How it works
How DossierMap analyzes your dossier
DossierMap uses a two-stage process: an AI model proposes possible evidence matches, and a deterministic verifier confirms each match against real source lines before anything reaches your gap report. No ungrounded citation reaches the output.
Overview
The eight-step pipeline
Each analysis run follows the same sequence. Steps 1 through 3 are deterministic. Step 4 is the only step that involves an AI model. Steps 5 through 8 are deterministic again.
Criteria loaded from matrix template
The full set of promotion criteria rows is read from the institution-specific, track-specific, version-controlled matrix template before any document analysis begins.
PDF preflight and validation
Uploaded PDFs are checked for line numbers (CV and cover letter), page references (supplemental), and readability. Encrypted, corrupt, or non-PDF files are rejected before processing starts.
Evidence indexed by source component
Each uploaded document is parsed into source components: indexed CV line ranges, cover letter line ranges, and supplemental page or line references. The AI proposal step receives these components, not raw document text.
AI citation proposals generated
The only AI step. The pipeline sends one structured-output request per criteria section to the configured AI model provider. Each request contains the criteria rows for that section and all indexed source components from all uploaded documents. The model returns proposed citations with a strength classification and a rationale for each.
Deterministic citation verification
Every proposed citation is checked against the indexed source components. A citation is accepted only if its quoted text is grounded to real, indexed lines or pages in the uploaded documents. Proposals that do not match are rejected and logged in the audit trail.
Gap report generated
Each criteria row receives a status based solely on verified citations. The four possible statuses are explained in detail below.
Human review of possible matches
Verified citations classified as possible matches are held in a review screen. Faculty decide which possible matches to accept or exclude. No possible match enters the matrix export without an explicit decision.
Matrix export
Only strong-match citations that passed verification are written into matrix source-location cells by default. Accepted possible matches may be included after review. The export maps each citation to the correct matrix column based on document type.
Step 1
Criteria loading
DossierMap reads criteria rows from the selected Personalized Promotions Matrix template for your institution, school, track, rank, and criteria version. Criteria are loaded before any document is uploaded or analyzed.
The criteria version date is displayed on every gap report and matrix export. DossierMap does not use generic academic promotion criteria or infer criteria from document content.
The criteria set is fixed at the start of each run. It cannot change during analysis, and the AI proposal step cannot expand or reinterpret criteria rows beyond what the template specifies.
Step 2
PDF preflight
Before any analysis begins, each uploaded file is checked against the requirements for its document type. The preflight step rejects files that would produce unreliable results.
CV and cover letter PDFs must have visible line numbers. Supplemental materials must have stable page references. All files must be unencrypted, readable, and in PDF format. Files that fail preflight are returned with a specific reason and are not sent to the analysis pipeline.
All uploads
- PDF format only.
- Readable, unencrypted, and not password protected.
- Text must be extractable enough to support verification.
- The selected analysis scope must include every document type required for the run.
- Files outside the selected scope are not analyzed for that run.
CV
- Visible sequential line numbers are required.
- Line numbers must be dense enough for the verifier to map citations reliably.
- The CV should be the current academic CV intended for promotion review.
- Scanned or image-only CVs require OCR before upload.
Cover letter
- Visible sequential line numbers are required.
- The letter should be uploaded separately from the CV and supplemental packet.
- Letter citations are treated as narrative claims, not independent verification.
- Summaries or paraphrases are not accepted as quotes.
Supplemental materials
- Stable page references are required.
- Visible line numbers are optional and used only when they are reliable.
- Exhibits should be paginated and grouped in the order faculty will review them.
- Image-only pages may need OCR or manual review before they can support quoted evidence.
Step 3
Evidence indexing
Each document is parsed into source components: discrete, addressable segments of evidence with their exact line or page locations. A CV source component might be lines 84 through 91. A supplemental component might be page 3 of a teaching statement.
The AI proposal step receives these indexed components, not raw document text. This ensures every proposed citation can be traced back to a specific, verifiable location in the original file.
Step 4
AI citation proposals
This is the only step in the pipeline that involves an AI model. DossierMap uses a configured AI model provider with structured output to generate citation proposals. The pipeline sends one request per criteria section, with each request containing the criteria rows for that section and all indexed source components from all uploaded documents.
The model returns a structured response for every criteria row: a row assessment status, proposed citations with quoted evidence, line or page references, a strength classification, and a short rationale.
