AI tool for extracting claims

Automate the reading of your claims thanks to AI: file number, date, date, nature, amount, documents... Data ready to be integrated into your business tools.

50 free credits

No credit card

100% secured

Insurance
ClaimInsurance
Claim

The best teams work with Koncile

logo Kuhn
logo Sightness
logo demathieu bard
logo SpendHQ
logo Giesper
logo Beal
logo Cosma
logo skyrm

Why automate claim management?

Insurance claims often arrive as PDFs or low-quality scans. Koncile’s AI-powered OCR automatically extracts key data, structures it, and thus facilitates pre-sorting, analysis, and rapid file creation.

Workflow Extraction Insurance
Claim

Koncile automates the intelligent extraction of contractual data. Despite the complexity of our clients’ contracts, the tool ensures quality and speed, saving us valuable time.

What fields are detected by the Koncile OCR tool?

Koncile extracts key data from a claim form or letter and delivers it in a structured format.

This enables intelligent document processing, accelerates validation, and ensures reliable recording of claims within your systems.

Need to extract specific fields? The model is fully customizable to your business needs.

Name

Type

Example

Guideline

Validité

Text

Oui

Vérifie que le RIB est bien constitué des éléments suivants :
- Code banque (5 chiffres)
- Code guichet (5 chiffres)
- Numéro de compte (11 caractères alphanumériques)
- Clé RIB (2 chiffres)
Si les RIB est bien constitué de ces éléments, choisis la valeur "Oui". Sinon choisis la valeur "Non".

Claim number

Number 03982794 Unique identifier assigned to the claim

Reporting date

Date 15/05/2025 Date the claim was reported

Location of loss

Text 12 rue des Lilas, Paris Precise address where the disaster occurred.

Date of loss

Date 12/05/2025 Date on which the disaster occurred.

Description of loss

Text Living Room Water Damage Complete and accurate description of damage or events.

Estimated damage

Currency 5,000.00 Financial estimate of the damage caused.
Flèche courbée vers le haut.

Add any extraction field

Flèche courbée vers le haut.

Edit AI instructions

Why choose Koncile to process insurance documents?

Extraction home insurance

Custom insurance data extraction

A simple and intuitive interface to precisely select the fields to extract from your insurance documents.

Automatically identify key information such as policy numbers, validity dates, insured parties, indemnified amounts, claim references, and more.

Eliminate manual entries and speed up case processing with data extraction perfectly tailored to your business workflows.

99% reliability

Accuracy for your insurance documents

With a success rate above 99%, our OCR engine delivers exceptional accuracy on key insurance document fields.

Every detail: contract numbers, validity dates, claim amounts, or claim references is captured with high reliability.

Thanks to our built-in anomaly detection system, errors or inconsistencies are flagged early, enabling automated quality control and faster decision-making.

Multilingual OCR insurance

Multilingual recognition of insurance documents

Our OCR engine, enhanced by advanced language models (LLM), accurately recognizes alphabets and languages from around the world.

Chinese, Arabic, Cyrillic, Japanese… whatever the format or language of the document, Koncile identifies key fields and enables automatic translation.

Scan, extract, and centralize your data with ease, even in a complex multilingual environment.

Handwritten amicable report

Handwriting detection for insurance documents

Our handwriting OCR accurately detects and interprets handwritten text, even under challenging conditions such as low-quality scans, incomplete forms, or difficult-to-read handwriting.

The tool supports multiple handwritten languages and relies on AI models trained to recognize a wide variety of writing styles.

Ideal for processing claim declarations, handwritten statements, supporting documents, or hand-filled enrollment forms while maintaining a high success rate.

scanned insurance certificate

Insurance documents scanned or photographed

Whether scanned, photographed, or submitted by policyholders, your insurance documents are converted into usable data with remarkable reliability thanks to our OCR technology.

Even old contracts, handwritten declarations, blurry or poorly framed documents can be accurately analyzed thanks to our automatic correction engine.

Unrecognized fields are isolated and sent to our control center for manual validation or processing, ensuring a high level of completeness and reliability in your insurance workflows.

Insurance integration

Integrated with your tools for insurance documents

Koncile integrates perfectly into your digital ecosystem: connection via API, automatic import from your emails or direct synchronization with your ERP.

Easily import documents, trigger automated extractions, and retrieve structured data where you need it.

Whether you use Excel, Outlook, SAP or another business tool, Koncile adapts to your workflow to simplify document management and maximize your productivity gains.

Logo de Koncile.

Test new generation data extraction

Start with a ready-to-use model, test on a document and scale

Créez vos modèles d’extraction, testez sur un premier document et passez à l’échelle !

