Skip to content
Stepwork logoStepwork logo
Marketplace
Deterministic AgentsSecurity

The Stepwork Platform

Deterministic work across the tools you already run

  • Extraction
  • Rule
  • Webhook

In product

  • ProcedureRun the process end to end
  • ExtractionPull data into the next step
  • File processingExtract fields, split scans, and fill PDF forms
  • Ask BobBuild a flow by chatting

Solutions

How Stepwork shows up for your team and industry

By team

  • ITAccounts, access, helpdesk requests
  • Security & ComplianceAccess reviews, evidence, audits
  • Finance & AccountingInvoices, billing, month-end close
  • Sales & RevOpsCRM to ERP, orders, quotes
  • OperationsOrders, deliveries, dispatch
  • HR & PeopleOnboarding and offboarding
See all teams

By industry

  • HealthcareReferrals, eligibility checks, EHR entry
  • 3PL and warehousingPDF orders, WMS entry, client billing
  • Freight and truckingRate confirmations, carrier checks, TMS
  • Fuel and convenience storesStore staff, POS IDs, back office
  • ConstructionJob setup, subcontractor insurance
  • Manufacturing and distributionPO entry, supplier dates, legacy ERPs
  • Accounting firmsMonth-end across every client file
  • Field services and tradesService calls to jobs to invoices
  • MSPsNew users and license true-ups
See all industries
⌘K
Log inBook a Demo

Product

  • ProcedureRun the process end to end
  • ExtractionPull data into the next step
  • File processingExtract fields, split scans, and fill PDF forms
  • Ask BobBuild a flow by chatting
Marketplace

By team

  • ITAccounts, access, helpdesk requests
  • Security & ComplianceAccess reviews, evidence, audits
  • Finance & AccountingInvoices, billing, month-end close
  • Sales & RevOpsCRM to ERP, orders, quotes
  • OperationsOrders, deliveries, dispatch
  • HR & PeopleOnboarding and offboarding
See all teams

By industry

  • HealthcareReferrals, eligibility checks, EHR entry
  • 3PL and warehousingPDF orders, WMS entry, client billing
  • Freight and truckingRate confirmations, carrier checks, TMS
  • Fuel and convenience storesStore staff, POS IDs, back office
  • ConstructionJob setup, subcontractor insurance
  • Manufacturing and distributionPO entry, supplier dates, legacy ERPs
  • Accounting firmsMonth-end across every client file
  • Field services and tradesService calls to jobs to invoices
  • MSPsNew users and license true-ups
See all industries
Deterministic AgentsSecurity
Log inBook a Demo

File processing

Any document in. Edited, split, or structured out.

Pull digital exports and literal physical documents — scanned mailroom packets, handwritten forms, crumpled receipt photos, and faxed contracts — straight into the container's local file manager. Parse layouts, extract typed fields, edit and flatten PDFs, separate batch scans, classify, and summarize — then pass changed files or data to other flows, drives, data warehouses, data lakes, databases, or any API.

Book a DemoExplore Procedures
DownloadsUp to 7 MB
Physical scans & digital files
  • PDFscan_0031.pdfMailroom · Scanned invoiceReady
  • JPGIMG_4182.jpgPhone photo · Handwritten receiptReady
  • PDFclosing-packet.pdfOn-prem · 24-page physical scanReady
  • FORMvendor_w9_blank.pdfPortal · Editable PDF formReady
PDFJPG · HEICDOCX · XLSXCSV · EML
File processing

Process incoming document

5 actionsStandard or High accuracy

Input variables

  • File

Output variables

  • extracted_json
  • category
  • file_path
  • filled_file_path

Deliver edited files or data anywhere

  • Warehouses, lakes & APIsLoad Snowflake, S3, Postgres, or POST
  • Google Drive & split loopsArchive edited/split PDFs or loop per doc
  • ERPs, CRMs & portalsEnter bills or upload edited PDFs
  • Summaries, Slack & emailSend digests, approvals, or packets

Inside the container

Saved to the local file manager. Passed straight to anything next.

Every run happens inside an isolated local or cloud container with its own real filesystem. Files downloaded from a portal, email, or scanner share land directly in the device's local file manager — then flow straight through File processing into other flows, drives, data warehouses, data lakes, databases, or APIs.

