Exemples d’API à copier
Exemples de prompts pour Document AI et Data APIs — pour Claude, Cursor et votre IDE.
PaperOffice llms.txt — intégration dans Claude et Cursor, sans théâtre SDK.
- Coller llms.txt Dans Claude, Cursor ou votre IDE.
- Exprimer l’intention Ce qu’il faut construire — ou un prompt de cette page.
- Laisser écrire le code L’IDE livre l’intégration fonctionnelle.
Document AI
Copiez le prompt, collez-le dans Claude ou Cursor – terminé.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build me an invoice extractor that:
1. Uploads a PDF via POST /job/add/workflow (multipart, field file_1)
2. Uses idp_collection=invoice, processing_lane=instant (sync)
3. Reads every field from result.pages_idp[0].suggested_fields
(keys like _supplier_name, _total_amount, _invoice_date)
and the boxes from result.pages_aiocr.pages
4. Renders a verification view highlighting each value
at its bounding box position
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Extrayez les champs de la facture y compris la position dans le document.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Write a minimal script that:
1. Sends an image or PDF to POST /job/add/paperoffice_aiocr___generate
(multipart, field file_1)
2. Uses ocr_mode=complete and processing_lane=instant (sync)
3. Prints the extracted text from result ?? job_result (pages)
Modes: complete (+tables), grid (+bounding boxes), text (plain).
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Texte intégral via POST /job (ocr_mode=complete).
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a splitter for large batch PDFs (up to 3000 pages):
1. POST /job/add/workflow with template=pdf_ai_split (multipart, field file)
2. naming_instruction=Dokumenttyp_Datum_Absender,
locale=de_DE, processing_lane=instant
3. List every created document from the result
(suggested filename + page range)
The AI detects document boundaries automatically.
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Détectez les limites du document et nommez les fichiers de sortie.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Also use llms-full.txt for anonymize parameters (scenario, apply).
Build a GDPR anonymizer (preview → apply):
1. POST /job/add/workflow template=document_anonymize_preview (field file)
2. Set scenario=gdpr_auskunft (or externe_weitergabe / finanzdaten),
redact_categories=all, optional whitelist / custom_redact
3. client_wait=false then poll GET /job/get/{job_id}
4. Show detected_pii.redact_box_ids + simplified_boxes
5. Apply: POST /job/add/paperoffice_dataripper___redact_image
with files + bounding_boxes + redact_boxes from the preview
(or MCP: po_anonymization_pii_detect → po_anonymization_redaction_apply
with preview_job_id)
Optional one-shot: REST template=document_anonymize OR MCP po_anonymization_anonymize
(no HITL; pass scenario/whitelist).
Redact Agent: POST /documents/redact-agent-run or MCP po_documents_redact_agent_run.
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Détectez et rayez les noms, IBAN, adresses.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a text-to-speech generator:
1. POST /job/add/paperoffice_voice___tts with text=..., voice=Nadja,
output_format=mp3
2. output=url and processing_lane=instant for a synchronous audio link
3. Play or download the audio URL from result ?? job_result
Voices: Nadja, Thomas, Anna, Hans (DE) + 100+ more.
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Synchronisez MP3 via voice=Nadja (et plus).
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a contract extractor that:
1. Uploads a PDF via POST /job/add/workflow (multipart, field file_1)
2. Uses idp_collection=contract, processing_lane=instant (sync)
3. Reads parties, dates and notice period from
result.pages_idp[0].suggested_fields (value + bounding box)
4. Renders a verification view with bounding boxes
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Extrayez les champs du contrat y compris la position dans le document.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build an e-signature request flow:
1. Ensure the document has a pofid in PaperOffice
2. POST /signatures/create with document_pofid (or pofid)
and a signers array (name + email per signer)
3. Return the signature request id and status
4. Optionally POST /signatures/remind for pending signers
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Invitez les signataires et gérez le statut/les rappels.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a secure document delivery (digital registered mail):
1. POST /document_delivery/create_and_send with:
pofids: ["POFID_HERE"],
recipient_email, optional recipient_name,
subject, optional message
2. security_mode=link → PDF password in the same email
security_mode=secure_sms → link by email, password by SMS
(requires recipient_phone in E.164, e.g. +49170…)
3. Show delivery_id and that access events are logged
(Versandhistorie / delivery log)
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Livraison sécurisée avec mot de passe PDF (e-mail ou SMS) et journal de livraison.