The benefits of an OCR data capture tool

Intelligent reading of all declaration formats

Koncile reads claims from PDF forms, photos, emails or scanned documents — even handwritten or poorly structured.

Targeted extraction of critical data

Claim number, type of incident, date, estimated amount, insured contact information, contract number, and associated supporting documents.

Seamless integration into your insurance tools

The extracted data is ready to use, exportable in JSON, Excel or via API to your claims management tools, CRM or treatment platforms.

Automating pre-sorting and filing

Automatically categorize and assign cases according to their type, priority, or completeness. Ideal for saving time in the back office or on high-volume platforms.

Processing of related supporting documents

Link photos, findings, expert reports or other supporting documents to the right files, for complete and centralized processing.

The OCR API for automate your PDF data capture

status

string

Document status, which can be DONE, DUPLICATE, or IN PROGRESS.

document_id

integar

Unique number assigned to each invoice

general_fields

objects

General fields that appear only once in each extracted document. Returned in the format: {field name: extracted value}

line_fields

objects

Repeated fields extracted in bulk for each line or table. Returned in the format: {field name: extracted value}

status

string

Statut du document qui peut être DONE, DUPLICATE, IN PROGRESS.

document_id

integer

Numéro unique attribué pour chaque document

general_fields

objects

Champs généraux apparaissant une seule fois dans chaque document extrait. Retour au format : {nom du champ: valeur extraite}

line_fields

objects

Champs répétés extraits en bloc pour chaque ligne ou chaque tableau. Retour au format : {nom du champ: valeur extraite}

Request

curl api.koncile.ai/tasks/{task_id}/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY"
response = requests.get(f"{api_url}/tasks/{task_id}/",
headers={"accept": "application/json", "Authorization":{"Bearer{api_key}"})

Response

{
"status": DONE | DUPLICATE | IN PROGRESS | FAILED,
"document_id": ID,
"document_name": "name",
"status_message": "",
	"General_fields":
		{
		"Date" : {"value": "05/08/2022", "confidence_score": 0.99},
		"Price" : {"value": "$23", "confidence_score": 0.98}
		}
	,
	"Line_fields":
		{
		"Date" : [{"value": "05/08", "confidence_score": 0.97}, {"value" : "05/08", "confidence_score": 0.98}, ],
		"Price" : [{"value": "$23", "confidence_score": 0.98}, {"value": "$12", "confidence_score": 0.97}],
		}
}

An AI OCR designed for security

No training on your data

Fully encrypted software

Secure storage of extracted data

RGPD compliant

Cadenas noir entouré d'étoiles noires.

Discover all the documents to be automated

SEE ALL TEMPLATES
Rental liability insurance certificate

Insurance

Name of the insured, address of the property, contract number, warranty period, coverage amount

Amicable Auto Report

Insurance

Vehicles, dates, damages, signatures, signatures, signatures, signatures, circumstances, sketches, checked areas

Certificate of
Liability Insurance

Insurance

Type of insurance, guarantees, amounts, deadlines, deductibles

Home insurance certificate thumbnails

Insurance

Proof of insurance coverage

Any question?

Contact us at contact@koncile.ai, check out our documentation, or book a demo.

How does OCR extract information from an insurance claim?

Koncile OCR identifies the essential data of a claim, such as the name of the declarant, the nature of the claim, and the amounts declared for compensation.

Can OCR process a printed or handwritten insurance claim?

Yes, Koncile OCR is capable of processing printed or handwritten claims. It uses advanced character recognition to ensure accurate data extraction.

Can I extract specific information from an insurance claim?

Yes! You can retrieve only fields such as the date of the claim, applicable guarantees, or insurance contract references, depending on analysis needs.

In what format should I import an insurance claim report for OCR analysis?

You can upload your claim in the format PDF, PNG, or JPEG. These formats are compatible with our OCR and allow detailed extraction of information related to the incident.

How does OCR integrate with my existing tools and software?

The software is accessible via a powerful API, with comprehensive documentation available. Plus, you can upload documents directly into the app and export the extracted data to XLSX, XLS, CSV, or JSON for seamless integration into your workflows.

I need further assistance.

Check our API documentation, contact us at contact@koncile.ai. You can also create a demo account or book a demonstration with our team.

What are Koncile's prices?

Koncile offers 3 plans, including enterprise options for handling large volumes of data. You can check our pricing on our pricing page.

What are general fields and repeated fields?

In each extraction template, you will find:

  • General fields: These are pieces of information that appear only once in each document (e.g., the invoice number or the invoice date).
  • Repeated fields: These are pieces of information that appear multiple times in a document, such as item descriptions or prices in each line of a quote. Use repeated fields for extracting tables and charts from your documents.