By outcome

AI That Reads Your Documents

Stop retyping PDFs: learn how OCR and parsing work, then summarize a long proposal, question a contract, catch every change in a new version, sign a form without printing, and pull invoice fields into a spreadsheet with an approval step.

AI That Reads Your Documents is a free, hands-on AI course for office managers, bookkeepers, operations and admin staff who read contracts and proposals and retype invoices, receipts and forms: 10 short modules (about 1.5 hours in all) where you do each step yourself in a safe practice copy of Smallpdf, KDAN, Foxit, Docparser and other tools, which checks your work. No coding, no cost, and you can start without signing up.

Who it’s for: Office managers, bookkeepers, operations and admin staff who read contracts and proposals and retype invoices, receipts and forms. No coding until the last two modules.

10 modulesBeginner to Advanced~1½ hr of practiceFree

Why this course

PDFs are where office time disappears. A 25-page proposal arrives an hour before the meeting. A contract renewal hides a 90-day notice window in section 3.2. Version 2 of an agreement comes back with "small cleanups" and a fee that went up. And every week someone retypes the vendor, invoice number, date and total from a pile of invoices into a sheet.

This course starts with how software reads a document: OCR turns a scan into text, parsing finds the fields, and checks catch mistakes before they count. Then it uses the right tool for each job, in order: Smallpdf and KDAN to summarize and question long PDFs with page references, Foxit to review a contract, compare two versions and fill and sign a form, Docparser to pull invoice fields with parsing rules, and two n8n workflows that extract receipts and invoices with AI and send big ones for approval.

The payoff: hours of reading and retyping back every month, fewer missed deadlines and fee changes, and extracted data you can trust because you know where it slips. Every practice uses made-up documents.

Who this course is for

The first eight modules are beginner: a browser and the PDFs you already handle. The last two use n8n to automate extraction and are intermediate to advanced.

You can already

  • Open, read and download PDFs
  • Use a spreadsheet
  • Nothing else: no code and no accounts to start (the practice runs in your browser)

After this course you can

  • Tell a digital PDF from a scan and explain what OCR does
  • Explain parsing rules vs AI extraction and choose between them
  • Summarize a long PDF and check every AI answer against its page
  • Find a contract's fees, deadlines and renewal terms and compare two versions
  • Fill and e-sign a flat PDF form without printing
  • Turn invoices and receipts into spreadsheet rows, with checks and an approval step

What you’ll build

  • Module 3: You help Maya Chen, office manager at Larkspur Accounting Group, a made-up 24-person firm with a 25-page managed IT proposal and a 2 PM meeting.
  • Module 4: You help Dana Whitfield, office manager at Linden Row Accounting, a made-up firm. A 4-page managed IT agreement at $2,640 a month arrives with a call booked at 2:00 PM, and section 3.2 renews it for another year unless someone gives notice 90 days before the term ends.
  • Module 6: You help Dana Reyes, operations manager at Bright Path Marketing, a made-up agency, check version 2 of a software subscription agreement that the vendor called "small cleanups".
  • Module 7: You help Jordan Ellis, operations manager at Bright Path Marketing, a made-up agency, return a new client's New Vendor Setup Form so the first $4,800 invoice can be paid.
  • Module 8: You help Jordan, the office manager at Maple Lane Accounting, a made-up firm, stop retyping vendor invoices.
  • Module 9: A working n8n workflow: a chat window you can drop a receipt photo into, an AI agent that reads it, and a Google Sheet called Invoices with the columns Date, Category, Vendor and Amount.
  • Module 10: You keep the books at Cobalt Street Architects, a made-up firm. The workflow already catches invoice emails and turns each PDF into text. You add an Information Extractor that pulls out the vendor, invoice number, dates and total without guessing, log every invoice with Google Sheets Append row in sheet, and add an If node: total greater than 1000.
  1. Module 1 · Stepthrough · Beginner · ~2 min

    Start Here: How Stepthrough Works

    Welcome to Stepthrough: you learn AI by doing it, on practice copies of real app screens, free and with no risk to your real accounts. Your first practice takes under two minutes.

  2. Module 2 · Stepthrough · Beginner · ~7 min

    How AI Reads a PDF: OCR, Parsing and Field Extraction, Explained

    Invoices, receipts, contracts and forms arrive as PDFs, and somebody retypes them: vendor, invoice number, date, total, renewal date. It is slow, and a single misplaced digit can mean paying the wrong amount or missing a deadline.

  3. Module 3 · Smallpdf · Beginner · ~10 min

    Smallpdf: Get the Key Points of a 25-Page PDF in 5 Minutes

    Long proposals, policies and contracts land on someone's desk an hour before the meeting. The terms that cost money, such as automatic renewal, price increases and fees for leaving, are usually in the back.

