Short answer
Create one project for one research question. Add the PDFs, correct each source record, and use statuses and tags consistently.
Read in the built-in viewer and attach each important note to the page it describes. Search for known wording when needed, then check Citation History and exported material before writing.
What this workflow solves
A folder can keep PDFs together, but it cannot explain which passage supports which idea. CiteFlow adds a local project library, a built-in PDF reader, source-linked notes, search and citation drafts. It is for reviewing sources you already collected, not discovering every paper on a topic.
Before you start
Write one clear research question and gather the PDFs in a temporary intake folder. A source record stores details such as title, authors, year and DOI. A source-linked note keeps your comment connected to its PDF and page. A status marks progress; a tag groups sources by a meaning you choose.
How we checked this guideSee what we reviewed, what we confirmed, and where the feature stops.
- What we reviewed
- Reviewed the project library, source reuse, statuses, tags, built-in reader, linked notes, exact search, Citation History, citation styles, exports, OCR and Semantic Search BETA in the current CiteFlow source.
- What we confirmed
- PDFs, notes and installed search indices remain in the local project workflow. Selecting DOI lookup, title lookup or title translation sends the entered query to an online service.
- Important limit
- A note that says only "important" is still hard to use. A better note states the claim, why it matters and the page to reopen, without pretending the app has evaluated the study.
Build the project from empty folder to checked evidence
1. Create a project for one question
Give the project a plain name that explains the subject. Choose the citation style required for the work: APA 7, MLA 9, Chicago 18 Author-Date, Chicago 18 Notes-Bibliography or IEEE.
Checkpoint: Someone seeing the project name can tell what belongs in it.
2. Add and identify every PDF
Import the source, then check its title, authors, year, publication and DOI when available. Reuse an existing source record instead of creating a second copy of the same paper. Selecting DOI or title lookup sends that value to an online service. Enter sensitive metadata manually instead.
Checkpoint: Open two source records and confirm that their titles match the first page of each PDF.
3. Use statuses for progress
Choose a small set of meanings such as To read, Reading, Reviewed and Excluded. Apply one status based on work completed, not on whether you agree with the paper.
Checkpoint: Every source has a progress state that another reading session can understand.
4. Use tags for the comparison question
Create tags for concepts you will compare, such as population, method, outcome or limitation. Avoid a different spelling for the same idea. Tags organize retrieval; they do not judge quality.
Checkpoint: A tag shows a coherent set of sources rather than one accidental item.
5. Read and write source-linked notes
Open the PDF in CiteFlow, select the relevant passage when text is available and record what it says, why it matters and any limitation. Use OCR for image-only pages, then compare names, numbers and quotations with the page image.
Checkpoint: From the note, reopen the exact source page and find the supporting passage.
6. Retrieve without losing context
Use exact search for a known phrase, title or identifier. Semantic Search BETA can retrieve related meaning with an optional E5 Large INT8 or BGE-M3 Full Precision local index, source filters and refinement, but similarity is not an answer or proof.
Checkpoint: Every retained search result has been reopened and read in context.
7. Copy, review and export
Copy a passage with citation context and review the saved draft in Citation History. Export only the bibliography, history, highlights and notes needed for the next stage. A citation draft and an export can carry incorrect metadata, so verify them before submission or sharing.
Checkpoint: Open the exported file in a second program and check one quotation, page locator and bibliography entry against the PDF.
Problems and limits
- CiteFlow is not a literature discovery database or a formal systematic review platform.
- It does not provide shared cloud collaboration or a full manuscript editor.
- OCR can misread text, and Semantic Search BETA can return a related but unsuitable passage.
- Online DOI, title lookup and title translation send the entered query to external services.
- Generated citations are drafts that still need source and style-rule checks.
Checkpoint: project ready for writing
- Each source record matches its PDF.
- Statuses describe progress and tags use consistent meanings.
- Each important note returns to a supporting page.
- Search results were read in context.
- Citation History and the export were checked before use.
CiteFlow
Organize a local research project with PDFs, source-linked notes, exact or optional meaning-based search, OCR, two-document comparison and citation drafts.