Skip to main content
PDF4me APIIntegrationsKnowledge BaseExtensionsAPI TesterBlog

AI-Extract and Smart-Rename Any PDF in Make: A 4-Module Dropbox Workflow with PDF4me AI - Document Parser

· 20 min read
Sankalp Mishra
SEO and Content Writer

The hardest part of vendor-invoice automation has always been the file naming. A folder full of 2030703747 (1).pdf and Scan_2026-04-12_invoice.pdf is unsearchable, unsortable, and impossible to audit. PDF4me AI - Document Parser plus a Make Parse JSON module fix that in 4 modules, zero code: the AI extracts the vendor name from the PDF, and the same scenario re-uploads the file as Acme Industries.pdf. The screenshots below walk through the exact run captured in the canvas.

The scenario at a glance
1. Dropbox Download
Pulls /pdf4metest/sample/2030703747 (1).pdf. Scheduled trigger shown.
2. PDF4me AI - Document Parser
Runs the default_invoice_extraction Analyzer Template. Output: Doc Text JSON.
3. JSON Parse JSON
JSON string mapped to 3. Doc Text. Exposes vendorName, invoiceNumber, totalAmount, etc.
4. Dropbox Upload
Writes to /pdf4meoutput/ with File Name = 6. vendorName + .pdf. Smart-rename complete.
The short version

Four Make modules. Dropbox Download a File pulls the raw vendor PDF (screenshots show YnooxTestone connection, path /pdf4metest/sample/2030703747 (1).pdf). PDF4me AI - Document Parser maps File Name and Document from the prior step and runs default_invoice_extraction as the AI Analyzer Id. JSON Parse JSON turns the Doc Text output into individually mappable tokens. Dropbox Upload a File writes to /pdf4meoutput/ with File Name = 6. vendorName + .pdf and Data = 1. Data from the original download. The result: the same PDF lands in your output folder with a meaningful filename, no human in the loop.

The thing that makes this 4 modules instead of 8

Two design choices. First, Data on the Upload module is bound to Module 1 (original Dropbox Data), not Module 3. The AI parser only needs to extract metadata; the upload re-uses the original untouched file, so there is no re-encode, no quality loss, and one fewer step. Second, File Name uses the parsed token plus a literal .pdf extension (the screenshot shows 6. vendorName followed by the typed text .pdf) so the renamed file keeps a valid extension regardless of what the AI returns.

Common real-world questions this solves​

People search this exact problem with phrasings like:

  • "How do I rename a PDF by its content automatically?" This 4-module scenario does it: the AI reads the vendor name, the upload uses it as the filename. Zero manual work.
  • "Can Make extract vendor name from a PDF and use it elsewhere?" Yes. the JSON Parse JSON step right after AI - Document Parser exposes every extracted field as an individually mappable token (vendorName, invoiceNumber, totalAmount, etc).
  • "Is there an AI document parser in Make?" Yes. the PDF4me AI - Document Parser module. It is template-driven (Analyzer Template), so the same module handles invoices, receipts, contracts, and custom forms.
  • "How do I extract structured JSON from a PDF without training a model?" Pick a built-in Analyzer Template (default_invoice_extraction for AP) or build a custom one in the PDF4me dashboard. Zero training required.
  • "Can I rename the output file using one of the extracted fields?" Yes. After Parse JSON, drop the parsed token into the Upload File Name field. Done.

What you are building​

A reusable Make scenario for AP / inbound-document automation. Trigger fires (manual, scheduled as shown, file-watch, webhook), the vendor PDF gets parsed by AI, and the same file is re-uploaded with a meaningful filename derived from its content. Drop in any of the other PDF4me Analyzer Templates (receipts, contracts, purchase orders, custom forms) to handle other document types with the same flow.

Make scenario canvas: Dropbox Download a File (with scheduled clock badge), PDF4me AI - Document Parser, JSON Parse JSON, and Dropbox Upload a File. Four big circular module icons connected with the standard Make dotted-line connectors.