  4. Module 4 · KDAN · Beginner · ~8 min

    KDAN: Get a Vendor Contract's Key Terms with AI Chatbot

    Vendor agreements get skimmed, and the clauses that cost money are the quiet ones: an automatic renewal with a 90-day notice window, a yearly price increase, a large early exit fee.

  5. Module 5 · Foxit · Beginner · ~10 min

    Review a Client Contract in 10 Minutes using Foxit AI

    Skimmed contracts hide auto-renewals, late fees and liability caps. Upload one to Foxit Workspace, get a plain-English summary and every renewal and exit date, check them against the PDF, and hand your boss a one-page watch list.

  6. Module 6 · Foxit · Beginner · ~8 min

    Foxit PDF Editor: Catch Every Change in a Revised Contract

    When a vendor or client sends "version 2" of a contract, the changes nobody mentions are the expensive ones: a fee, a notice period, a new sentence. Re-reading both versions side by side is slow, and your eye slides past a changed number.

  7. Module 7 · Foxit · Beginner · ~8 min

    Foxit PDF Editor: Fill and Sign a Form without Printing

    Clients, banks, landlords and HR send PDF forms that must come back signed, and most are flat: you cannot type in them. Printing, signing and scanning is slow at the desk and impossible on the road, and a vendor form that waits means an invoice that waits.

  8. Module 8 · Docparser · Beginner · ~10 min

    Docparser: Pull Invoice Data from PDFs into a Spreadsheet

    Most small firms still retype vendor invoices: open the PDF, copy the vendor, invoice number, date and total into a spreadsheet, check for typos, repeat. At a hundred or so invoices a month that is a full working day, and one slipped digit in a total is a payment problem.

  9. Module 9 · n8n · Intermediate · ~12 min

    AI Receipt Extractor

    Receipts pile up in photos, email attachments and the bottom of a bag. Typing the date, the store and the total into a spreadsheet one at a time is slow, and one slipped digit means the books do not match the card statement at month-end.

  10. Module 10 · n8n · Advanced · ~14 min

    Invoices from Your Inbox to Google Sheets, with Approval

    Vendor invoices arrive as PDFs. Someone copies the vendor, invoice number and total into a spreadsheet by hand, then chases the owner for a yes on the big ones. It is slow, typos slip in, and a large invoice can get paid because nobody asked.

Prerequisites

  • For the practice: a web browser. Each module runs in a copy of the real tool’s screens, so you need no account and no sign-up to start module 1.
  • To do it for real: a free Smallpdf account, a Docparser account, an n8n account, an OpenAI API key and a Google account. Each module says which one it uses.

Time to complete

About 1.5 hours of hands-on practice across 10 modules (271 steps in all). Modules take 2 to 14 minutes each, so you can do one in a sitting and come back for the next.

The ideas behind each module

Each module teaches one idea you will use again and again. Here it is in plain words: what it is, why a business uses it, and a real example.

Module 2 · How AI Reads a PDF: OCR, Parsing and Field Extraction, Explained

OCR, parsing and checks

What it is

OCR turns a picture of a page into text. Parsing finds the fields in that text, with rules for a fixed layout or AI extraction for varied ones. Checks (totals, duplicates, blanks, approval) catch mistakes.

Why a business uses it

Every document tool relies on these three steps. Knowing them tells you which tool to pick and where to look when a number comes out wrong.

A real example

A design studio's courier receipt scan comes back with a zero read as the letter O, and the totals check catches it before it reaches the books.

Words to know: OCR Searchable PDF Document parsing Data extraction

Module 3 · Smallpdf: Get the Key Points of a 25-Page PDF in 5 Minutes

Summarize a long PDF, then check it

What it is

An AI PDF summarizer reads the whole file and answers your questions, with page references you can click to check.

Why a business uses it

You get the cost, the lock-in and the way out of a 25-page proposal in minutes, without trusting a summary blind.

A real example

An accounting office catches a fee the AI left out of a list, and works out the first-year cost itself.

Words to know: AI PDF summarizer Source verification

Module 4 · KDAN: Get a Vendor Contract's Key Terms with AI Chatbot

Chat with a contract

What it is

Chat with PDF tools answer questions about one document and point to the section the answer came from.

Why a business uses it

Asking "what are the fees and deadlines?" is faster than reading every clause, and the section numbers let you confirm each answer.

A real example

An office manager finds an auto-renewal with a 90-day notice window before the call with the vendor.