Stepwork ContainerLocal device · /Users/stepwork/Downloads
Device Container OS09:00 AM
billing.apexfreight.com/exportsNo API

November Freight Statement

42 shipments · Ready to export

Export PDF
PDFstatement_nov_2026.pdf · Saved to /Downloads
File Manager~/Downloads
  • Downloads
  • Documents
  • Shared Mount
  • PDFstatement_nov_2026.pdf2.4 MB · Portal export
  • PDFq4_carrier_bols_batch.pdf4.1 MB · 18-page batch
  • FORMw9_brightline_filled.pdf312 KB · Filled PDF
  • CSVdaily_inventory_export.csv1.8 MB · Scheduled
file_path/Downloads/statement_nov_2026.pdf
File processing

Process local file

Extract fieldsReads local path

Input variables

  • downloaded_file_path

Output variables

  • extracted_json
  • file_path
  • invoice_total

Passed straight through to

  • Other flows & ProceduresTrigger ERP upload or approval flow
    Flow started
  • Google Drive & SharePointFile to /Finance/2026/Nov/
    Uploaded
  • Data warehousesSnowflake · BigQuery · Redshift
    42 rows loaded
  • Data lakesS3 · Databricks · Parquet / JSON
    Object written
  • DatabasesPostgres · MySQL · SQL Server
    Upsert OK
  • REST APIs & webhooksPOST file + extracted JSON
    200 OK
0:00 / 0:16

01 · Export in container browser: An Execution step signs into a non-API portal inside the container and clicks Export — no API connector required.

Physical paper in motion

Parse physical documents into sections. Write clean data straight back to PDF.

Watch real physical documents — stamped copier scans, handwritten W-9s photographed on a desk, crumpled receipts, and faxed contracts — decompose section by section into structured blocks, then watch upstream Procedure data write live into fillable PDF forms and flatten into final documents.

Video 01 · Parse physical documents

Decompose scans & photos into typed sections

A layout-aware vision scan reads headers, key-value fields, multi-row tables, handwriting, stamps, and wet-ink signatures into separate, cited blocks.

Scanning layout…scan_0031.pdf · 300 DPI scan
SUMMIT INDUSTRIAL SUPPLYvendor · Summit Industrial Supply2210 Dock St · Tacoma, WA 98421
INVOICE
Invoice #10482invoice_number · 10482Date10/21/2026TermsNet 30
Bill to: Acme Corp · Accounts Payable
QtyDescriptionUnitAmount
12Pallet wrap, 18 in24.50294.00
40Shipping boxes, large31.201,248.00
6Packing tape, case129.40776.40
line_items · 3 rows
Subtotal2,318.40Tax0.00TOTAL DUE$2,318.40total · $2,318.40
RECEIVEDOCT 24 2026
OK to pay – MK
Parsing
Parsed document sectionsExtracting blocks…
  • 01HEADERVendor & remit headerBox [y: 8%] · 0.99

    Summit Industrial Supply · 2210 Dock St, Tacoma, WA

  • 02KEY-VALUEInvoice metadata & termsBox [y: 26%] · 0.99

    invoice_number: 10482 · date: 10/21/2026 · Net 30

  • 03TABLE · 3 ROWSParsed line-item tableBox [y: 44%] · 0.98
    12×Pallet wrap, 18 in$294.00
    40×Shipping boxes, large$1,248.00
    6×Packing tape, case$776.40
  • 04STAMP + HANDWRITINGTotal, rubber stamp & pen noteBox [y: 78%] · 0.99

    total_due: $2,318.40 · Stamp: RECEIVED OCT 24 · Pen: "OK to pay – MK"

0:00 / 0:08
Video 02 · Write back to PDF

Detect form slots, write live values, and flatten final PDFs

Map upstream Procedure variables straight into blank or existing PDFs — populating text fields, checkboxes, character-per-box grids, and tables while guarding signature lines and outputting a locked final file.

