A quick demo of Firn’s tiered cache architecture. Upserts vectors with text, runs a cold query (hits MinIO/S3), then the same query warm (served from the foyer cache in microseconds). Followed by a BM25 full-text search and a metrics scrape proving the cache saved the S3 round-trip. This demo runs against local MinIO - on real AWS S3 the cold query takes 25 seconds instead of 109ms, making the cache speedup even more dramatic.