Automated CV Extraction and Candidate Data Management

somdn_product_page

This n8n workflow automates the process of extracting and organizing candidate information from emails with PDF resumes. It streamlines HR operations by automatically parsing CVs, extracting relevant data using AI, and updating a Notion database for candidate tracking. Key steps include:

1. Monitoring a Gmail inbox for incoming emails with attachments.

2. Filtering and extracting PDF files from email attachments.

3. Using OCR to convert PDF images into text.

4. Sending the extracted text to an AI model (GPT-4) to detect if it’s a CV and extract structured data such as name, contact details, skills, education, and experience.

5. Mapping the extracted data to specific fields in a Notion database.

6. Checking for duplicate candidates based on email before creating new entries.

7. Creating a new candidate record in Notion if no duplicates are found.

This workflow is particularly useful for HR teams and recruiters receiving large volumes of CVs via email, allowing for efficient data extraction, deduplication, and centralized candidate management.

Node Count

11 – 20 Nodes

Nodes Used

@n8n/n8n-nodes-langchain.openAi, code, gmailTrigger, httpRequest, if, notion, set, stickyNote

Reviews

There are no reviews yet.

Be the first to review “Automated CV Extraction and Candidate Data Management”

Your email address will not be published. Required fields are marked *