, released in 1997 on PS1. What you can do is reach something playable and genuinely yours in about a project, and then keep going for as long as it stays interesting. Any figure that claims otherwise is measuring a prototype and calling it a game.

What do I lose by building my own Gran Turismo?

A tyre model that took Polyphony a decade — the entire reason the game exists. Licensed cars and real tracks, both legally and as laser-scanned data. The career progression and economy that made the driving mean something. Those are the parts a prompt will not hand you.

Which AI coding agent should I use to build it?

Any of Claude Code, Codex or Cursor will handle this prompt. Paste it as your first message, let the agent scaffold the project, then iterate on feel — the second, third and tenth prompts are where a game actually gets good. Work in an empty folder or a fresh git branch so you can throw it away cheaply.

Get the next game

One email when new games go on the list. No other reason to email you, ever.