Skip to content

README.md

Latest commit

 

History

History
90 lines (70 loc) · 2.99 KB

README.md

File metadata and controls

90 lines (70 loc) · 2.99 KB

Invoice Sorting

Sanitized case study for an AI-assisted receipt and invoice intake system.

This repository is a public portfolio version of a private automation concept. It explains the architecture and engineering decisions without publishing a usable n8n export, live endpoints, server details, provider configuration, credentials, prompts, account identifiers, folder names, sheet schemas, database names, or production payloads.

Case Study

Problem

Receipts and invoices arrive through messy channels. A useful assistant has to accept images or text, extract structured data, validate missing fields, archive the source document, record the transaction, and confirm the result without leaking financial data.

Solution

The private system routes receipt images and text submissions through extraction, validation, storage, and confirmation steps. This public case study keeps the operating model visible while removing all account and implementation details.

flowchart LR
  A["Chat or Form Intake"] --> B["Message Router"]
  B --> C["Image or Text Extractor"]
  C --> D["Validation"]
  D --> E["Receipt Archive"]
  D --> F["Accounting Table"]
  D --> G["Summary Database"]
  E --> H["Confirmation"]
  F --> H
  G --> H
Loading

Engineering Decisions

  • Accept multiple intake modes but normalize them before validation.
  • Separate extraction from validation so the system can explain missing fields.
  • Store the source document separately from the structured transaction record.
  • Send a confirmation only after archive and record steps succeed.
  • Keep financial categories, storage paths, and database structure private.

Outcome

The private workflow reduces manual sorting while keeping humans informed about what was captured. The public version demonstrates intake design, AI extraction, validation, and operational safety without exposing a deployable bookkeeping system.

What This Shows

  • Receipt and invoice intake design
  • AI-assisted data extraction
  • Validation and error handling
  • Archive plus structured record split
  • Confirmation loop after successful processing

What Is Intentionally Missing

  • No importable n8n workflow
  • No node parameters
  • No live chat, form, storage, or server URL
  • No financial categories or folder names
  • No database schema or sheet structure
  • No production examples or execution payloads

Repository Structure

docs/architecture.md                     Sanitized architecture notes
scripts/validate-public-case-study.mjs   Leak and export-shape validation
SECURITY.md                              Public handling policy
package.json                             Validation command

Validate

npm test

The validator blocks common secret formats, URLs, webhook paths, credential blocks, local paths, n8n export shapes, and private terms supplied through SHOWCASE_PRIVATE_TERMS.

Note

This is a case study, not a template. It is designed to show automation design and security discipline without giving away a working financial workflow.