Compare

OpenAI-only transaction enrichment alternative

TxnKit is a focused cleanup layer for teams evaluating OpenAI-only enrichment. Use it when the transaction feed already exists and the visible merchant row still looks unfinished.

Ask about a 100-descriptor cleanup auditInspect the API

Target intent

builders deciding whether to prompt an LLM for each transaction or use deterministic enrichment.

TxnKit avoids live LLM calls during POST /v1/enrich.

Raw descriptor

SQ *JOES COFFEE 0421 TORONTO

API-shaped output

{
  "input": {
    "descriptor": "SQ *JOES COFFEE 0421 TORONTO",
    "country": "CA"
  },
  "output": {
    "merchant_name": "Joes Coffee",
    "category": "Coffee shop",
    "confidence": "medium",
    "signals": [
      "processor_pattern",
      "merchant_alias",
      "category_hint"
    ],
    "warnings": [
      "review_low_confidence_matches_before_showing_logo"
    ],
    "logos": []
  }
}

Low-confidence results should keep fallback labels and warnings visible instead of forcing a guessed logo or website.

When to use

  • You already receive transaction data and need a narrower OpenAI-only enrichment alternative for display enrichment.
  • Your app needs merchant names, categories, confidence, warnings, and logo-ready metadata.
  • You want deterministic enrichment behavior without live LLM, crawler, logo-provider, or third-party enrichment calls.

When not to use

  • TxnKit avoids live LLM calls during POST /v1/enrich.
  • Do not use TxnKit to process card numbers, account numbers, full statements, bank credentials, emails, phone numbers, addresses, customer names, or customer PII.
  • Do not use TxnKit when the product requirement is guaranteed merchant identity, every-merchant resolution, or contracted uptime terms.

Proof surfaces

The public contract is POST /v1/enrich, backed by the OpenAPI file, benchmark examples, privacy rules, and deterministic request-path tests.

OpenAPI · Benchmark · Security · Pricing

Related pages