Four modules end-to-end. The clock badge on Dropbox 1 indicates a scheduled trigger; swap to webhook or file-watch for production.

What you need​

  • Make account with a scenario open. Create a Make account if you need one.
  • PDF4me API key. Get your API key. Add it on the first PDF4me module. See Connect PDF4me to Make.
  • Dropbox with a source folder (e.g. /pdf4metest/sample/) holding the vendor PDFs and an output folder (/pdf4meoutput/). Any storage works the same way.
  • A vendor invoice PDF. Download the sample used in the screenshots to follow along exactly. Any standard invoice format works (the AI handles layout variation).
  • (Optional) A custom Analyzer Template if your use case is not invoices. Build one at dev.pdf4me.com. Use the built-in default_invoice_extraction for AP.

Quick reference: what each parameter does​

AI Analyzer Id
Picks the Analyzer Template. default_invoice_extraction for invoices; custom templates for receipts, contracts, purchase orders.
File Name + Document
Both mapped from the prior storage module. Filename (with extension) and binary content of the source.
Doc Text (output)
JSON string with every extracted field. Always wire into a JSON Parse JSON module next.
Parsed tokens
After Parse JSON, every Analyzer Template field becomes an individually mappable token (vendorName, invoiceNumber, etc).
Smart-rename pattern
Drop a parsed token + .pdf into the downstream Upload File Name slot. Output file is renamed automatically.
Connection reuse
One PDF4me connection per Make team is enough. Add it once, reuse across every PDF4me module.

Build the scenario​

Module 1: Dropbox Download a File​

Pull the raw vendor PDF from the source folder.

FieldValue used in this run
ConnectionYnooxTestone (ynoox.test...). your Dropbox connection
Way of selecting filesSelect a file
File/pdf4metest/sample/2030703747 (1).pdf
Make Dropbox Download a File configuration with Connection YnooxTestone, Way of selecting files Select a file, and File path /pdf4metest/sample/2030703747 (1).pdf.

Module 2: PDF4me AI - Document Parser​

Search for PDF4me in the action picker and pick AI - Document Parser.

FieldValue used in this run
ConnectionMy PDF4me connection (t...)
FileMap
File Name1. File Name (from Module 1)
Document1. Data (from Module 1)
AI Analyzer Iddefault_invoice_extraction (built-in)
PDF4me AI - Document Parser action configured with Connection My PDF4me connection, File set to Map, File Name 1. File Name, Document 1. Data, and AI Analyzer Id default_invoice_extraction.

The default_invoice_extraction template is built-in. Click the Analyzer Template link in the hint to create a custom analyzer for receipts, contracts, or any document type.

Module 3: JSON - Parse JSON​

The AI module returns its result as a JSON string on Doc Text. Parse it to expose individually mappable fields.

FieldValue used in this run
Data structureMy data structure (or leave blank. Make builds one on first run)
JSON string3. Doc Text (from Module 2)
Make JSON Parse JSON action with Data structure left as My data structure and JSON string mapped to 3. Doc Text from the AI - Document Parser module.

Leave Data structure as the default My data structure and Make builds one from the live AI output on the first scenario run.

Module 4: Dropbox Upload a File​

The smart-rename step. Map File Name to the parsed token plus a literal .pdf extension, and Data to the original Module 1 file (not the AI output).

FieldValue used in this run
ConnectionYnooxTestone (ynoox.test...)
Folder/pdf4meoutput/
FileMap (so File Name and Data come from prior modules)
File Name6. vendorName + .pdf (the parsed vendorName plus a literal .pdf extension)
Data1. Data (re-uses the original Dropbox download. not the AI output)
Make Dropbox Upload a File configuration with Connection YnooxTestone, Folder /pdf4meoutput/, File set to Map, File Name set to 6. vendorName followed by .pdf, and Data mapped to 1. Data from the original Dropbox download.

Smart-rename: 6. vendorName is the parsed token from Module 3, with a literal .pdf typed right after it.

