
How to prepare documents for RAG
Prepare documents for RAG with a practical checklist for selection, permissions, parsing, metadata, versioning, chunking, testing and ingestion.
Read articleAuthor
Founder of .mdSiren
Writing about document security, prompt injection and exact-version controls for AI workflows.
About
Joseph Waddington is the founder of .mdSiren, a document-security product focused on the checkpoint before outside documents enter AI systems. He writes about document-borne prompt injection, exact-version controls before RAG ingestion, and practical document-review decisions. His writing distinguishes an observed signal from a measured system effect and from a consequential outcome, helping readers decide what merits review without inferring malicious intent.
Editorial approach
Joseph’s writing separates the presence of an instruction-like signal, a measured change in a model or pipeline, and a consequential real-world outcome. A finding is a reason to review—not proof that a document or its author is malicious.
Selected writing
Evidence-led articles on preparing documents, reviewing instruction-like signals and understanding what AI systems can read.

Prepare documents for RAG with a practical checklist for selection, permissions, parsing, metadata, versioning, chunking, testing and ingestion.
Read article
See what current studies show about hidden prompts in research papers, where the evidence stops, and how to check papers before AI-assisted review.
Read article
Learn how hidden or machine-readable PDF content can reach AI workflows, what current detection research shows, and how to review a PDF before use.
Read articleInformation for editors
These details can be used when commissioning or publishing an editorial contribution from Joseph.