# Quietforge Dataset Audit PDF Report

> Quietforge Dataset Audit PDF Report is a paid API for AI agents from qf-api.quietforge-studio.workers.dev, paid per call via x402, $1.99/call, status unknown (last checked 2026-10-11).

Audits a CSV or JSON dataset for data quality issues—duplicates, missing values, type inconsistency, class imbalance, numeric outliers, and PII patterns—and returns a one-page PDF summary plus a JSON report in a ZIP archive.

## Facts

- Endpoint: POST https://qf-api.quietforge-studio.workers.dev/v1/dataset-audit/pdf?utm_source=zero.xyz
- Price: $1.99/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/quietforge-dataset-audit-pdf-report-60ed5969
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_yhNRMuEkXqH0hxNV-EhLB

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability quietforge-dataset-audit-pdf-report-60ed5969 -d '<json body>'
```

Example prompt: Can you audit this CSV dataset for data quality issues—duplicates, missing values, type inconsistencies, outliers, class imbalance, and any PII patterns—and give me back a one-page PDF summary along with the detailed JSON report?

## When to prefer this

Choose this endpoint when you need a comprehensive, automated data quality audit of a tabular dataset (CSV or JSON) delivered as both a machine-readable JSON report and a human-shareable one-page PDF — especially when no signup or API key is desired and pay-per-call via USDC is acceptable. Prefer this over manual pandas profiling scripts when you need a portable PDF artifact, or over generic LLM-based data inspection when you want deterministic duplicate counts, outlier detection, and PII-pattern scanning in a single call.

## Known failure modes

- Dataset exceeds 5 MB, 50,000 rows, 200 columns, or 2,000,000 cells — returns a size-limit error
- Malformed CSV or JSON that cannot be parsed — format detection or parsing error
- Payment not received or insufficient USDC — x402 payment required response before processing
- Empty dataset with zero rows — may return minimal or error response
- Network timeout on very large datasets approaching limits

## How this service works

Pay-per-call document conversion, PDF text extraction, headless-browser rendering of a URL or HTML to PNG / JPEG / PDF, a health-probed directory of x402 pay-per-call endpoints, a sudoku generator (solver-verified, technique-graded puzzles as JSON or a print-ready A4/Letter book), a book typesetter (prose manuscript to a KDP-ready interior PDF + editable docx), a crossword generator (verified freeform grid from your clue/answer pairs as JSON or print-ready PDFs), a family tree chart layout engine (descendant / ancestor / hourglass charts from people+families JSON or a GEDCOM file, as verified layout JSON or print-ready poster and tiled PDFs), and a dataset quality audit tool (duplicates, missing values, type consistency, class imbalance, numeric outliers and PII-pattern counts for a CSV/JSON dataset, as JSON or a one-page PDF summary). Payment: x402 (USDC on Base). No signup, no API key.

## Output

Returns a ZIP archive (base64-encoded) containing a machine-readable JSON audit report and a one-page print-ready PDF summary. The JSON includes quality score (0–100), duplicate row count, row and column counts, elapsed processing time, and flags for missing values, type inconsistencies, numeric outliers, class imbalance, and PII-pattern counts. The PDF provides a human-shareable one-page visual summary of the same findings.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "string",
   "description": "the dataset itself: CSV text, or a JSON array of flat objects. Max 5242880 bytes, 50000 rows, 200 columns, and 2000000 cells (rows x columns) — the cell cap binds first on wide datasets."
  },
  "format": {
   "enum": [
    "auto",
    "csv",
    "json"
   ],
   "type": "string",
   "description": "auto (default, sniffs '[' for JSON), csv, or json"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "bytes": 9000,
  "files": [
   "report.json",
   "summary.pdf"
  ],
  "pages": 1,
  "col_count": 4,
  "row_count": 4,
  "elapsed_ms": 40,
  "content_type": "application/zip",
  "quality_score": 79,
  "content_base64": "UEsDBBQ...",
  "duplicate_row_count": 1
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/quietforge-dataset-audit-pdf-report-60ed5969/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from qf-api.quietforge-studio.workers.dev](https://www.zero.xyz/host/qf-api.quietforge-studio.workers.dev/llms.txt)