CV Anonymization and Data Extraction using Gemini AI and Google Sheets - n8n Workflow

• Recruiters and HR specialists needing to anonymize candidate data for bias reduction or compliance.


• Technical users looking for advanced n8n templates integrating large language models (LLMs) and spreadsheet operations.


• Data managers who need a reliable, automated ledger for tracking document processing via an n8n workflow.

Manually processing résumés (CVs) and extracting relevant data while ensuring anonymization is a time-consuming and error-prone task. This robust n8n workflow provides a complete solution for automating this critical HR function. The process starts when new CV files are uploaded to Google Drive. The n8n workflow then performs a crucial deduplication step, checking a Google Sheets ledger to ensure only new files are processed. Utilizing the Google Gemini AI n8n node, the automation extracts unstructured text from the CV, transforms it into structured data, and enforces anonymization rules. The resulting data is then written back to Google Sheets. This specific n8n template is essential for creating an efficient, compliant, and scalable hiring pipeline, leveraging the power of modern AI within a cohesive n8n framework.

This comprehensive n8n workflow initiates using the Google Drive Trigger, which monitors a specified folder for new file uploads. Immediately upon triggering, the workflow branches to two preparatory steps: retrieving a list of current files (via HTTP/Code processing) and reading the list of already processed documents from the main Google Sheets ledger.

The central Compare Datasets n8n node then filters this list, ensuring that only CVs not yet recorded in the ledger proceed. For each unique document, the automation uses the Google Drive n8n node to download the file and the Extract from File n8n node to obtain its raw text content.

The extracted text is passed to the AI Agent n8n node, which leverages the connected Google Gemini Chat Model to perform complex tasks: identifying key CV elements (e.g., job history, skills) and anonymizing personal identifiers (names, contact info).

After the AI processing, a Clean output code n8n node standardizes the resulting structured data. This clean data is then written to the main Google Sheet using the Update CV Fields n8n node. Finally, the file ID is logged using the Log the processing of the doc Google Sheets n8n node, effectively marking the document as complete and preventing reprocessing by the n8n trigger in the future. This architecture demonstrates how effective n8n templates handle complex file and data management.

1. Import the n8n workflow: Copy the provided JSON code and paste it directly into your n8n instance's workflow editor.


2. Set up Credentials: You will need credentials for the following services:

1. Configure Nodes: Review the AI Agent - get targeted elements from text n8n node configuration to ensure the prompt accurately reflects your desired extraction and anonymization logic.


2. Activate: Once credentials and configurations are set, activate the n8n workflow.

Google Drive Trigger: The primary n8n trigger. Starts the n8n workflow whenever a new CV file is detected in the monitored Google Drive folder.
Read processed docs (Google Sheets n8n node): Reads the current ledger of documents that have already been run through this n8n template, used for deduplication.
Compare Datasets n8n node: Compares the newly detected files against the list of processed files, allowing only truly new items to proceed.
Extract from File n8n node: Crucial for PDF processing. Extracts the raw, unstructured text content from the downloaded CV file.
Google Gemini Chat Model / AI Agent n8n node: The core of the automation. The Agent uses the Gemini model to analyze the raw CV text, extract specific fields, and apply necessary anonymization rules defined in its instructions.
Clean output (Code n8n node): Custom code used to parse the typically JSON or structured text output from the AI Agent into a format suitable for Google Sheets.
Update CV Fields (Google Sheets n8n node): Writes the clean, anonymized, structured data extracted by the n8n workflow back into the main output spreadsheet.
Log the processing of the doc (Google Sheets n8n node): Records the File ID in the processed ledger, ensuring the n8n workflow does not run the same file repeatedly.