Skip to content
All builds
BUILD #005LIVE

AI Automation

Turning a repetitive back-office process into an automation nobody has to think about.

Status
LIVE
Date
January 2026
Stack
n8n / AI / Node.js / SQLite
AIAUTOMATIONN8N

The problem

A business was receiving supplier invoices as PDFs and photographs, then retyping every line into a spreadsheet. Four hours a week, every week, with the kind of transcription mistakes that only surface at the end of the quarter.

The idea

The process was already well defined — it just happened to be executed by a person. Extract the structure with a model, validate it against rules that already existed, and only involve a human for the cases that genuinely need judgement.

Building it

How it came together, step by step.

01 / 04

Writing down the rules first

Before any model was involved, the existing implicit rules were written out: which fields matter, what a valid total looks like, which suppliers format dates backwards.

Terminal

02 / 04

Extraction with a confidence score

The model returns structured fields plus how sure it is. Anything below the threshold is queued for a human rather than silently guessed.

Editor

03 / 04

Wiring it together in n8n

Inbox trigger, extraction, validation, database write, and a notification only when something needs attention.

Interface

04 / 04

A review queue for the edge cases

Roughly one invoice in twelve needs a human glance. That review takes seconds instead of minutes, from a phone.

Mobile

Features

What it actually does.

01

Document extraction

PDFs, scans and phone photographs into structured, validated fields.

02

Confidence thresholds

Low-confidence extractions route to a human instead of being guessed.

03

Rule validation

Totals, tax and dates checked against the rules the business already had.

04

Review queue

The exceptions surface in one place and clear in seconds.

05

Audit trail

Every extraction keeps the source document alongside what was read from it.

06

Runs unattended

Triggered by the inbox. It only speaks up when something needs a decision.

Tech stack

What it is built with.

  • n8n
  • AI
  • Node.js
  • SQLite

The result

Where it ended up.

Hours saved weekly
4
Needs a human
1 in 12
Transcription errors
~0
Runs per week
60+