1. Documentation
  2. Processor
  3. Findings
Open Specter
  • Introduction
  • Quickstart
  • Authentication
  • Errors
  • Rate limits
  • Best practices
  • Overview
  • Access
  • Best practices
  • Create a key
  • Read and write
  • Overview
  • Best practices
  • Hosted page
  • Submit from your code
  • Drafts, files and corrections
  • Overview
  • Best practices
  • Create a key
  • Send documents
  • Read results
  • Findings
  • Process a deal
  • Errors and limits

Findings

What the processor concluded about a job — what's missing, fraud per statement, and which lenders fit.

Loading documentation…

Read results< PreviousProcess a dealNext >

On this page

missinginformationfraudassessmentlenderrecommendations

A job's findings are the processor's judgements, one per kind — and, for a fraud assessment, one per file. Each is the latest version:

FieldHolds
kindmissing_information, fraud_assessment, lender_recommendations or deal_insights.
fileIdThe file a fraud_assessment is about; "" for the others.
versionGoes up when the processor reports a different answer for the same kind and file.
payloadThe processor's answer, kept exactly as it sent it — below.
atWhen it arrived.

findings is [] until the processor has reported. A payload may gain keys over time; ignore the ones you don't use. A deal_insights finding is accepted but not sent by the processor today.

missing_information

What the deal still lacks. Present on a finished job; it is why a job ends needs_information.

json
{"kind": "missing_information", "fileId": "", "version": 1, "payload": {"completion_status": "incomplete", "completeness_score": 60,             "missing_documents": ["3 most recent months of business bank statements"],             "missing_fields": ["credit score"],             "missing_items": ["3 most recent months of business bank statements", "credit score"],             "required_actions": "…", "reason": "…",             "profile_key": "mca_default", "analysis_date": "2026-09-18T14:04:39Z", "…": "…"}}
KeyHolds
missing_itemsEverything missing, documents and fields together — what to ask the sender for.
missing_documents, missing_fieldsThe same, split.
completeness_score0–100.
completion_statusThe processor's one-word verdict.
required_actionsWhat to do next, as text.
reasonWhy, in a sentence.
profile_keyThe rule set it was judged by — picked by the productType you started the job with.
term_loan_readinessFor term loans, the readiness assessment; otherwise null.

fraud_assessment

One per PDF bank statement, naming the file in fileId.

json
{"kind": "fraud_assessment", "fileId": "9f0e6a2b-…", "version": 1, "payload": {"fraud_score": "35/100 - MEDIUM", "fraud_score_numeric": 35,             "fraud_reasoning": "…", "bank_name": "JPMorgan Chase"}}
KeyHolds
fraud_score_numeric0–100, higher is worse.
fraud_scoreThe same, with its level — LOW, MEDIUM, HIGH or CRITICAL — for a person.
fraud_reasoningWhy, as text.
bank_nameThe bank the statement was judged against.

lender_recommendations

The lenders the processor matched the deal to, when it did.

json
{"kind": "lender_recommendations", "fileId": "", "version": 1, "payload": {"source": "…", "run_id": "…",             "recommendations": [{"lender_name": "Fitting Funding", "rank": 1, "score": 0.71,                                  "reason": "…", "requested_amount": 45000,                                  "requested_term_days": 270, "requested_factor_rate": 1.3}]}}
KeyHolds
recommendationsBest first: lender_name, rank, score, reason, requested_amount, requested_term_days, requested_factor_rate, tags. A key the processor had no value for is left out.
run_idThe matching run it came from.

Nothing is sent to any lender.