Skip to content
Creative American Consultants, Inc.

Generative AI

Shipping RAG that survives security review

CAC Engineering Team, Sep 22, 2026, 8 min read

Retrieval-augmented generation is the default enterprise pattern for generative AI. Here is what security teams ask about, and how to have answers ready.

Retrieval-augmented generation (RAG) grounds a language model's answers in your own documents. It's the right starting point for most enterprise assistants — and the first thing a security reviewer will want to understand.

Permissions travel with the document

If a user can't open a document in SharePoint, the assistant shouldn't quote it. Index access-control lists alongside content and filter at query time, not after generation.

Treat retrieved text as untrusted input

Documents can contain instructions. Separate system instructions from retrieved content, restrict which tools the model can call, and test with prompt-injection examples from the OWASP Top 10 for LLM Applications.

Log for audit, minimize for privacy

Keep question, retrieved sources and answer for audit, but redact sensitive fields and set retention periods your privacy office agrees with.

Evaluate before every release

A golden set of questions with expected sources lets you detect regressions when you change a prompt, a chunking strategy or a model version. Put it in CI.

Keep reading

Data Engineering, Aug 30, 2026

Medallion architecture without the hype

Bronze, silver, gold is a useful convention — if each layer has a clear contract. Without one, it's three copies of the same mess.

Have a problem worth solving?

Book a 45-minute working session. We'll look at your data, your constraints and your goals, and tell you plainly what we'd do first — whether or not you hire us.