Prompt pattern fans out subagents, then loops with a harsh critic until quality passes
paul_cal · x · 2026-07-26
The post says the real substance of the request is tiny: the important part is how to fan out subagents and then verify or critique their outputs.
The attached image shows a prompt pattern for building a high-quality first-person shooter, with instructions to:
- fan out sub-agents for each task,
- loop on each item until it reaches AAA quality,
- use a separate harsh critic to visually compare results,
- keep iterating in Three.js until the result matches or beats the real game.
The main takeaway is a workflow pattern for agent orchestration: parallelize work, add an explicit critic, and iterate aggressively until quality is acceptable.
More from coding & agent
- AI coding benchmarks should show performance, cost, and latency distributions — zainhas · 2026-07-26
- AI coding benchmarks should report performance, cost, and time distributions — zainhas · 2026-07-26
- Official Obsidian CLI guide shows how AI agents can drive a vault from the terminal — dSebastien · 2026-07-26
- Aethos_Memory is an open-source memory bank for coding assistants across sessions — Longjumping-Koala396 · 2026-07-26
- Claude + Kit MCP: Automating Email Marketing Workflows via Natural Language — evielync · 2026-07-26
- Builder replaces hundreds of installed agent skills with one registry-backed skill — abhimanyu_saharan · 2026-07-26