Procedure variablesUpstream ERP / HRIS variables
  • legal_nameBrightline Logistics LLC
  • tax_classLLC · Taxed as S Corp
  • address88 Harbor Rd, Tacoma WA 98421
  • ein_digits12-3456789 (9 char boxes)
  • flatten_pdftrue · Preserve signature block
Output file/Downloads/vendor_w9_filled_final.pdf
Writing PDF
01 · Detecting fillable PDF form slots…vendor_w9_filled_final.pdf
FormW-9(Rev. 3-2024)
Request for Taxpayer Identification NumberDepartment of the Treasury · Internal Revenue Service
1 · Name of entity/individual text
Detected text field · awaiting value
3a · Federal tax classification checkbox + code
☐ Individual☐ C CorpLLC (Tax classification: _)
5 · Address (number, street, city, state, ZIP) text
Detected text field
Part I · Employer identification number (EIN) 9 char boxes
–
Part II · Sign Here (Signature)Left unsigned for human sign-off
Signature block preserved
0:00 / 0:08

Full document engine

Parse, extract, edit, split, classify, and summarize.

Digital exports and literal physical documents — office copier scans, handwritten forms, phone photos of receipts, stamped bills of lading, and faxed contracts — all flow through one production document engine inside your Procedure.

Works on physical paper & digital files alike
  • Mailroom paper scans
  • Handwritten forms & W-9s
  • Phone receipt photos
  • Faxed & wet-ink contracts
  • Stamped BOLs & manifests
  • 35+ file types · 100+ languages

Modify literal documents programmatically — fill forms, check boxes, and flatten.

Auto-detect every field on a fillable or static PDF form, populate text inputs, checkboxes, dropdowns, multi-line fields, and character-per-box fields (like EINs or SSNs) from upstream Procedure variables or natural-language instructions, then flatten into a locked final PDF ready to upload or email.

Change literal business forms — W-9s, carrier claims, insurance apps, HR packets — without manual re-typing.

Editable Form PDFvendor_w9_and_ach_form.pdf

3 pages · 48 detected fields · EIN boxes + checkboxes

FORM W-9 + ACH48 detected fields
1. Legal business name (text)Brightline Logistics LLC
3a. Tax classification (checkbox)
☐ Individual☑ LLC☐ C Corp
Part I. EIN (character-per-box)
12–3456789
Part II · Signature lineFlagged · preserved unsigned
Edit & fill PDFs→
Edited & Flattened PDFvendor_w9_filled_final.pdf
PDF
vendor_w9_filled_final.pdf/Downloads/vendor_w9_filled_final.pdf
Flattened ✓
Fields populated47 / 48
Flattened PDFLocked · final
Signature safety1 block flagged
Schema or natural-language editPasses straight to portal upload or email
  • Auto-detects text, checkbox, radio, dropdown & char-per-box fields
  • Fill via repeatable schema (up to 300 fields) or plain-English instructions
  • Flatten completed PDFs into locked, non-editable final documents
  • Preserves existing digital signatures & flags unsigned signature blocks
File formats
35+ types (PDF, scans, Office, CSV, .eml)
Languages
100+ printed & handwritten languages
PDF form editing
Up to 300 fields + flatten to final PDF
Extraction & routing
100 typed fields · 25 categories · auto-loop

How it works

Configure once. Test on a real file before running.

Every File processing card is configured and verified against your real digital or scanned physical documents inside the editor.

  1. PDFJPGXLSXEML
    file_path · ≤ 7 MB
    1

    Fetch digital or physical files

    Pull files from Google Drive, email inboxes, non-API web portals, on-prem scanner shares, or scheduled automatic exports — PDFs, phone photos, copier scans, Office docs, CSV, HTML, XML, and .eml.

  2. ExtractSplitFill
    StandardHigh accuracy
    2

    Pick an operation & accuracy

    Choose Parse / Read text, Extract fields, Edit & fill PDF form, Split into documents, or Classify document — chain with AI Summary or Verification, and pick Standard or High accuracy.

  3. vendortotaldue_date
    Discover from file
    3

    Discover fields or form slots

    Define up to 100 typed fields or 25 categories, or drop a sample document so Stepwork auto-discovers extraction fields and editable PDF form slots for you.

  4. scan_0031.pdfLive pipeline · 3 fields read
    4

    Test on the live pipeline

    Drop a real sample scan or PDF into the modal and inspect exact parsed text, confidence scores, split pages, or the edited PDF before saving the card.

