The Blog

Tutorials, teardowns, and agentic AI workflows for the creator economy.

Paperless-ngx Workflow: Triggers, Actions, and Examples That Automate Filing
GuideNov 16, 2026· 9 min read

Paperless-ngx Workflow: Triggers, Actions, and Examples That Automate Filing

How Paperless-ngx workflows work: the four triggers and what each can filter on, every action type, title and webhook placeholders, six example workflows, and how to debug ordering and webhook problems.

Read more →
PDF OCR in Python: Send a PDF to our OCR API With httpx and Get JSON Back
GuideNov 16, 2026· 4 min read

PDF OCR in Python: Send a PDF to our OCR API With httpx and Get JSON Back

A short, dependency-light Python example that uploads a PDF to the OCRskill /ocr endpoint with httpx and reads per-page Markdown from a JSON response.

Read more →
Paperless Storage Path: How to Make Paperless-ngx File Documents Into Folders You Can Browse
GuideNov 15, 2026· 8 min read

Paperless Storage Path: How to Make Paperless-ngx File Documents Into Folders You Can Browse

What a Paperless-ngx storage path is, how it differs from PAPERLESS_FILENAME_FORMAT, template examples with placeholders and custom fields, how to assign paths automatically, and how to change them without losing files.

Read more →
Paperless-ngx Demo: Try the Public Instance, Then Test It on Your Own Documents
GuideNov 14, 2026· 8 min read

Paperless-ngx Demo: Try the Public Instance, Then Test It on Your Own Documents

Where the official Paperless-ngx demo is, what it can and cannot tell you, and how to run a throwaway local trial with Docker Compose so you can judge OCR, matching, and search on your own files.

Read more →
Paperless-ngx OCR: Settings That Fix Missing Text, Wrong Languages, and Bloated PDFs
GuideNov 13, 2026· 9 min read

Paperless-ngx OCR: Settings That Fix Missing Text, Wrong Languages, and Bloated PDFs

How Paperless-ngx OCR works in v3: OCR modes, archive file generation, language packs, cleaning and rotation, re-running OCR on old documents, and a symptom-by-symptom fix list.

Read more →
Tracking Code Example: What Carrier Numbers Look Like and How to Check Them
GuideNov 12, 2026· 8 min read

Tracking Code Example: What Carrier Numbers Look Like and How to Check Them

Tracking code examples for UPU S10 international mail, USPS, UPS, and GS1 SSCC pallet labels, what a label ID is, and a Python checker that validates OCR'd tracking codes by check digit.

Read more →
Paperless Archive: How to Build One That Stays Readable and Findable
GuideNov 11, 2026· 8 min read

Paperless Archive: How to Build One That Stays Readable and Findable

A paperless archive is more than a folder of scans. Learn which file formats last, how originals and archive copies differ, what metadata to capture, and how to back up, verify, and exit a digital document archive.

Read more →
Paperless ECM Services: What You Are Buying and Where OCR Fits
GuideNov 10, 2026· 9 min read

Paperless ECM Services: What You Are Buying and Where OCR Fits

Paperless ECM services cover capture, indexing, storage, retention, and delivery of business documents. Learn what a provider should actually do, how ECM differs from content services, and where OCR and structured extraction belong.

Read more →
Which IDP System Handles Inspection Notices from Multiple Sources?
GuideNov 8, 2026· 10 min read

Which IDP System Handles Inspection Notices from Multiple Sources?

Which IDP system handles inspection notices from multiple sources? Normalize email, portal, fax, and scan intake, classify the notice, extract fields your CMMS or EHS can store, and route with a review queue.

Read more →
Handwritten Parcel Code System: Codes People Can Write and OCR Can Read
GuideNov 7, 2026· 9 min read

Handwritten Parcel Code System: Codes People Can Write and OCR Can Read

Design a handwritten parcel code system that survives bad handwriting: a restricted alphabet, a fixed format, a Damm check digit, and OCR validation in Python.

Read more →
Customer Onboarding Form Data Extractor: Turn Applications into Typed JSON
GuideNov 6, 2026· 9 min read

Customer Onboarding Form Data Extractor: Turn Applications into Typed JSON

Customer onboarding form data extractor: pull name, contact, company, consent, and signature fields from account-opening packets with schema-field OCR, then validate before your CRM write.

Read more →
Build a Document Extraction Agent with Claude: Tool Use, OCR, and a Validation Loop
TutorialNov 5, 2026· 9 min read

Build a Document Extraction Agent with Claude: Tool Use, OCR, and a Validation Loop

How to build a document extraction agent with Claude: give it an OCR tool through the Messages API tool use loop, let it pick fields and retry, then validate the JSON in plain code before anything reaches your database. Runnable Python included.

Read more →