Architecture

AI-Safe Views

The practice of creating constrained, pre-filtered views over lakehouse tables that limit what data AI/LLM systems can access, preventing models from inadvertently reading PII, confidential, or out-of-scope data during RAG retrieval or automated querying.

8 connections 3 resources

Summary

What it is

The practice of creating constrained, pre-filtered views over lakehouse tables that limit what data AI/LLM systems can access, preventing models from inadvertently reading PII, confidential, or out-of-scope data during RAG retrieval or automated querying.

Where it fits

AI-Safe Views are the security boundary between LLM-assisted data systems and the full lakehouse. As organizations deploy RAG and text-to-SQL applications against their data lakes, these views ensure that the model's effective query scope is explicitly bounded, regardless of the model's intent or prompt injection attempts.

Misconceptions / Traps
  • AI-Safe Views are not just regular database views. They must be enforced at the catalog/engine level so that LLM-generated queries cannot bypass them by referencing underlying tables directly.
  • View definitions must evolve with the underlying table schema. A schema change that adds a PII column to the base table automatically exposes it through a SELECT * view.
  • Performance of views depends on the engine's ability to push predicates through the view definition. Complex views with multiple joins may not benefit from partition pruning.
Key Connections
  • scoped_to LLM-Assisted Data Systems, Lakehouse — AI access control
  • depends_on Row / Column Security — underlying access control mechanism
  • enables RAG over Structured Data — safe retrieval scope for LLM queries
  • relates_to PII Tokenization — complementary PII protection strategy

Definition

What it is

Logical views over lakehouse tables on S3 that are specifically designed for LLM consumption — filtering out PII, applying column masking, and reshaping data into formats suitable for embedding generation or retrieval-augmented generation.

Why it exists

Exposing raw lakehouse tables to LLM pipelines risks leaking sensitive data into model contexts, embeddings, or generated outputs. AI-Safe Views provide a governed data access layer that ensures LLMs only see sanitized, policy-compliant data.

Primary use cases

PII-safe data for embedding generation, governed table access for RAG pipelines, compliance-compliant LLM data feeds.

Connections 8

Outbound 7
scoped_to3
LLM-Assisted Data SystemsLakehouseS3
depends_on2
Row / Column SecurityPII Tokenization
enables1
RAG over Structured Data
solves1
Policy Sprawl
Inbound 1
enables1
Redaction Layers

Resources 3

DocsHigh
docs.databricks.com/aws/en/data-governance/unity-catalog/

Unity Catalog governance documentation covering view-based access control for exposing curated, safe datasets to AI/ML workloads.

DocsHigh
trino.io/docs/current/sql/create-view.html

Trino CREATE VIEW documentation for defining security-filtered views over S3-backed catalogs that restrict AI model access to approved data.

DocsHigh
ranger.apache.org/

Apache Ranger policy engine documentation for enforcing row/column masking on views consumed by AI pipelines.