  5. Rule logicLoop per documentEnter bill in ERP
    5

    Deliver anywhere or loop

    Send edited PDFs, split files, summaries, or extracted JSON to other flows, Google Drive, data warehouses, data lakes, databases, REST APIs, ERPs, or Slack Approvals.

Sources & destinations

Fetch from anywhere. Deliver anywhere.

Because File processing runs inside a Stepwork Procedure, it is never trapped behind an API integration. Pull digital files or scanned physical documents from email, Google Drive, non-API portals, on-prem desktop systems, or scheduled exports — then route edited PDFs, separated documents, summaries, or extracted data to warehouses, data lakes, databases, Drive, ERPs, or any API.

Combine any file source on the left with any destination on the right — no custom connectors required.

Pull files from

  • Google Drive & cloud foldersCloud storage

    Pull PDFs, mailroom scans, phone photos, and spreadsheets from Drive, SharePoint, Box, or Dropbox.

  • Emails & shared inboxesInbox

    Ingest .eml files, scanned attachments, and signed contracts from Gmail, Outlook, or intake mailboxes.

  • Non-API web portalsNo API needed

    Sign into bank, carrier, healthcare, supplier, or government portals and click Download for you.

  • On-prem & scanner sharesOn-prem

    Fetch physical copier scans, legacy ERP exports, SAP GUI files, and VPN-only local network shares.

  • Scheduled automatic exportsScheduled

    Trigger daily, weekly, or month-end report exports automatically without manual clicks.

Stepwork ProcedureFetch · Process · Route
File processing card
  • Parse
  • Extract
  • Edit PDF
  • Split
  • Classify
  • Summarize
5 sources→5 destinations

Send files or data to

  • Data warehouses, lakes & databasesData stack

    Load parsed CSVs, large tables, and JSON into Snowflake, BigQuery, Databricks, S3 data lakes, Postgres, or MySQL.

  • Google Drive & cloud archivesCloud storage

    Rename, organize, and file split PDFs, edited/flattened forms, searchable OCR PDFs, or raw exports.

  • REST APIs & webhooksAPI handoff

    Pass edited or split files, Markdown, summaries, or cited JSON straight to internal endpoints via API.

  • ERPs, CRMs & portalsApp execution

    Enter bills, update records, or upload edited and flattened PDFs back into NetSuite, SAP, Salesforce, or portals.

  • Email, summaries & Slack approvalsHuman loop

    Deliver filled packets by email, trigger Slack sign-off, or post page-cited AI document summaries.

Every document operation in practice

From raw paper scans to edited PDFs and summaries.

Watch each document operation work directly inside a Stepwork Procedure — wired over typed ports into downstream apps, loops, approvals, and data stores.

Extract structured fields

Pull typed fields and huge tables from physical scans and photos.

Define the exact fields you need — text, number, boolean, date, currency, list, or nested table arrays — or run one-click field discovery on a sample scan. Every field becomes a typed output port alongside extracted_json, backed by confidence scores and page citations.

What it outputs

  • Up to 100 typed fields per card, large multi-page tables, plus full extracted_json
  • Reads printed text, ballpoint handwriting, checkboxes, rubber stamps, and wet-ink signatures
  • Per-field confidence scores and bounding-box source citations for audit trails
  • Standard or High accuracy depending on scan quality and layout complexity
THE PINE TAVERNmerchant · The Pine Tavern
412 Pine St · Seattle, WA
Server: AnaTable 12
10/28/2026date · Oct 28, 20268:42 PM
2 Ribeye96.00
1 Caesar salad14.00
1 Fries9.00
2 Sparkling water8.00
1 Espresso4.00
Subtotal131.00
Tax11.46
Tip26.00tip · $26.00
Total168.46total · $168.46
VISA **** 4821APPROVED
xA Moreno
THANK YOU
File processing

Read receipt photos

IMG_4182.jpg

Extracted variables

  • merchant
  • date
  • tip
  • total
RampCreate expense
Handwritten tip and total read
File processing

Edit & fill vendor W-9

Edit & fill PDFUp to 300 fields · Flatten

Input variables

  • File (W-9 PDF)
  • legal_name
  • tax_class
  • ein

Output variables

  • filled_file_path
  • filled_values
Form W-9Request for Taxpayer Identification Numberw9-filled.pdf
1 · Legal name (text)—
3a · Tax classification (checkbox)
Individual LLC C Corp
Part I · EIN (text)—
Part II · Signature fieldUnsigned
Flagged · signature unsupported
Populating PDF text, checkbox, and choice fields…

Edit & fill PDF forms

Edit, populate, and flatten literal PDF forms without re-typing.

