Skip to content
Evidence ingestion

Bring the evidence in without losing its meaning.

ReturnValue preserves source context, validates readiness, and makes every accepted record accountable before it enters a financial investigation.

Evidence-grade intelligence · Human validation · Traceable decisions
Ingestion / evidence viewIllustrative view
evidence readiness scan
claims_2026.csvschema recognized
policy_terms.pdfcontext extracted
Ready for analysis2 exceptions assigned
  • SourcesFiles, systems, feeds
  • ReadinessValidated before analysis
  • ExceptionsVisible and owned
  • LineagePreserved end to end
The ReturnValue approach

Evidence is only useful when it is trustworthy.

Ingestion is a controlled evidence process—not a blind upload. Every source is classified, mapped, validated, and linked to its intended use.

01

Connect

Add finance, operations, contract, claims, premium, commission, and document sources.

02

Classify

Identify source type, period, ownership, sensitivity, and intended analytical use.

03

Validate

Expose missing fields, coverage gaps, duplicates, freshness, and mapping exceptions before analysis.

Ingestion inputs

Import what your business actually has.

Most ingestion tooling assumes the input is already clean: a single tab, well-typed columns, no merged cells, no headers that span two rows. Real spreadsheets do not look like that. Real PDFs are worse. ReturnValue takes spreadsheets, PDFs, exports, and structured data as they arrive, not pre-cleaned and not pre-filtered.

A workbook with thirty tabs and a summary sheet that pulls from twelve of them keeps that structure, and every sheet stays addressable on its own. A contract with a clause buried under a scanned page is extracted, anchored to a page reference, and made queryable. The file you have is the file ReturnValue expects.

Each input is treated as a first-class source, so no upstream cleaning is required before insights can run. Types are inferred and normalized first, so downstream work is not guessing at column shapes, and anomalies, gaps, and outliers are surfaced early, before they get baked into a number you have to defend.

Documents
PDFs, contracts, reports, and scans. Text and tables are extracted and kept linked to the source page.
Spreadsheets and sheets
Excel and Google Sheets. Multi-tab workbooks are preserved, and worksheets can be modeled as joinable sources where supported, so joins can target any one sheet.
Encodings and locales
Character encodings, date formats, and number locales are detected so columns line up cleanly across sources.
Source provenance
Each input keeps a link back to where it came from, so downstream surfaces never lose track of the origin.
Connected investigation

Readiness before results.

A visible readiness gate prevents incomplete evidence from silently shaping financial conclusions.

  1. 01ReceiveSource registered
  2. 02ProfileStructure understood
  3. 03MapFields aligned
  4. 04ValidateGaps assigned
  5. 05ApproveReady for analysis
Evidence in context

Clarity at every decision point.

A defensible finding begins with evidence that can explain where it came from.

Illustrative view. Values shown are examples, not customer data.

Evidence validation

Scanning
  • claims_2026.csvSchema valid · 98%
  • policy_terms.pdfContext mapped
  • commission_detail.xlsx2 exceptions
See ReturnValue in your environment

Follow your first financial signal.

Ingestion — Platform | ReturnValue.ai