Data & Security APIs
Géocodage, Météo, Empreinte digitale, TVA et plus encore — en tant que prompt.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a geocoding helper that:
1. Forward: GET /geocoding/forward?q=...&lang=de
2. Reverse: GET /geocoding/reverse?lat=...&lon=...
3. Autocomplete: GET /geocoding/autocomplete?q=...
4. Prints display_name, lat, lon and credits_billed
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Adresse ↔ coordonnées.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a weather lookup that:
1. Calls GET /weather/current?lat=...&lon=...&lang=de
2. Shows temperature, condition text and air quality if present
3. Displays credits_billed from the response
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Météo actuelle incluant la facturation.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build an IP intelligence client that:
1. Calls GET /ip2location/full (empty ip = visitor IP)
2. Extracts country, city, geo_lat/lon, ISP
3. Optionally chains weather from the same response
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Emplacement à partir de l'IP, météo optionnelle.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a device fingerprint check that:
1. Collects client signals in the browser
2. POSTs to /fingerprint/identify
3. Returns visitor_id / confidence for fraud checks
Auth: Authorization: Bearer po_ut_YOUR_API_KEY ID visiteur et confiance.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build an email risk checker that:
1. Validates an address via the Fake Email Detector endpoint
2. Flags disposable / role / invalid domains
3. Returns a clear allow/deny recommendation
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Courrier jetable et score de risque.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a VPN/proxy detector that:
1. Calls GET /ip2location/vpn?ip=...
2. Normalizes is_vpn, is_proxy, is_tor, is_datacenter flags
3. Shows a clear risk badge for the visitor
Auth: Authorization: Bearer po_ut_YOUR_API_KEY VPN, proxy, Tor, datacenter.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a VAT ID validator that:
1. Checks an EU VAT number via the VAT validator endpoint
2. Returns company name and address when valid
3. Handles invalid / not-found responses cleanly
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Validité et données d'entreprise.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a currency converter that:
1. Calls the currency exchange endpoint (from, to, amount)
2. Shows rate and converted amount
3. Caches the last rate for the UI
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Conversion avec taux en direct.
Pour Claude, Cursor & Co.
Prompts à copier-coller qui fonctionnent vraiment
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Create a Python script that:
1. Takes a folder of invoice PDFs
2. Extracts all fields using POST /job/add/workflow with idp_collection=invoice
3. Returns bounding boxes for verification (result.pages_aiocr)
4. Exports to CSV
Important: Use file_1 for uploads; fields live in result.pages_idp[0].suggested_fields.
Handle sync (HTTP 200 with result) and async (HTTP 202 → poll GET /job/get/{job_id}).
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Extraction par lots avec coordonnées de vérification.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Help me set up the MCP Server for PaperOffice in Cursor.
I want to use Document AI directly in my IDE.
Show me:
1. How to configure the MCP connection (URL https://mcp.paperoffice.ai/cursor)
2. Available tools via tools/list
3. How to process documents from my workspace
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Connectez MCP et traitez les documents de l'espace de travail.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Create a voice agent that:
1. Takes audio input (Speech-to-Text)
2. Processes the text
3. Generates audio response (Text-to-Speech)
Use these pipelines:
- STT: POST /job/add/paperoffice_voice___stt (audio_file)
- TTS: POST /job/add/paperoffice_voice___tts (text, voice=Nadja,
output_format=mp3, output=url)
- Use processing_lane=instant for a synchronous response.
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Traitez l'entrée vocale et répondez avec de l'audio.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a fraud detection system that:
1. Checks device fingerprints
2. Validates IP geolocation
3. Detects suspicious patterns
Use the Security & Data AI endpoints.
These are instant APIs (no polling needed).
