סקירה סקירה חדשות חדשות
שיתוף

Build your first Document AI app with a single prompt.

Paste llms.txt
Prompt what should be built
Get the finished code
Made for coding agents. Less API research, more focus on product and outcome.
1 · Access

How would you like to start?

2 · llms.txt

Give PaperOffice to the coding agent

AI-readable PaperOffice API specification https://api.paperoffice.ai/latest/docs/llms.txt
Use with
  • Cursor
  • Claude Code
  • Codex
  • AI Coding Agents
3 · Prompt

Copy the instruction and paste it

Ready Document AI build instruction 
Read in full:
https://api.paperoffice.ai/latest/docs/llms.txt

Task:
Build, run and verify a production-ready Document AI batch web app with PaperOffice AI-OCR.

Access:
Demo mode:
Use the preprocessed responses and Sandwich PDFs from this manifest: https://paperoffice.ai/demos/ai-ocr/batch/manifest.json
Clearly label the mode as a static demo. Never claim live processing.

Synthetic batch source files:
- https://paperoffice.ai/demos/ai-ocr/batch/sample1-source.jpg
- https://paperoffice.ai/demos/ai-ocr/batch/sample2-source.jpg
- https://paperoffice.ai/demos/ai-ocr/batch/sample3-source.jpg

Preprocessed demo artifacts:
- Responses: https://paperoffice.ai/demos/ai-ocr/batch/sample1-response.json | https://paperoffice.ai/demos/ai-ocr/batch/sample2-response.json | https://paperoffice.ai/demos/ai-ocr/batch/sample3-response.json
- Sandwich PDFs: https://paperoffice.ai/demos/ai-ocr/batch/sample1-searchable.pdf | https://paperoffice.ai/demos/ai-ocr/batch/sample2-searchable.pdf | https://paperoffice.ai/demos/ai-ocr/batch/sample3-searchable.pdf
- Complete package: https://paperoffice.ai/demos/ai-ocr/batch/paperoffice-aiocr-batch-demo.zip

Requirements:
- Download and process all three source JPGs together as one batch
- Run AI-OCR Complete with ocr_mode=complete, output_searchable_pdf=true, processing_lane=instant and client_wait=true
- Call the documented endpoint once per file; send every live upload as multipart/form-data in file_1
- Coordinate the three jobs as one batch and show per-file progress and partial results
- In demo mode, use only the preprocessed responses and PDFs without new API processing
- Fully implement upload, processing, HTTP 202 polling, errors and result
- For every file, render and offer downloads for the source JPG, OCR text, bounding boxes, response and Sandwich PDF
- Offer individual downloads and the complete demo batch download
- Use only endpoints documented in llms.txt
- Do not invent APIs, fields or download URLs

Result:
Implement the complete batch app, start it and verify all three source files.
  1. 1 Paste into the coding agent
  2. 2 Run the generated app
4 · Result

This is what the completed three-file batch looks like

3 synthetic source files
Synthetic invoice 1 Download source JPG
Synthetic invoice 1
OCR mode
Complete (Ultra)
Pages
1
Detected language
English (en)
Text lines
260
Characters
2728
Bounding boxes
260
Average confidence
98%
Download source JPG Download response Download Sandwich PDF
Successfully processed Batch 1/3 · AI-OCR Ultra
GET STARTED

Now try it yourself

Continue directly with the selected access mode.

Try visitor mode now
Show optional technical details

Only needed for debugging or manual verification. The AI-first path above does not require copying this code.

Underlying request 
curl -O "https://paperoffice.ai/demos/ai-ocr/batch/sample1-source.jpg"
curl -O "https://paperoffice.ai/demos/ai-ocr/batch/sample2-source.jpg"
curl -O "https://paperoffice.ai/demos/ai-ocr/batch/sample3-source.jpg"

for file in sample1-source.jpg sample2-source.jpg sample3-source.jpg; do
  curl -X POST "https://api.paperoffice.ai/latest/job/add/paperoffice_aiocr___generate" \
    -H "Authorization: Bearer po_ut_YOUR_API_KEY" \
    -F "file_1=@${file};type=image/jpeg" \
    -F "ocr_mode=complete" \
    -F "output_searchable_pdf=true" \
    -F "processing_lane=instant" \
    -F "client_wait=true"
done
Response fixture
{
  "status": "success",
  "demo_fixture": true,
  "synthetic_documents": true,
  "live_processing": false,
  "batch_size": 3,
  "manifest": "/demos/ai-ocr/batch/manifest.json",
  "download_all": "/demos/ai-ocr/batch/paperoffice-aiocr-batch-demo.zip",
  "responses": [
    "/demos/ai-ocr/batch/sample1-response.json",
    "/demos/ai-ocr/batch/sample2-response.json",
    "/demos/ai-ocr/batch/sample3-response.json"
  ],
  "searchable_pdfs": [
    "/demos/ai-ocr/batch/sample1-searchable.pdf",
    "/demos/ai-ocr/batch/sample2-searchable.pdf",
    "/demos/ai-ocr/batch/sample3-searchable.pdf"
  ]
}

היכן תרצו לנסות את PaperOffice?

להירשם בחינם פתיחת היישום יישום PaperOffice המוצר המלא: ווב, שולחן עבודה ונייד. לכידה, ארגון, חיפוש ועבודה על מסמכים עם הצוות. נדרש חשבון חינם פתיחת Playground Playground נסו פונקציות נבחרות מיד — ללא רישום, עם מפתח API להדגמה מוגבל. ללא הרשמה, אך עם מפתח API להדגמה מוגבל