Guardians of the State: An Air-Gapped AI Fortress for Consumer Data — Rachna Srivastava, DFPI

DFPI separated ingestion, processing, and reasoning across Kafka, Spark, and local models after an initial system failed within **2 hours**. Routing work to the smallest capable model handled **over 80% of tasks** and tripled traffic without more GPUs.

For sensitive agent systems, make provenance and replay architectural requirements. Clean inputs before inference, tokenize PII with hardware-held keys, route by task, quarantine external updates, and preserve the exact data state behind each decision.

The physical isolation, one-way data diode, and immutable history target unusually high legal and privacy stakes. The talk reports nearly **70% lower processing cost**, but provides no workload definition or independent security and accuracy evaluation.