Upload any fillable or static business PDF to detect its fields automatically, map upstream Procedure variables into text boxes, checkboxes, dropdowns, and character-per-box fields (up to 300 fields), and output a ready-to-send or flattened filled_file_path.

How PDF editing works

  • Detects and edits text, checkbox, dropdown, multi-line, and character-per-box (EIN/SSN) fields
  • Populate deterministically by schema (up to 300 fields) or plain-language instructions
  • Flatten completed PDFs into locked final copies while preserving valid signatures where supported
  • Automatically flags unsigned signature blocks instead of guessing, outputting filled_file_path

Split & separate documents

Separate physical batch scans into individual files and loop per doc.

Mailrooms, closing binders, and AP copier trays routinely pack ten physical documents into one PDF. Split into documents detects visual headers, layout breaks, and unique identifiers — saving each separated file into Downloads and looping downstream cards once per document.

How separation works

  • Separates mixed physical packets or 50 repeated invoices by unique invoice # or member ID
  • Saves clean individual files into a <stem> documents folder inside the container's Downloads
  • Outputs file_path, filename, category, start_page, end_page, identifier, and document_count
  • Linking any per-document output automatically loops every downstream step once per file
File processing

Split inbound packet

Split into documents18 pages → 3 files

Per-document outputs

  • file_path
  • category
  • identifier
File processing

Extract document fields

Extract fieldsRuns per file

Input variables

  • File

Outputs

  • extracted_json
Execution
NetSuite

File record in NetSuite

Input variables

  • Record fields
closing-packet.pdf (18 pages) → closing-packet documents/
File processing

Classify incoming file

Classify documentUp to 25 categories

Input variables

  • File

Output variables

  • category
  • confidence
Rule logic

Route by category

Input variables

  • category

Paths

  1. If category equals Vendor InvoiceThen: Enter bill in QuickBooks
  2. OtherwiseThen: Vendor & legal intake
Enter AP billQuickBooks Online
Vendor & legal queueRoute W-9s & contracts
scan_0031.pdf → Vendor Invoice (0.99)

Classify & route documents

Sort incoming physical scans and attachments into the right branch.

Name up to 25 document categories in plain language. Vision-based classification reads visual layouts, logos, and text cues — returning the matched category and numerical confidence score so Rule logic branches cleanly and escalates edge cases to humans.

How routing works

  • Define up to 25 custom categories in plain language — no training code required
  • Visual layout recognition works on image-only scans and phone photos (IMG_4182.jpg)
  • Outputs category and numerical confidence ports ready for Rule logic thresholds
  • Route low-confidence or unknown files straight to a Slack review or Approval card

Parse & read documents

Parse complex layouts, tables, and charts into clean Markdown & text.

When you need complete document contents — multi-page contracts, rate tables, financial charts, policy packets, or handwritten field logs — layout-aware parsing returns clean text, Markdown blocks, and page_count ready for AI, Scripts, or searchable OCR PDFs.

What layout parsing captures

  • Preserves exact reading order across multi-column pages, merged tables, and footers
  • Captures charts, diagrams, checkboxes, stamps, formulas, and 100+ languages
  • Can embed a searchable OCR layer directly into scanned physical PDFs
  • Feeds cleanly into AI cards, Python/JS/Bash Scripts, or vector/warehouse pipelines
PDFnorthwind-msa.pdf14 pages

6.2 Renewal Term. Agreement renews automatically unless either party provides 60 days prior written notice…

9.1 Service Levels. Provider maintains 99.95% monthly availability across production containers…

text · 18,420 charspage_count · 14
File processing

Parse vendor MSA PDF

Parse & readLayout · Tables · OCR

Input variables

  • File

Output variables

  • text
  • page_count
AI promptSummarize renewal clauses
ScriptParse SLA numbers in Python
SummaryLegal review digest
Reading full printed and handwritten text…
File processing

Parse & verify lease

Parse & read32 pp. · verified

Input variables

  • scanned_lease.pdf

Output variables

  • parsed_markdown
  • verify_status
Summary

Summarize key terms

Input variables

  • parsed_markdown

Output variables

  • executive_brief
  • renewal_deadline
Slack briefCited clauses + p. 4, 11
CRM deal noteRenewal date + CAM cap
Warehouse / APIStore brief + trust status
Parsing 32-page scanned lease tables and clauses…

Summarize & verify

Turn dense multi-page documents into cited briefs and trust checks.

