Loop 021
The Boeing 747 benchmark
A vision-guided Three.js workflow that builds, inspects, and improves a Boeing 747 from repeatable camera angles until the agent is 100% satisfied.
Ready-to-use prompt
Copy the loop
/goal Create the most realistic Boeing 747 you can using Three.js. Use your vision capabilities to create a self-verifiable system, then enter a loop until you are 100% satisfied with the result. Build a repeatable camera system to inspect the aircraft from every required angle. After each significant change, render those same views, identify what looks least realistic, improve it, and inspect again. Preserve the best version as you iterate, and stop only when you are 100% satisfied that no visible issue remains worth fixing.
Verify / stop
You are 100% satisfied with the Boeing 747.
The camera system shows every required angle, and you cannot identify another visible issue worth improving.
Context and guidance When to use it, steps, safety notes, and related loops
Use this when
Use this as a visual benchmark for an agent that can build a complex Three.js scene, inspect its own renders, and improve the result through repeated vision feedback.
How to run it
- Build the first Boeing 747 model in Three.js, starting with the silhouette, proportions, wings, engines, tail, and other major forms.
- Create a repeatable camera system that renders the same required angles after every significant change.
- Use vision to inspect those views, identify the least realistic part of the current build, and improve it without losing stronger work.
- Render and inspect again, preserving the best version until you are 100% satisfied with the complete result.
Why it works
The camera system turns visual judgment into a repeatable feedback loop. Inspecting the same angles after every change makes improvement visible and gives the agent a concrete way to decide when it is fully satisfied.
Implementation note
Choose the required camera angles before the run and preserve the final renders. The contributor's stop condition is 100% satisfaction, so the images should make that judgment reviewable afterward.