RAG security: risks, controls and a practical threat model
Threat-model a RAG system across documents, indexing, retrieval and generation, then apply layered controls for permissions, provenance and testing.
Read articleBrowse by topic
Risk and assurance
Assessment, supplier review and assurance records for defined AI uses.
In this topic
Risk and assurance guides and articles.
Articles can appear here while keeping their primary category, so related guidance stays discoverable across the library.
6 articles
RAG evaluation: metrics, test sets and release gates
Evaluate a RAG system with test sets, retrieval and answer metrics, security tests, release gates and regression monitoring tied to real user tasks.
Read article
AI governance framework: a practical guide
Build a practical AI governance framework covering ownership, inventory, risk tiers, approval, monitoring, incidents and improvement.
Read article
AI risk assessment template: a practical guide
Use this AI risk assessment template to assess a use case, record evidence, rate risks, assign controls and decide whether to proceed.
Read article
AI vendor risk assessment: checklist and template
Assess an AI supplier's data handling, security, model controls, incident response and contract terms with this practical checklist and template.
Read article
Sensitive data classification: categories and criteria
Learn how to identify and classify sensitive data using content, context, legal duties, aggregation risk and the likely impact of compromise.
Read article