Chain layout-aware parsing directly into Stepwork AI and Summary cards to distill 30-page contracts, claims packets, or board reports into page-cited briefs, renewal dates, and risk flags — paired with confidence and tamper verification before downstream actions run.

What downstream teams get

  • Page-cited executive briefs, redline digests, and key clause / renewal date callouts
  • Summarizes multi-page financial schedules, rate tables, and embedded charts accurately
  • Pairs with confidence checks and tampering / post-signature verification signals
  • Posts structured summaries directly to Slack, CRM deal notes, email, or your data warehouse

Built for real-world documents

Physical scans. Production scale. Zero guesswork.

Engineered for messy operational reality — from crumpled paper receipts and 200-page mailroom scans to strict compliance logs.

  • Physical scans, handwriting & 35+ formats

    Processes copier scans, tilted phone photos, faxes, ballpoint handwriting, rubber stamps, and wet-ink signatures alongside PDFs, Office docs, spreadsheets, and .eml files in 100+ languages.

  • Layout-aware tables, charts & OCR

    Hybrid computer-vision layout models preserve merged multi-page tables, checkboxes, formulas, and charts — and can embed searchable OCR straight back into scanned PDFs.

  • Confidence scores, citations & verification

    Per-field confidence scores and bounding-box source locations show where every value came from, with tampering and post-signature checks to catch altered documents before acting.

  • Standard & High accuracy modes

    Run fast Standard mode for crisp digital PDFs and bulk exports, or switch to High accuracy vision models for dense scans, handwriting, skewed photos, and complex forms.

  • Live-pipeline sample testing

    Drop a real sample scan or PDF inside the editor to auto-discover fields or form slots and inspect exact parsed text, split pages, or filled PDFs on the live pipeline before saving.

  • Explicit flags & metadata-only logs

    Unreadable pages, missing fields, or unsigned signature blocks surface clear status codes. Run records store timing and counts — keeping sensitive tax, HR, and legal contents out of logs.

Where teams use it

From physical paper stacks and portal exports to closed records.

Pull digital files or scanned physical documents from emails, Google Drive, non-API portals, and on-prem scanner shares — parse, edit, split, classify, and summarize — then deliver anywhere.

Scheduled Exports & Data Pipelines

  • Scheduled export → Warehouse & LakeParse & extract

    Nightly non-API portal → Snowflake & S3

    On a schedule, sign into a bank or supplier portal with no API, trigger the daily PDF/CSV/XLSX export, parse multi-page tables, and load straight into Snowflake, BigQuery, or an S3 data lake.

  • On-prem → Drive & DatabaseParse & read

    On-prem ERP export → Google Drive & Postgres

    Pull weekly inventory or GL reports from a VPN-only desktop system, validate totals with a Script card, archive to Google Drive, and upsert clean rows into Postgres.

  • Non-API portal → APIExtract fields

    Legacy portal file → internal API

    Download PDFs, CSVs, or XML statements from a portal with no API and pass the fetched file or cited JSON straight to internal endpoints via an API card.

Finance, AP & Mailroom

  • Physical scan → Drive & ERPSplit & separate

    Physical mailroom stack → per-invoice loop

    Pull a 30-page copier scan of mixed paper invoices, checks, and W-9s from a local scanner share, separate each document by invoice #, archive to Drive, and enter every bill automatically.

  • Email / Photo → ERPExtract & verify

    Handwritten receipts & scans → Slack Approval → ERP

    Extract vendor, line items, and totals from crumpled receipt photos or scanned PDFs with confidence citations, verify totals, route for Slack Approval, and enter in NetSuite or QuickBooks.

