Package Long Documents for AI — Delimiters and § Labels
Pasting a document raw mixes material with instructions. Package it: explicit delimiters, citable [§N] section labels, and grounding rules — the source travels verbatim.
Overview
A long document pasted raw forces the model to guess where your words end and the document begins — and it guesses wrong in both directions. The packaged source ends the guessing: the material sits verbatim between explicit SOURCE START/END delimiters, sections carry [§N — title] labels so answers can cite them, and grounding instructions sit outside the delimiters where they belong. The packaging even neutralizes instruction-looking text inside the document. This setup loads a multi-section policy document in standard mode — six labeled sections, ready for support-team Q&A.
Workflow
-
Wrap, don't just paste
Delimiters bound the material; everything outside them is instructions about it.
-
Label the sections
[§N — title] lines make every part of the document addressable in answers.
-
Ground the answers
Answer-from-source-first rules, with outside knowledge labeled when it appears.
Why This Works
- Structural separation ends the source-versus-instruction guessing
- Citable sections turn vague answers into checkable ones
- Verbatim carriage means packaging never distorts the document
Best for
- Policies, handbooks, and reference documents
- Documents queried more than once
- Anyone whose pasted documents got treated as instructions
Not for
- Documents that exceed the window — split first with the Long Prompt Splitter
- Restructuring your instruction text — that's the Prompt Formatter
Use cases
- Preparing a policy for repeated Q&A sessions
- Making document sections citable by marker
- Separating source text from instructions structurally