RFP Compliance Matrix

RFP Compliance Matrix Generator & Proposal Audit

Upload an RFP.
Get a cited compliance matrix in Excel.
Add your proposal draft to find missing requirements before submission.

Free preview	Full proposal audit — $6.50
Upload one RFP; first 10 pages	Upload up to three RFPs; all supported pages
Eight highest-priority findings	Complete, source-cited requirement matrix
Two-sheet Excel preview	Five-sheet proposal-ready Excel workbook
Excel + CSV + JSON + Markdown	Excel + CSV + JSON + Markdown
No completed-analysis fee	One charge after the complete package is stored

Validated sample: 3 seconds · Excel + CSV + JSON + Markdown. The free preview detected 29 candidate requirements, returned the eight highest-priority findings, generated all four download formats, and explicitly logged that no completed-analysis fee was charged. Inspect the cloud run.

What the $6.50 full audit buys

This is not just a shall/must extractor. A completed full analysis includes:

• a five-sheet Excel workbook ready for proposal-team ownership and status tracking;
• a Proposal Coverage Audit that prioritizes missing and partially addressed requirements;
• proposal evidence citations linking each coverage decision to the strongest draft passage;
• a source-cited compliance matrix with RFP page numbers and verbatim evidence;
• a Section L/M crosswalk, deadline candidates, delivery risks, and an executive summary;
• matching CSV, structured JSON, Markdown, and Apify dataset outputs for downstream automation.

Built for human proposal teams and AI workflows: deterministic, source-cited, structured output with no external generative-AI API dependency.

Try the free preview

Choose Free quick preview, upload one RFP PDF, and press Start. No public file hosting is required. You can optionally upload a proposal PDF to see prioritized coverage gaps. If you do not upload anything, the documented public sample runs automatically. Free preview does not emit the USD 6.50 completed-analysis event; normal Apify platform usage may still apply.

{
  "analysisMode": "preview",
  "documentUrls": [
    "https://ardcplanning.org/wp-content/uploads/2025/11/Website-Redesign-2025-RFP-ARDC-and-ARDC-Planning-Final.pdf"
  ]
}

What you get

Proposal Coverage Audit

When you provide a proposal draft, the Actor compares every extracted requirement with short passages from the draft and returns:

• a conservative coverage status for every matrix row;
• the strongest matching proposal passage;
• a proposal page citation for PDF drafts, or block and segment coordinates for pasted text;
• a numeric match score and the terms that contributed to it;
• a separate audit sheet ordered by the most urgent gaps first;
• counts of critical and high-risk requirements that were not found.

The four statuses are designed for triage, not automatic approval:

Status	Meaning	Recommended action
Likely addressed	Strong requirement-specific lexical evidence appears in one proposal passage.	Confirm the passage fully answers the requirement and uses defensible evidence.
Partially addressed	Some relevant language appears, but the full obligation may be missing.	Expand or revise the cited section.
Not found	No sufficiently complete matching passage was identified.	Treat as a drafting gap and verify manually.
Manual review	The requirement is too short or vague for a reliable deterministic match.	Read the RFP citation and decide manually.

The audit intentionally favors review over confident claims. A high score means strong textual overlap, not that the answer is correct, persuasive, or legally compliant.

Proposal-ready compliance workbook

The Excel workbook contains five working sheets:

1. Executive Summary — volume, deadlines, delivery risks, coverage counts, and high-risk omissions.
2. Proposal Coverage — prioritized gaps with RFP evidence, proposal evidence, citations, scores, and review reasons.
3. Compliance Matrix — editable owner, status, compliance response, and evidence fields beside every extracted requirement.
4. L-M Crosswalk — deterministic alignment between supported Section L instruction subjects and Section M evaluation subjects.
5. Documents — source URLs, page counts, text coverage, SHA-256 provenance, and extraction status.

Cross-document IDs such as CM-0001 stay consistent across the workbook, CSV, dataset, summary, and JSON package.