  • Scheduled export → WarehouseExtract fields

    Month-end statements → data warehouse

    Schedule automatic month-end statement downloads from bank and card portals, parse multi-page transaction tables, and load reconciliation tables into Snowflake.

Operations, Logistics & Supply Chain

  • Physical scan / Portal → Drive & ERPSplit & separate

    Stamped physical BOLs → split & archive

    Download or scan physical freight packets with handwritten delivery notes and stamps, split into individual bills of lading, match shipment IDs against ERP POs, and archive each BOL in Drive.

  • ERP → Non-API portalEdit & fill PDF

    Carrier claim forms → edit, flatten & upload

    Auto-fill and flatten carrier PDF claim forms with order IDs, item counts, checkboxes, and dates from your ERP, then upload the finished PDF straight back into the carrier portal.

  • On-prem → APIExtract fields

    On-prem WMS manifests → partner API

    Fetch nightly shipping manifests from an on-prem warehouse system, parse tables, and deliver structured JSON to 3PL or customer APIs.

Legal, Security & Compliance

  • Physical scan / Email → Slack & CRMSummarize & verify

    Scanned 30-page MSA → page-cited Slack summary

    Parse wet-ink signed contracts arriving by email or scan, verify signature integrity, summarize renewal windows and liability caps with page citations in Slack, and update Salesforce.

  • Drive → Searchable Drive archiveSplit & OCR

    Physical closing binder → separated archive

    Split 40-page scanned legal binders from Google Drive into separate named agreements, embed searchable OCR, and organize each file cleanly into Drive or SharePoint folders.

  • Scheduled export → VantaExtract fields

    Scheduled SOC 2 & audit evidence

    Run scheduled procedures to export access reports and compliance PDFs from internal tools, extract attestation dates, and upload artifacts to Vanta or Drata.

HR, Healthcare & People Ops

  • HRIS → Drive & EmailEdit & fill PDF

    HRIS records → edited & flattened onboarding PDFs

    Edit and populate tax, direct deposit, and policy PDF forms (including SSN/EIN boxes and checkboxes) from Workday or Rippling, flag signature lines for sign-off, and archive in Drive.

  • Physical scan → DatabaseClassify & extract

    Handwritten intake forms → EHR / database

    Classify and extract handwritten paper patient or employee intake scans from a shared inbox or copier folder, route low-confidence items for review, and write clean rows to your database.

  • Drive → Slack & EmailSummarize

    Benefits & policy packets → AI summary in Slack

    Parse updated benefits PDFs and rate tables stored in Drive or SharePoint and deliver a clear employee-ready summary to Slack and email.

Sales, RevOps & Customer Intake

  • Email → CRM, Slack & APIExtract & summarize

    Signed order forms → CRM, summary & billing API

    Extract SKUs, seats, billing terms, and start dates from scanned or digital order PDFs, post a deal summary in Slack, update Salesforce, and trigger provisioning via API.

  • Scheduled export → WarehouseParse & extract

    Partner portal exports → BigQuery

    Schedule automatic weekly exports from channel or partner portals without APIs, parse messy tables and spreadsheets, and load reporting rows into BigQuery or Snowflake.

  • Portal / Email → Drive & APIClassify & verify

    Customer KYC, COI & W-9 packet intake

    Classify incoming W-9s, COIs, and KYB scans from email or portals, verify document authenticity, archive originals in Google Drive, and POST verified JSON via API.

Explore all Procedure cards

Explore related pages

  • Extractions deep dive
  • Month-end close & collections
  • Vendor renewal management
  • Employee onboarding
  • Warehouse & delivery ops
  • Investor data rooms

