Claude Vision and PDF processing
View badge details
About This Course
Process images and PDFs with Claude chart extraction, receipt/invoice OCR, form understanding, multi-page document reasoning, and structured JSON extraction from visual sources. Learn the vision content-block shape, PDF beta, cost/latency tradeoffs, and when to route to Haiku vs Sonnet vs Opus.By the end of this course you will be able to build a document-intelligence pipeline for Orion Analytics that ingests scanned invoices, extracts line-items, validates totals, and hands off structured data to downstream systems.
Course Curriculum
10 Lessons
Vision content blocks and image inputs
How Claude accepts images: content-block shape, base64 vs URL, supported formats, size limits, and the "one image = ~1.15K tokens" cost model.
Describe a chart with Claude Vision - Lab Exercises
Encode a chart image, send it via a base64 image block, and read Claude's structured description.
Structured extraction from images
Get JSON out of pictures — receipts, forms, screenshots. Prompt patterns for reliable schema-conforming extraction.
Extract a receipt to JSON - Lab Exercises
Use tool_use to extract a scanned receipt into structured JSON with merchant, date, total, and line items.
PDF processing — pages, tokens, and the beta header
Send PDFs directly to Claude. Cost model, page limits, multi-page reasoning, and when to slice vs whole-doc.
Extract a 3-page invoice PDF - Lab Exercises
Send a multi-page PDF invoice to Claude via the document content-block, extract totals and line items across pages.
Vision routing — Haiku vs Sonnet vs Opus
Choosing the right vision model. Cost/accuracy tradeoffs by task type: simple OCR (Haiku), forms/charts (Sonnet), complex layouts (Opus).
Compare Haiku, Sonnet, and Opus on the same image - Lab Exercises
Send the same receipt image through all three model tiers, compare accuracy, latency, and cost side-by-side.
Vision + tool_use — decide then act
Combine vision with tools: Claude sees an image, decides what to do, then invokes a tool to act. Two-turn pattern for document-routing pipelines.
Orion invoice processing pipeline capstone - Lab Exercises
Build an end-to-end document pipeline: vision router → structured extraction → validation. Works on both PDFs and images.
This course includes:
- 24/7 AI Instructor Support
- Live Lab Environments
- 5 Hands-on Lessons
- Completion Badge
Earn Your Badge
Complete all lessons to unlock the Claude Vision and PDF processing achievement badge.
Claude Vision and PDF processing
Awarded on completion of CLD-AI-110. The holder can process images and PDFs with Claude, extract structured JSON from documents, choose between Haiku/Sonnet/Opus by task complexity, and build document-intelligence pipelines.
Skills You'll Earn
Complete all lessons in this course to earn this badge