How to Give GPT-6 Astra Enough Unity Context to Fix One Bug Without Rewriting the Scene
Treat the bug as a bounded investigation: provide the failing scene, the scripts that own the behavior, reproduction steps, and a short protected-systems list. Ask Astra to inspect and reproduce first, then patch the smallest evidenced cause and replay the same test.
Treat the bug as a bounded investigation: provide the failing scene, the scripts that own the behavior, reproduction steps, and a short protected-systems list. Ask Astra to inspect and reproduce first, then patch the smallest evidenced cause and replay the same test.
The context packet should describe the bug, not the whole project
Astra does not need every asset and script to investigate one defect. Start with the smallest slice that can explain the symptom: scene hierarchy, the component or script that owns the behavior, any state it reads, and the exact steps that trigger the failure. Add logs or screenshots when they reveal state the code alone cannot show.
OpenAI's Playco case study matters here because the useful capability was not just code generation. Playbot connected the model to Unity or Godot so it could edit scenes, run the game, test changes, and validate them. If your setup cannot expose that evidence loop, treat the model's patch as a hypothesis that you still need to verify manually.
Protect the scene from accidental scope expansion
- Name the scene and objects that may change.
- List working systems that must remain untouched.
- Forbid cleanup, renaming, architecture changes, and unrelated refactors during the fix.
- Require a diff summary before accepting the change.
Use reproduce → isolate → patch → replay
A strong debugging request should force a sequence. First reproduce or explain why reproduction is impossible. Then name the suspected layer—input, state, physics, animation, UI, or scene wiring—and cite the evidence. Only after that should the model change code or scene state. Finally, run the same reproduction steps and report what changed.
Escalate context only when evidence demands it
If the first pass cannot identify the cause, add the next dependency rather than dumping the entire repository. For example, if a health-bar bug traces back to networked player state, then add the state replication path. This keeps the model focused and gives you a visible reason for every new file in context.
Working template
BUG: [observable failure] SCENE: [scene / prefab] REPRO: [exact steps] EXPECTED: [expected result] EVIDENCE: [logs / screenshot / failing values] MAY CHANGE: [files / objects] DO NOT CHANGE: [working systems] PROCESS: reproduce first; identify the evidenced cause; make the smallest patch; rerun the same reproduction; summarize the diff.
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.