Quick start

Use analysisMode: "preview" for the free quick preview. Use analysisMode: "full" when you want the complete paid package.

In Apify Console, use Upload RFP PDF files and optionally Upload proposal draft PDF. Uploaded files are placed in the Apify Key-Value Store selected by the user and passed to this Actor as storage references. You do not need to publish confidential drafts on the open web. Query-string access signatures are removed from delivered citations and artifacts.

For API and automation workflows, public or signed HTTPS file references remain supported:

To audit pasted proposal text:

{
  "analysisMode": "full",
  "projectName": "City Website Redesign Bid",
  "documentUrls": [
    "https://example.gov/procurement/website-redesign-rfp.pdf"
  ],
  "proposalText": "Paste the proposal draft here...",
  "includeGuidance": true,
  "maxPages": 250
}

To preserve PDF page citations in the proposal evidence, use proposalPdfUrl instead of proposalText:

{
  "analysisMode": "full",
  "projectName": "City Website Redesign Bid",
  "documentUrls": [
    "https://example.gov/procurement/website-redesign-rfp.pdf"
  ],
  "proposalPdfUrl": "https://files.example.com/proposal-draft.pdf",
  "includeGuidance": true,
  "maxPages": 250
}

Provide either proposalPdfUrl or proposalText, not both. Leave both empty when you only need RFP extraction and the compliance package.

Input reference

Field	Required	Description
analysisMode	Yes in the form	preview inspects one PDF, up to 10 pages, and returns eight prioritized findings without the completed-analysis fee. full unlocks the complete package. Legacy API inputs that omit this field continue to run as full.
rfpFiles	No	Console upload field for one RFP in preview mode or up to three in full mode. No public hosting step is required.
proposalFile	No	Console upload field for one optional proposal draft PDF. Mutually exclusive with the other proposal inputs.
documentUrls	No	API-friendly alternative: one to three direct public or signed HTTPS PDF references.
projectName	No	A 1–120 character title used in the workbook and summary.
proposalPdfUrl	No	One direct public or signed HTTPS PDF URL for the proposal draft. Mutually exclusive with proposalText.
proposalText	No	Pasted proposal text from 20 to 500,000 characters. Mutually exclusive with proposalPdfUrl.
includeGuidance	Yes	Include lower-confidence should and guidance candidates when true.
maxPages	Yes	Reject any individual PDF above this 1–500 page limit.

Output records

Both modes use the same predictable artifact links. Preview artifacts are visibly labelled and limited; full-mode artifacts contain the complete supported analysis.

Open the run result to download:

• COMPLIANCE_MATRIX.xlsx — two preview sheets in free mode or the complete five-sheet working package in full mode;
• COMPLIANCE_MATRIX.csv — all compliance and proposal-coverage columns in a portable table;
• EXECUTIVE_SUMMARY.md — concise deadlines, risks, crosswalk results, and proposal gaps;
• REQUIREMENTS.json — the complete structured package, including documents, requirements, coverage, deadlines, and crosswalk;
• Dataset — one structured row per requirement for Apify API, automation, or downstream review workflows.

Every requirement row includes the source URL, SHA-256 digest, RFP page range, source quote, modality, category, review priority, source role, risk, and human-review status. Coverage-enabled runs add proposal evidence, proposal citation, score, matched terms, and a plain-language reason.

How the audit works

1. Downloads each allowed PDF after validating the HTTPS destination and every redirect.
2. Extracts text page by page and refuses to emit an empty success for image-only documents.
3. Generates requirement candidates with page-level source quotes and conservative review priorities.
4. Builds delivery risks, actionable date candidates, and the Section L/M subject crosswalk.
5. Splits the optional proposal draft into bounded passages and compares each requirement using weighted, normalized lexical evidence.
6. Stores the dataset and all downloadable artifacts.
7. Emits the billable completion event only when analysisMode is full; preview mode explicitly skips it.