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Vérifiez l'empreinte numérique de l'appareil et les signaux géo/IP.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Create a batch processor that:
1. Takes a folder of large PDFs (up to 3000 pages each)
2. Uses POST /job/add/workflow with template=pdf_ai_split
3. Uses naming_instruction for smart filenames
4. Handles async jobs (HTTP 202) by polling GET /job/get/{job_id}
Use locale=de_DE for German document types.
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Divisez les dossiers de grands PDFs de manière asynchrone.
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a document classifier that:
1. Watches a folder for new PDFs
2. Uses OCR (POST /job/add/paperoffice_aiocr___generate, ocr_mode=complete)
to extract text
3. Classifies into: invoice, contract, receipt, correspondence
4. Moves files to category subfolders
5. Logs results to classification_log.csv
Authenticate with: Authorization: Bearer po_ut_YOUR_API_KEY.
processing_lane=instant for a synchronous response. OCR, classez, triez dans des sous-dossiers.
End-to-End
Solutions complètes pour des problèmes réels
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build an accounts-payable pipeline:
1. Watch a folder for incoming invoice PDFs
2. Extract fields via POST /job/add/workflow (file_1,
idp_collection=invoice, processing_lane=instant)
3. Flag every field with confidence < 0.9 for manual review,
including its bounding box for the verification UI
(result.pages_idp[0].suggested_fields + result.pages_aiocr)
4. Export supplier, total, date and IBAN as CSV for the accounting import
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Téléchargement PDF → AI-IDP + Bounding Boxes → Validation → Exportation
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a contract analyzer:
1. Upload contracts via POST /job/add/workflow (file_1,
idp_collection=contract, processing_lane=instant)
2. Extract parties, start date, end date and notice period
from result.pages_idp[0].suggested_fields (each with a bounding box)
3. Store the key terms in a knowledge graph
4. Alert me 90 days before a notice period expires
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Téléchargement contrat → Termes clés → Knowledge Graph → Alertes
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a PDF converter service:
1. One pipeline per target format (field file_1):
POST /job/add/pdfstudio___pdf_to_word | pdfstudio___pdf_to_powerpoint |
pdfstudio___pdf_to_pdfa | pdfstudio___pdf_to_webp
2. processing_lane=instant for a synchronous response
3. Return the download URL from result ?? job_result
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Téléchargement PDF → Choisir format → Convertir → Télécharger
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a webhook event handler:
1. Register a webhook via POST /webhooks/subscribe
(url, events: ["job.completed", "job.failed"], secret)
2. Verify the HMAC-SHA256 signature of every delivery
with the subscription secret (see llms-full.txt, webhooks)
3. Process the payload whenever job.completed arrives
Note: webhooks always require a token (account binding).
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Enregistrer Webhook → Envoyer document → Recevoir événement → Traiter
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a document-to-audio pipeline:
1. OCR via POST /job/add/paperoffice_aiocr___generate
(file_1, ocr_mode=complete, processing_lane=instant)
2. Split the extracted text (result ?? job_result, pages) into 5000-character chunks
3. TTS per chunk: POST /job/add/paperoffice_voice___tts (text, voice=Nadja,
output_format=mp3, output=url, processing_lane=instant)
4. Save all returned audio URLs as a playlist
Auth: Authorization: Bearer po_ut_YOUR_API_KEY OCR du document → Préparer le texte → Générer TTS → Enregistrer audio
Prompt
Read this llms.txt (AI-optimized API docs):
https://api.paperoffice.ai/latest/docs/llms.txt
Build a batch OCR-to-CSV exporter:
1. Scan a folder for PDF/PNG/JPG/TIFF/WEBP files
2. For each file: POST /job/add/paperoffice_aiocr___generate
(file_1, ocr_mode=complete, processing_lane=instant)
3. Collect filename, page_count, text preview and confidence
4. Write everything to ocr_results.csv
Auth: Authorization: Bearer po_ut_YOUR_API_KEY Analyser le dossier → OCR par lots → Collecter le texte → Export CSV
Prochaine étape
Voici la suite
L'étape suivante recommandée dans le tunnel développeur et deux branches correspondantes.
Continuer avec l’API
llms.txt et Playground — sans détour.