Words to know: Chat with PDF

Module 5 · Review a Client Contract in 10 Minutes using Foxit AI

Review a contract with citations

What it is

Foxit's AI summarizes a contract in plain English and pulls out renewal and termination deadlines, each with a citation to the page.

Why a business uses it

The terms that cost money are the ones nobody reads. A citation for every deadline means you check the clause, not the summary.

A real example

A facilities firm reviews a four-page services agreement before signing it this week.

Words to know: AI summarization

Module 6 · Foxit PDF Editor: Catch Every Change in a Revised Contract

Compare two versions

What it is

A compare tool marks every change between version 1 and version 2: added, removed and changed text.

Why a business uses it

"Just a few small cleanups" is exactly where a fee increase hides. A compare takes minutes instead of a 40-minute side-by-side read.

A real example

A marketing firm finds a $150 a month fee increase, $1,800 a year, in a revised subscription agreement.

Words to know: Redline

Module 8 · Docparser: Pull Invoice Data from PDFs into a Spreadsheet

Parsing rules: same layout, every time

What it is

Docparser pulls the vendor, invoice number, date and total out of every PDF with parsing rules, and you add any field its template missed.

Why a business uses it

When invoices from a vendor always look the same, rules are exact and cheap, and the whole month downloads as one spreadsheet.

A real example

An accounting office stops retyping about 120 invoices a month.

Words to know: Parsing rules Document parsing

Module 9 · AI Receipt Extractor

AI extraction from a photo

What it is

An n8n agent reads a receipt photo, pulls out the date, vendor and total, decides the expense type and adds a row to a sheet.

Why a business uses it

Receipts come in every layout, which breaks rules. AI extraction handles them, as long as the output is checked.

A real example

A photographed receipt becomes a categorized row in an Invoices sheet.

Words to know: Data extraction

Module 10 · Invoices from Your Inbox to Google Sheets, with Approval

Inbox to sheet, with approval

What it is

A workflow catches invoice emails, turns each PDF into text, extracts the fields without guessing, logs them in Google Sheets and sends any invoice over a limit for approval.

Why a business uses it

Extraction saves the typing; approval keeps a person in charge of what gets paid.

A real example

An architecture firm's bookkeeper gets a log of every invoice, and the owner gets a yes-or-no request for the big ones.

Words to know: Approval workflow Duplicate invoice Accounts payable

Take it with you

Glossary

OCR Searchable PDF Document parsing Parsing rules Data extraction AI PDF summarizer Chat with PDF Redline E-signature Digital signature Fillable PDF Approval workflow

Questions about this course

Is AI That Reads Your Documents free?

Yes. All 10 modules of AI That Reads Your Documents are free, and you can start module 1 without signing up.

How long does AI That Reads Your Documents take?

About 1.5 hours of hands-on practice across 10 modules, beginner to advanced. Each module takes 2 to 14 minutes, so you can do one at a time.

Which tools will I practice in?

Smallpdf, KDAN, Foxit, Docparser and n8n. You practice in a copy of each tool's real screens that checks every step, so nothing touches your real accounts, and no coding is needed.

Who is AI That Reads Your Documents for?

Office managers, bookkeepers, operations and admin staff who read contracts and proposals and retype invoices, receipts and forms. No coding until the last two modules.

Where do I start?

Start with module 1, Start Here: How Stepthrough Works. The modules are in order, so each one builds on the last.

What is AI document processing?

Software that reads documents for you: OCR turns scans into text, parsing or AI extraction pulls out the fields you need (vendor, invoice number, total, dates), and checks catch mistakes before the data is used. It also covers summarizing long PDFs, comparing versions and e-signing.

What is the difference between OCR and document parsing?

OCR turns a picture of a page into text. Parsing takes that text and finds the specific fields you need. A digital PDF from billing software skips OCR because it already contains text.

Can AI extract data from invoices into a spreadsheet?

Yes. Parsing rules (Docparser) work well when each vendor's layout never changes. AI extraction (an n8n Information Extractor) handles varied layouts. Either way, check totals, duplicates and blank fields before the rows count.

Can I trust an AI summary of a contract?

Use it to find things fast, then check them. Every tool in this course shows the page or section an answer came from, and the lessons make you click through and confirm before you rely on it.

Do I need to code?

No for the first eight modules. The last two use n8n, which is visual but needs connected accounts and an API key.

What do I need before I start AI That Reads Your Documents?

Only a web browser for the practice: it runs in a copy of each tool's screens, so you need no account and no sign-up to start module 1. To repeat a module in your own tools afterwards, the modules list a free Smallpdf account, a Docparser account, an n8n account, an OpenAI API key and a Google account.

← All courses