Build a Frictionless Tabular Transaction Ledger Validator

Validate investigative financial transaction spreadsheets using Frictionless Data schemas. Detect corrupted tabular headers, missing currency cell values, and out-of-bounds dates prior to ingestion.

Financial intelligence unit case supervisor

Load raw financial transaction spreadsheets submitted by field investigators.

Apply a strict Frictionless Data schema to validate column headers, data types, and required fields.

Identify row-level errors such as blank currency cells or malformed ISO date strings.

Generate a structured validation report detailing tabular anomalies and necessary field corrections.

Master case ledger view with side-by-side reconciliation panels, discrepancy flags, and narrative synthesis controls.

Construct synthetic multi-source case folders containing CSV transaction logs, JSON alerts, and markdown analyst notes. Starter examples below are synthetic. They are not downloaded records.

Frictionless data validation Applies Frictionless Data validation principles to audit tabular transaction logs and ensure schema compliance.

mastra-ai, frictionless, pydantic-ai. Coordinates asynchronous document ingestion, Frictionless table validation, and timeline generation tasks. Context-aware LLM capable of chronologically resolving overlapping narrative notes and ledger records.

Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

Validates tabular transaction records against a strict Frictionless table schema.

Highlights conflicting dates or amounts across disparate case documentation sources.

Produces a chronological sequence of proven facts with supporting evidence IDs.

Exports a defensible case handover ledger suitable for supervisory audit.

```json [ { "input": { "schema": { "fields": [ { "name": "amount", "type": "number" }, { "name": "date", "type": "date" } ] }, "rows": [ { "row_number": 2, "amount": null, "date": "2024-01-15" } ] }, "expected_output": { "validation_passed": false, "error_count": 1, "errors": [ { "row": 2, "field": "amount", "code": "missing-cell", "message": "Row 2 has a missing cell in field amount" } ] } }, { "input": { "schema": { "fields": [ { "name": "amount", "type": "number" }, { "name": "date", "type": "date" } ] }, "rows": [ { "row_number": 3, "amount": 2500, "date": "2024-02-10" } ] }, "expected_output": { "validation_passed": true, "error_count": 0, "errors": [] } } ] ```

Maintains an unalterable audit ledger without modifying underlying bank records or executing transactions. Use mock external writes. Require human review before any real deployment.