# Cross-day lesson — Riverfront Steel, 2026-04-21

_Generated by `gpt-oss:20b` in 5.4s. Based on 5 events + 2 mid-day checkpoints._

**  
Before any expansion or emergency event, pre‑fetch and validate the pool data for the target location—missing pool info caused all failures. Use a smaller, more reliable model (e.g., gpt‑4o‑mini) for large or high‑risk events and keep prompts concise. Verify that the number of required positions matches available candidates before invoking the model. If the model returns empty output, switch to a more robust model and re‑validate the data. This will reduce failures and improve turnaround.