FAQ

Questions about file processing

  • Yes. Businesses routinely scan paper mailroom stacks, crumpled receipts, handwritten W-9s, faxed contracts, and stamped bills of lading into email, Google Drive, or an on-prem copier folder. Stepwork's vision-language document engine reads printed text, handwriting, checkboxes, rubber stamps, tables, charts, and signatures across rotated scans and phone photos — and can separate a combined paper scan into individual named files or embed searchable OCR back into the PDF.
  • Stepwork detects fillable and static PDF form fields — text boxes, checkboxes, radio buttons, dropdowns, multi-line fields, and character-per-box inputs like EINs and SSNs (up to 300 fields per PDF) — and populates them from upstream Procedure variables or plain-language instructions. Completed PDFs can be flattened into locked final files, existing digital signatures can be preserved where supported, and unsigned signature blocks are automatically flagged for human sign-off rather than guessed.
  • Yes. Layout-aware parsing turns dense multi-page PDFs, scanned contracts, financial tables, and embedded charts into clean Markdown and text preserving exact reading order. Passing that output into Stepwork's AI and Summary cards generates executive briefs, renewal-term digests, and risk callouts grounded in page numbers — ready to post to Slack, email, CRM notes, or your data warehouse.
  • Because File processing runs inside a Procedure with its own local container filesystem, an upstream Execution, Webhook, or Schedule step can fetch files from virtually anywhere: Google Drive, SharePoint, Dropbox, and Box; Gmail, Outlook, and shared inboxes; non-API web portals (banks, carriers, healthcare, suppliers, government sites); VPN-only on-prem desktop apps and physical scanner shares; or scheduled automatic exports triggered daily, weekly, or at month-end.
  • Downstream Procedure cards can pass raw, split, or edited/flattened files and structured outputs to other flows and Procedures; archive files into Google Drive, SharePoint, Dropbox, or web portals; load structured rows and JSON into data warehouses (Snowflake, BigQuery, Redshift), data lakes (S3, Databricks), and databases (Postgres, MySQL, SQL Server); POST files or payloads via an API card; enter records into ERPs and CRMs; or deliver summaries and packets over email and Slack.
  • Vision and semantic boundary detection splits combined multi-document PDFs (like a 30-page copier scan or 50 invoices in one file) by detecting new headers, layout shifts, mid-page breaks, or unique identifiers such as invoice numbers. Stepwork saves each separated file into a dedicated folder inside Downloads and emits per-document ports (file_path, filename, category, start_page, end_page, identifier, document_count) — linking any port automatically loops downstream cards once per document.
  • File processing handles 35+ file formats across 100+ languages, including PDFs, scanned documents, phone photos (PNG, JPG, TIFF, HEIC, WebP, SVG, BMP, GIF, PSD), Office documents (DOCX, DOC, XLSX, XLS, PPTX, PPT, ODT, ODS), CSV, plain text, HTML, XML, RTF, Markdown, and .eml emails.
  • Extractions and classifications expose numerical confidence scores and page bounding-box citations so you can branch low-confidence files to Slack Approval or human review via Rule logic. You can also test any card on a real sample file inside the editor on the live pipeline, toggle Standard vs. High accuracy, and flag missing fields, unsigned signature blocks, or tampered/altered documents before downstream systems update.
  • Extractions read live tables, lists, grids, and values directly from application screens (including multi-page pagination up to 100 pages). File processing operates on files — digital exports and scanned physical documents, photos, spreadsheets, and emails — to parse, extract fields, edit and flatten PDFs, split batch scans, classify, and summarize. Many Procedures use both together.

See it run on a process you already repeat

Bring one. We will show you what it looks like as a flow and what each run records.

Book a Demo
Stepwork

Deterministic agents for work that must run the same way every time.

Product

  • Procedure
  • Extractions
  • File processing
  • Marketplace

Solutions

By team
  • IT
  • Security & Compliance
  • Finance & Accounting
  • Sales & RevOps
  • Operations
  • HR & People
By industry
  • Healthcare
  • 3PL and warehousing
  • Freight and trucking
  • Fuel and convenience stores
  • Construction
  • Manufacturing and distribution
  • Accounting firms
  • Field services and trades
  • MSPs

Capabilities

  • Deterministic Agents
  • Stepwork MCP
  • Containers
  • Ask Bob

Company

  • ROI
  • Security
  • FAQ

Resources

  • Calm Case Study
  • Claude Co-Work Alternative
  • Free IT Ticket Analysis
  • Stack check
  • For AI tools (llms.txt)

Legal

  • Terms and Conditions
  • Privacy Policy
  • Data Processing Agreement
  • Subprocessors

Ask your AI about this page

  • ChatGPT
  • Claude
  • Perplexity

2261 Market Street #4481, San Francisco, CA 94114, USA

Loot Discount inc dba Stepwork

© 2026 Stepwork. All rights reserved.