PAR Technology, which serves over 300 restaurant businesses, built a production-ready multi-tenant LLM analytics system that enforces row-level security through three independent architectural layers (AWS Machine Learning Blog). The system enables business users to ask questions in plain English and receive data-backed answers, while ensuring that each user—whether a franchise owner with access to two locations or a brand manager overseeing 200 locations—receives only the data they are authorized to see (AWS Machine Learning Blog).
The three-layer architecture operates independently: Layer 1 uses AWS Signature Version 4 (SigV4) to cryptographically sign and authenticate every API call; Layer 2 validates semantic intent on Amazon Bedrock before any data access; and Layer 3 enforces programmatic data isolation via Split-Plane SQL at the database level (AWS Machine Learning Blog). This design addresses a critical insight: LLMs are probabilistic generators that may silently omit filters or hallucinate values, making them unsuitable as sole security enforcers in multi-tenant systems (AWS Machine Learning Blog). For commerce platforms and SaaS providers handling sensitive business data across multiple tenants, the approach demonstrates that security must be deterministic and enforced at the architecture level, regardless of what the model generates.