There are two strength classifications a proposed citation can receive:
A citation classified as a strong match means the quoted evidence directly and specifically supports the matrix criterion. A citation classified as a possible match means the quote is relevant but requires faculty judgment or corroboration before it should be used in the matrix.
The AI proposes. It does not decide. Every proposal passes through deterministic verification in the next step before it can influence the gap report or matrix export.
Step 5
Deterministic verification
Every proposed citation is checked against the indexed source components from step 3. The verifier confirms that the quoted text in the proposal actually appears at the referenced line or page location in the uploaded document.
Proposals that do not match the indexed source are rejected. Rejected citations are logged in the run audit trail and are visible in the gap report — they do not silently disappear. A rejected citation cannot reappear in the matrix export.
The verification step exists specifically to catch cases where the AI model cited a plausible-sounding but fabricated or mislocated source. No ungrounded citation reaches the output.
Step 6
Gap report statuses
After verification, each criteria row in the gap report receives one of four statuses based solely on what the verifier accepted.
The distinction between unsupported and not found matters. Unsupported means the AI looked and found something, but verification rejected it. Not found means the AI did not find a match in the materials you provided, which may reflect an out-of-scope document type, a missing upload, or a genuine gap.
Step 7
Human review gate
Verified citations classified as possible matches are held in a dedicated review screen before they can reach the matrix export. Faculty see the quoted evidence, the source location, and the AI rationale for each possible match, and make an explicit decision to accept or exclude it.
Faculty decisions are stored separately from the verifier output. Accepting or excluding a possible match does not alter the original run record. The audit trail preserves the full verification history regardless of export decisions.
Possible matches do not populate matrix source-location cells by default. The default state is conservative. Faculty must take an action to include a possible match in the export.
Step 8
Matrix export rules
The matrix export writes verified citations to the correct source-location columns in the selected Personalized Promotions Matrix template. Each citation's document type determines its column: CV evidence writes to the CV column, cover letter evidence to the cover letter column, and supplemental evidence to the supplemental materials column.
By default, only strong-match citations that passed verification are written into export cells. Possible matches accepted during the human review step may be included. The exported matrix is editable — faculty and mentors retain full control over the final submission document.
DossierMap does not claim the exported matrix is complete, submission-ready, or institution-approved. The export is a draft starting point for faculty and mentor review.
Disclaimer
Assistant, not authority
DossierMap uses AI and deterministic verification to help identify possible evidence matches. It can miss relevant material, misclassify support, or surface evidence that still requires academic judgment.
The faculty member is always responsible for reviewing the source text, verifying accuracy, correcting errors, and deciding what belongs in a promotion submission. DossierMap is an assistant for organizing and checking evidence; it is not a substitute for the faculty member, mentor review, faculty affairs guidance, or committee judgment.
Before downloading a matrix export, users must acknowledge that the exported file is a draft aid and that they are responsible for validating all content before use.
Privacy
Privacy and data handling
Uploaded documents are sent to the configured AI model provider for the citation proposal step. They are processed for analysis only. DossierMap does not use uploaded documents for model training, and documents are not retained by DossierMap after your session ends.
The selected AI provider's API data handling is governed by that provider's API data usage policies. DossierMap is a pilot. Production deployment will add encrypted storage, configurable retention periods, deletion controls, minimal logging, and institution-level security review before accepting real faculty dossiers.
If you have questions about whether DossierMap is appropriate for your institution's data policies, consult your faculty affairs office or institutional privacy officer before uploading real dossier materials.
Limitations
What DossierMap does not do
DossierMap maps evidence to criteria. It does not score candidates, predict promotion outcomes, compare candidates to each other, or generate written content for your dossier.
The gap report reflects what is verifiable in the materials you upload in the scope you select. A not-found status does not mean the criterion is unmet — it means verified evidence was not found in the uploaded documents. Evidence in documents outside the selected scope, or in formats the tool cannot parse, will not appear in the analysis.
AI citation proposals can be wrong. The deterministic verification step is designed to catch ungrounded proposals, but verification confirms source grounding, not academic merit. Whether a cited passage genuinely satisfies a promotion criterion is an academic judgment that belongs to the faculty member, their mentor, and the promotion committee — not to DossierMap.
DossierMap is an organizational and verification aid. It does not replace mentor review, institutional guidance, or committee judgment at any stage of the promotion process.