Skip to main content

One post tagged with "custom Analyzer"

View All Tags

Build a Custom AI Analyzer for Your Own Invoice Format in Power Automate: A 3-Step Dropbox Workflow

· 24 min read
SEO and Content Writer

A Custom AI Analyzer Template is a named JSON schema you define in the PDF4me dev portal that tells the AI which fields to extract from a specific document type. This walkthrough builds an Analyzer for PDF4me's own SaaS subscription invoices (33 fields: vendor address block, Swiss MWST rate, subscription Id, line items, discount details), then calls it from a 3-step Power Automate flow that reads a PDF from Dropbox and returns structured JSON.

The built-in default_invoice_extraction covers generic invoices, but real AP teams have vendor-specific layouts, custom line-item columns, jurisdiction-specific tax fields, and subscription metadata that the generic schema misses. Building a custom Analyzer once gets you exact-match extraction forever, no per-field prompting required, no follow-up logic to clean up the response.

The full workflow at a glance
Setup A. Log in to dev portal
dev.pdf4me.com login. Email plus password or any SSO provider (Microsoft, Google, Facebook, Apple, GitHub).
Setup B. Open AI Document Parser
Dashboard sidebar, AI Document Parser. Lists every Analyzer Template you have already created.
Setup C. Add a Parse Analyzer
Click Add, name it (e.g. Test Invoice), choose Type Parse. The Analyzer Id is what Power Automate references.
Setup D. Paste the JSON schema
Document Schema field. Each schema entry has fieldName, fieldType, fieldDescription. Save Changes.
Flow 1. Manually trigger a flow
Replace later with HTTP / SharePoint / Outlook trigger when ready for production.
Flow 2. Get file content (path)
Dropbox path /pdf4me.pdf, Infer Content Type Yes. Reads the source PDF into the flow.
Flow 3. AI - Document Parser
PDF4me action. File Content from step 2, File Name Test.pdf, Customisation Note Test Invoice (your Analyzer Id). Returns body JSON.