Save and click Run once. The vendor PDF lands in /pdf4meoutput/ named after its vendor.

Get your API KeyFull action reference

Troubleshooting​

Parse JSON cannot see Doc Text
The AI module did not run yet. execute the scenario once with Run once. Make builds the data structure from the live output of Module 2 on first execution.
Renamed file has no .pdf extension
Forgot the literal .pdf text after the vendorName token. Click the File Name field, place the cursor after the parsed token, and type .pdf.
Upload writes an empty file
Data is bound to the wrong source. It should be Module 1 (original Dropbox download). 1. Data, not the AI output. The AI module returns metadata, not a binary file.
vendorName comes back as empty or wrong
The Analyzer Template did not match the document layout. Try a different built-in template, or create a custom template at dev.pdf4me.com tuned for the layout of your vendors.
Want to extract more than vendor name
Any field in the Analyzer Template is exposed as a token after Parse JSON. Drop invoiceNumber, totalAmount, lineItems, etc anywhere you would drop a normal Make variable.
AI Analyzer Id dropdown is empty
No analyzer templates exist on your PDF4me account yet. Open dev.pdf4me.com, navigate to the Analyzer Templates section, and either pick the built-in default_invoice_extraction or create a custom template.

When to use this pattern​

Accounts payable automation
Vendor invoices in, structured data into Airtable / NetSuite / Xero, renamed file archived.
Email-to-ERP routing
Inbound email PDFs get parsed and routed to the right department based on extracted fields.
Contract intake (custom template)
Custom Analyzer Template extracts effective_date, parties, governing_law into a legal tracker.
Audit-friendly archives
Renaming by extracted vendor and date makes folders searchable and audit-trail clean.

FAQ​

What is the difference between AI - Document Parser and AI-Invoice Parser?+
AI-Invoice Parser uses a fixed invoice schema (vendor, line items, totals, dates) and returns confidence scores. AI - Document Parser is template-driven via the AI Analyzer Id, so you can swap the document type by picking a different template. Use AI-Invoice Parser for AP-only workflows; use AI - Document Parser when you handle multiple document types or need a custom field set.
Where do I create a custom Analyzer Template?+
From the AI Analyzer Id dropdown click the Analyzer Template link in the hint, or visit dev.pdf4me.com. Define the fields you want extracted, name the template, save. The new template appears in the AI Analyzer Id dropdown in Make on the next scenario edit.
Why is Data on the Upload module bound to Module 1 instead of Module 2?+
Because the AI module only returns metadata (the extracted JSON on Doc Text), not a binary file. The original PDF lives on Module 1 Data. Re-using it on the upload avoids re-encoding and keeps the output identical to the input.
How do I add the .pdf extension to the renamed file?+
After dropping the parsed vendorName token into File Name, place the cursor right after it and type the literal text .pdf. Make stores File Name as a mixed string (token + literal), and the upload writes the file with the combined name.
Can I trigger this from email, SharePoint, or a webhook instead of a scheduled Dropbox download?+
Yes. Replace Module 1 with any module that produces a binary file and a filename: Gmail Get Attachments, SharePoint Get file content, OneDrive Download a File, Webhooks Custom webhook with file payload. Modules 2, 3, 4 stay identical.
How big can the input PDF be?+
Practical limits are bounded by Make operation timeouts and the PDF4me API payload limit. For multi-hundred-MB documents, downsample first via a PDF4me Compress action then run AI - Document Parser on the result.
Does this work in Power Automate, n8n, or Zapier?+
Yes. The PDF4me AI - Document Parser action is available on all four platforms with the same Analyzer Template concept. See the cross-platform comparison at the bottom of the Make action reference page.
How accurate is the extraction?+
Accuracy depends on document layout consistency and the Analyzer Template fit. Built-in templates like default_invoice_extraction are tuned across thousands of vendor invoices. For custom layouts that the AI mis-reads on, build a custom Analyzer Template in dev.pdf4me.com with examples of your specific format.

Get started​

Get your API KeyPDF4me on MakeAction reference