Skip to content

Back to the catalog

From Concept to Context Engine: How Wiz Built AI-Powered Data Discovery
wiz.ioarticle

From Concept to Context Engine: How Wiz Built AI-Powered Data Discovery

Wiz describes the evolution of its public bucket scanner into an AI-powered "context engine" for data security posture management (DSPM): a multi-agent pipeline where lightweight models triage files and larger models perform deep content analysis, iteratively learning bucket-specific patterns to find sensitive data that regex-based scanners miss. The production system adds structured severity scoring, synthetic/test-data filtering, algorithmic file clustering for scale, and now powers classification across cloud storage, cloud drives, endpoints, and Wiz's Red Agent attack-simulation findings. A one-week scan of public buckets using the engine surfaced over 2,700 sensitive data findings, including correlated credential/schema/export file sets that regex tools would treat as unrelated.

TL;DR Wiz turned a public S3-bucket scanner into a multi-agent, model-tiered AI engine that classifies sensitive data with context (not just regex matches) across cloud storage, drives, endpoints, and attack-simulation findings.
Open original ↗

Organisations named here

  • Red Agent

Technologies named here

  • Wiz DSPM
  • Public cloud storage buckets
  • Wiz AI-powered data classification system / context engine
  • Wiz Security Graph
  • Wiz Red Agent
  • Wiz classification engine
  • Wiz

Techniques named here

  • Public bucket scanning/reconnaissance
  • Traditional regex/rule-based data scanning
  • AI contextual data classification
  • Cross-file correlation for sensitive data collections
  • Synthetic/test data verification

Related in AI Security