How to Decide Which Game Tasks GPT-6 Astra Should Handle Inside the Engine vs in Code
Put tasks in the engine when correctness depends on scene state, timing, layout, physics, visual feedback, or play behavior. Keep pure transformations and isolated logic in code when they can be validated without running the game.
Put tasks in the engine when correctness depends on scene state, timing, layout, physics, visual feedback, or play behavior. Keep pure transformations and isolated logic in code when they can be validated without running the game.
The engine is not just a place to apply code
Playco's published setup connects models directly to Unity and Godot because game correctness is partly embodied in scene data and runtime behavior. A UI can compile and still overlap at one aspect ratio; a movement script can look sensible and still feel wrong because acceleration, animation, and camera response interact.
Use an engine-dependence test
- Needs scene hierarchy or serialized values → engine.
- Needs spatial placement or camera framing → engine.
- Needs physics, timing, animation, or play feel → engine.
- Pure data migration with deterministic tests → code.
- Isolated utility logic with unit tests → code.
Do not bounce the same task between surfaces
Choose one owner for a change. If a coding agent modifies the state machine and an engine agent separately tweaks the same transition, you create conflicting sources of truth. Instead, let one implement and the other validate, with an explicit handoff.
Keep validation close to the surface where failure appears
If the user-visible failure is visual or interactive, the final proof should happen in the engine. If the failure is a pure parser or calculation, a deterministic test may be sufficient. Match the validation tool to the failure mode rather than to the model you prefer.
Working template
TASK: [...] FAILURE IS VISIBLE IN: code / scene / runtime / visual / interaction NEEDS ENGINE STATE TO JUDGE? yes/no IMPLEMENT OWNER: [...] VALIDATION OWNER: [...] DONE WHEN: [observable evidence].
Source and verification note
This guide was checked against OpenAI / Playco case study and updated Sep 5, 2026. Product behavior can change; current primary documentation should take precedence over this guide.