The coverage audit is deterministic and does not call an external generative-AI API. The same extracted text and configuration produce the same comparison results.

Security and draft handling

• Console uploads are stored in the user's selected Apify Key-Value Store. The Actor strips query-string access signatures from delivered citations and artifacts.
• External URL inputs must resolve over public HTTPS. Private-network, loopback, credential-bearing, and unresolved URLs are rejected.
• Redirect destinations are revalidated before download.
• Each PDF has a 20 MB download limit, a 30-second fetch timeout, and a configurable page limit.
• Query strings from a proposal PDF URL are not copied into the delivered proposal metadata, but the original Actor input remains in your Apify run storage.
• Pasted proposal text is stored in the Actor input. Matching excerpts also appear in the run dataset and downloadable artifacts.
• Do not submit confidential or controlled proposal material unless your organization permits it to be processed and retained in your Apify account. Apply the appropriate run-storage retention or deletion policy after review.
• The Actor uses limited permissions and does not require access to unrelated Apify resources.

Pricing

The free quick preview does not emit the USD 6.50 completed-analysis event. Normal Apify platform usage and any small platform-defined events shown in the Pricing tab may still apply.

Full mode costs USD 6.50 per completed analysis. One completion covers the complete artifact package and the optional Proposal Coverage Audit. The event is emitted only after at least one RFP PDF succeeds and the dataset, Excel workbook, CSV, Markdown summary, JSON package, and run summary have all been stored.

Failed downloads and runs where every document is unsupported do not emit the completed-analysis event. Small platform-defined Actor-start and dataset-item charges are shown separately in the Pricing tab.

Validation evidence

The extraction pipeline has been evaluated on 10 public documents covering 336 pages and 1,913 requirement candidates. Review samples recorded:

• 100/100 checked page citations correct;
• 82.98% actionable precision on a deterministic 100-row full-queue sample with guidance included;
• 98.62% and 96.60% actionable precision on two fresh 150-row high-priority blind samples;
• 44/44 bounded gold obligations detected across two short RFPs, with 43/44 retained at high priority.

The free and full paths both passed capped public-cloud end-to-end validation on build 0.0.29 using a five-page public RFP and an intentionally incomplete synthetic draft. Free-preview run ixN9gvbMzaEB6T9UH finished in 3 seconds, detected 29 candidates, returned eight prioritized findings, stored the two-sheet workbook plus CSV, Markdown, and JSON, and logged chargedCount: 0 with reason free_preview_mode. Full regression run 4jatMxKmOrfge0QN2 finished in 3 seconds and generated 29 cited rows: 5 likely addressed, 8 partially addressed, 14 not found, and 2 manual review, including 7 critical/high-risk items not found. Both test runs used a USD 0.05 maximum-cost guard; the Console displayed USD 0.000 for preview and USD 0.001 for full platform usage. The project currently passes 32/32 automated tests, including upload-reference, restricted-token authentication, and access-signature regressions, all Apify schemas, dependency audit, structural workbook inspection, formula-error scanning, and rendered visual review.

These measurements establish tested behavior on the stated samples. They do not establish complete recall or general accuracy across every procurement format.

Current limitations

• No OCR for scanned or image-only PDFs.
• No structured reconstruction of complex tables.
• No automatic amendment comparison.
• No direct authenticated websites or private-network sources; use the built-in Apify upload fields for local/private PDFs.
• No DOCX, XLSX, ZIP, or controlled attachment ingestion.
• Coverage matching is lexical and may miss paraphrases or select a passage that uses similar language for a different purpose.
• Page limits, signatures, attachment packaging, deadlines, pricing accuracy, and legal terms still require final human review.

This Actor supports proposal planning and review. It does not make a legal, procurement, or final compliance determination.

Local verification

npm test
npm audit --omit=dev
npx apify-cli validate-schema
npm run validate-corpus

VALIDATION_REPORT.md documents the evaluation design, sampling limits, confidence intervals, source roles, and remaining risks.