Early Access — QA Lite

Know if your parser output is safe before it reaches your workflow.

ReceiptCheck is a QA layer for teams that rely on receipt parser or vendor JSON. Submit redacted outputs, get a benchmark report showing what’s unsafe, ambiguous, or missing — before it reaches payout, rebate processing, fraud review, or analytics.

QA Benchmark Report Sample
Accepted
passed all checks
Review
flagged, reason code
Rejected
buyer-critical issue
Top reason codes
Math reconciliation failed×4
Missing required field (total)×2
Ambiguous tax split×2
Merchant field empty or unstructured×1
JSON
Input
No images
QA Lite
Reasons
Findings
Redacted
Examples
01 — How QA Lite works

JSON in. Benchmark report out.
No images. No OCR. No live parser calls.

QA Lite works on structured JSON from any parser or vendor. Send 25–50 redacted outputs. We run QA checks and return a privacy-safe report showing what passed, what needs review, and what should be rejected — with reason codes for every flag.

Step 1
Send redacted JSON
25–50 parser or vendor outputs. Redact or anonymize before sending — no personal identifiers or receipt images required.
Step 2
QA checks run
Field presence, math reconciliation, structural integrity, and buyer-critical flags are evaluated across every output in the batch.
Step 3
Report delivered
Accept / review / reject counts, reason codes per flag, buyer-critical issue rate, redacted examples, and a gap summary.
02 — Report output

Accept, review, or reject —
with reason codes.

Every benchmark report shows which outputs passed QA checks, which need manual review, and which should be rejected before downstream processing. Each flag includes a reason code so your team knows exactly what failed and why.

  • Accept / review / reject verdict for every sample in the batch
  • Reason codes per flag — math failure, missing field, structural issue, buyer-critical
  • Buyer-critical issue rate — the share of outputs that could affect payouts or disbursements
  • Redacted examples and a gap summary included in every report
QA Lite report sample
Review
Verdict Needs review
Reason codes
subtotal_tax_total_mismatch line_sum_mismatch
Buyer-critical Yes — payout review recommended
Redacted example Line item sum does not reconcile with reported subtotal.
Gap summary OCR/image comparison not included in QA Lite.
Recommended action Hold for review before payout or downstream processing.
03 — What gets checked

Structured checks across
fields, math, and schema.

QA Lite runs a defined set of checks on every JSON output in your batch. No configuration required — checks apply to every sample automatically. Each check maps to a reason code in the report.

  • Required fields (total, line_items) checked for presence and validity; merchant and date fields checked for presence where required
  • Math reconciliation: line item sum must equal subtotal; subtotal + tax must equal total
  • Structural checks: empty arrays, null values in required fields, duplicate line items
  • Buyer-critical flags: missing total, zero-item receipt, structural failures that could affect payout
Reason-code examplesper sample
line_sum_mismatch
Review — item sum does not reconcile with reported subtotal
missing_total
Review — total field is missing or not greater than zero
duplicate_line_item
Review — repeated item rows may inflate basket value
buyer_critical
Yes — issue may affect payout, disbursement, or downstream trust
evidence_gap
JSON-only QA cannot compare against OCR text or receipt-image evidence
Output: needs_review · 4 reason codes
04 — Privacy-safe by design

Send redacted JSON.
No images required. Low-retention benchmark handling.

QA Lite works on JSON structure and math only. No receipt images, no OCR text, no raw capture data needed. Redact or anonymize before sending — we don’t need personal identifiers to run checks. Raw inputs can be deleted after the benchmark.

  • No receipt images or OCR text required — JSON structure only
  • Redact or anonymize samples before sending — PII not needed for QA checks
  • Reports are designed to avoid raw payloads and sensitive fields
  • Raw inputs can be deleted after the benchmark is complete

No images required

QA runs on JSON structure and math. Receipt images are not required and are not part of the QA Lite process.

Send redacted samples

Anonymize before sending. Personal identifiers are not needed to run QA checks.

Low-retention handling

Benchmark handling is designed to minimize raw receipt exposure. Raw inputs can be deleted after the benchmark.

Privacy-safe reports

Reports are designed to avoid raw payloads, sensitive identifiers, prompts, model responses, and model envelopes.

05 — Product suite

What ReceiptCheck is building.

ReceiptCheck is starting with QA Lite, a JSON-only benchmark for parser and vendor outputs. Additional QA workflows are in development for teams that need ongoing monitoring, vendor comparison, or evidence-based checks against OCR text or receipt images.

Available now
QA Lite
JSON-only benchmark on 25–50 redacted parser or vendor outputs. Returns accept / review / reject counts, reason codes, buyer-critical issue rate, redacted examples, and a gap summary.
In development
Continuous QA
Ongoing parser-output checks for teams that want to monitor quality over time and catch regressions before outputs reach payouts or downstream workflows.
In development
Vendor Benchmarking
Compare parser or vendor outputs on the same sample set to see which output is more reliable for your receipt types, fields, and business rules.
In development
Evidence-based Checks
Deeper checks for teams that need comparison against OCR text or receipt-image evidence when JSON-only QA is not enough.

Request a sample benchmark report.

Send 25–50 redacted JSON outputs from your current parser or vendor. We’ll return a privacy-safe report with accept / review / reject counts, reason codes, buyer-critical issue rate, and a gap summary.