Extract key resume data with an AI-powered OCR

Koncile's AI OCR, a solution to extract and validate resume data, powered by AI, reliable, customizable, and available via API.

50 free credits

No credit card

100% secured

Examples of resumesExamples of resumes

The best teams work with Koncile

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

The OCR that identifies key information in resumes

Koncile’s resume OCR tool is adapted for KYC verifications, sorting, initial screening of candidates, content analysis, qualitative assessment, and identifying potential red flags.

Upload resumes in image or PDF format into Koncile's OCR software and receive structured data in spreadsheet, JSON format, or a machine-readable database.

Illustration diagram of the extraction model for resumes

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.

Complete field extraction with our OCR tailored for resumes

Koncile’s resume OCR solution captures standardized information that recruiters, HR managers, or hiring managers look for. It allows the creation of a resume database, categorizing candidates based on your PDF resumes.

You can not only capture all this information and convert it into the format of your choice but also analyze it automatically by comparing the candidate's profile to the job description or an internal evaluation grid.

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".

First and last name

Text John Doe First name(s) and last name

Position sought

Text HR Manager Why is this candidate applying for this position and at this company? Does the resume mention the reasons for the interest in the company or the sector? Summarize briefly.

Languages

Text French (Native language), Spanish (Professional proficiency), German (Intermediate), English (Fluent, TOEIC: 910) Put the level in parentheses if it is mentioned.

Type of experience

Multiple Professional experience "Professional experience," "Education," or "Other."

Title

Text HR Manager

Name of the organization

Text Gucci

Period

Text Jan. 2024 - Present

Details about the experience

Text Development of an annual training program for marketing teams Briefly summarize the experience.

Clarity of the resume

Boolean Yes Is the resume clear, concise, and coherent? Does the structure and formatting allow for a quick understanding of the career path? Are there any spelling or syntax errors?
Flèche courbée vers le haut.

Add any extraction field

Flèche courbée vers le haut.

Edit AI instructions

Why choose Koncile OCR for your resumes?

Tailor the extraction to your needs

Easily add or modify extraction fields in the Koncile parser interface using natural language.

Champ à extraire : référence produit.

Set up Koncile in just one day

Koncile is pre-trained and can be deployed in a single day for all your extraction use cases.

No need for training on large volumes of your data.

Vignette de vidéo extraction de document.

Connect Koncile to your tools

Capture data in a structured format such as JSON, XLSX, CSV, or others.

Connect your application via our API. Access the full documentation here.

Liste des formats de document.
Logo de Koncile.

Discover next-generation data extraction

Start with a resume template, test it, and scale

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

An OCR solution designed to extract your resumes

Automatic extraction of resume information

Studies and education, languages spoken, interests: identify and extract key data automatically

From resume to actionable data

Easily manage your resumes by converting them into structured, usable data

Multi-format resume processing

Easily manage and standardize resumes in different formats (PPT, PDF, Word, Canvas)

Extraction of resume data for API

Create a comprehensive database integrated into an app accessible via API

Beyond OCR: Validation & control of extracted data

Does the candidate have experience in the sector? Are the candidate's skills aligned with the job description? Are there inconsistencies in the resume? Automate resume management with intelligent OCR.

The OCR API to automate resume management

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.

Explore our library of ready-to-use automation templates

SEE ALL TEMPLATES
No items found.

Any question?

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

Can I extract a specific field?

Absolutely! Koncile’s OCR extraction service offers fully customizable fields. Our pre-built models are just a starting point—you can modify and add your own fields to meet your specific needs.

How does Koncile integrate with my existing tools and software?

Koncile is accessible via an API. Check our full OCR documentation. Additionally, you can upload documents directly in the app and download extracted data in XLSX, XLS, CSV or JSON formats for seamless integration into your workflows.

I need to parse a document that’s very specific to my industry. 
Can Koncile handle it?

Of course! Start by exploring our library of pre-built templates, covering a wide range of industries. If you don’t find one that fits your needs, you can easily create your own custom model.

What are “General Fields” and “Repeated Fields”?

In each extraction template, you’ll find:

General fields: These are pieces of information that appear only once per document (e.g., an invoice number or date).

Repeated fields: These are elements that appear multiple times within a document, such as item descriptions or prices in each line of a quote. Use repeated fields to extract tables and structured data from your documents.

What file formats does Koncile support?

Koncile allows you to import PDF files and all common image formats, including PNG and JPEG.

What is Koncile’s pricing structure?

Koncile offers three plans, including enterprise options for handling large data volumes. Check out our pricing on the dedicated page in our documentation.