PDF
Your PDF
Paste your PDF. Nothing to upload.
←PDF
Make a content brief
Turn a PDF into a content brief
Upload the report. A writer gets the angle, the outline and every checkable figure — with page numbers.
Free to try, no card. Your PDF opens in Ancher.
Document structure in orderPage numbersTables as tables
Kept in parts
Every one of these stays separately addressable instead of collapsing into one block of text.
AngleTarget readerOutlineMust-include points
Content brief
An instruction set for a writer: angle, reader, outline, must-include points, sources.
A brief works when the writer never has to open the source, which for a hundred-page report is the whole point. Ancher lists the specifics — figures with page numbers, named entities, the caveats that must survive — and hands over the report's own reference list so the finished piece cites primaries rather than citing the report.
The honest version
For a hundred-page source, the brief is the entire job
A writer given a long report and a one-line angle will read the abstract, write from it, and produce something generic — because reading the whole thing is not a realistic ask. The brief has to do the extraction, which means it must contain the actual numbers and the page they came from, not a summary of where to look.
One page of one PDF, at p.118, read two ways.Illustrative. The figure is invented; the gap it falls into is not.
The brief says: include the headline growth figure,
Must-include, page 118 — not readThe specific never reaches the draft
Content brief
Must-include, page 118
19.4% (±1.2), n=1,204
from p.118
Lands in the draft, with its timecode
- Must-include points carry page numbers, so a writer verifies in seconds instead of reading a chapter.
- Caveats are listed as required inclusions, so the piece cannot accidentally overstate the research.
- The report's reference list becomes the writer's source list, so the article stands on primaries.
What comes out
Content brief, section by section
An instruction set for a writer: angle, reader, outline, must-include points, sources.
Angle
One sentence, drawn from what the report treats as its own contribution rather than from the topic.
Target reader
Inferred from what the report assumes its audience already knows, which sets how much explaining the piece must do.
Outline
Ordered for a reader, so the finding comes before the method rather than after it.
Must-include points
Every figure, date and named entity, each with a page number and its stated uncertainty.
Sources to cite
The report's own references, so the writer can cite what it cited instead of citing it for everything.
PDF-to-content-brief prompt
The link on its own gets a summary. This is the instruction that produces the 5 sections above, in that order, with the rules that keep them honest. Paste it with your PDF — in Ancher, or in whatever assistant you already use.
Build a content brief from this PDF. (1) State the angle from what the report treats as its own contribution. (2) Identify the target reader from what the document assumes is known. (3) Give an outline ordered for a reader, findings first. (4) List every figure, date and named entity as a must-include point, with page number and stated uncertainty. (5) List the caveats that must appear. (6) Build the source list from the report's references. Mark anything you could not attribute to a page.
The detail, if you want it
How each part of a PDF becomes a section
| From the PDF | Into | Why |
|---|---|---|
| Tables as tables | Must-include points | Must-include figures come from cells with their error bars intact, because a number without its uncertainty is a different claim. |
| Page numbers | Must-include points | Page numbers are what let a writer check a figure in seconds, which is the only reason a brief for a long report works at all. |
| Document structure in order | Outline | The heading tree is the raw material for an outline, which is then inverted so findings lead. |
| Embedded images and figures | Angle | A caption that states the contribution plainly is usually a better angle source than the introduction. |
| Document structure in order | Sources to cite | The reference section comes through as elements, giving the writer a ready-made source list ordered as the document ordered it. |
Everything Ancher keeps from a PDF
Document structure in order
Headings, body and captions arrive as separate elements, so the document's own outline survives ingest.
Page numbers
A page-level anchor is what makes a citation checkable by someone else holding the same file.
Tables as tables
Tables come back as their own elements rather than as flattened lines, so a figure stays attached to the row and column that give it meaning.
Embedded images and figures
Figure captions frequently carry the tightest statement of a finding in the whole document.
Reading order
Elements come back in sequence, which is what lets a section be reassembled rather than guessed at.
Word and PowerPoint too
The same path takes .docx and .pptx, so a deck and its write-up can sit in one collection.
The four steps
- Add the PDF. Upload the file. Ancher parses it into ordered elements rather than one flat string, keeps the page number on each, and pulls out the embedded images.
- Nothing gets flattened. Document structure in order, page numbers, tables as tables, embedded images and figures, reading order, word and powerpoint too stay separately addressable instead of collapsing into one block of text.
- Ask for a content brief. Ancher fills angle, target reader, outline, must-include points, sources to cite using the mapping above, not a generic summary pass.
- Check it before you use it. Every specific keeps a link back to where it came from in the PDF, so a claim can be verified without reopening the source.
Where this goes wrong
- A brief without page numbers sends the writer back into the report, which for a long document means they will write from the abstract instead.
- Figures quoted without their uncertainty become different claims. Carry the error bars and the sample size into the must-include list.
- If the must-include list contains no caveats, the resulting piece will overstate the research, and the correction will land on the byline.
Questions people ask
Can the writer skip reading the report?
That is the test. Every must-include point carries a page number, so verification is a spot-check rather than a read. If the writer still has to work through the document, the brief was too thin to be worth making.
How is this different from just summarizing it?
A summary tells you what the report says. A brief tells a writer what to produce — angle, reader, order, and the specific things that must appear. Those are different documents with different failure modes.
Does it work for a deck exported to PDF?
Well — decks are mostly headings and figures, which survive extraction best, so the must-include list comes out strong. The weakness is different: a deck assumes a talk track the file does not contain, so the brief will have gaps the slides never filled.
Bring your own PDFs
Everything you save lives in one workspace, so the content brief is built from your sources — not from a model's memory of the internet.
Open Ancher →Not a PDF? The same content brief also comes from YouTube video, X thread, LinkedIn post.