Automate Resume Screening with n8n and Google Gemini AI

What This Automation Does

This workflow downloads a resume PDF from Google Drive.

It turns the PDF into a clear image for AI to read.

The image is resized for faster AI processing.

Google Gemini AI reviews the image for hidden tricks in the resume.

The AI decides if the candidate qualifies for the job.

The workflow then branches automatically based on the AI decision.

Tools and Services Used

• Google Drive node: Downloads PDF resumes stored in the cloud.


• Stirling PDF API: Converts PDF pages to high-quality images.


• Edit Image node: Resizes images to speed up AI analysis.


• Google Gemini AI API with Langchain: Reads and understands images to detect hidden resume manipulations.


• Conditional IF node: Directs workflow based on AI results.

Workflow Inputs, Processing, and Outputs

Inputs

• The PDF resume file stored in Google Drive identified by file ID.

Processing Steps

• Download the resume PDF using the Google Drive node.


• Convert single-page PDF to an image via Stirling PDF HTTP API.


• Resize the image to 75% of original size in the Edit Image node.


• Send the resized image to Google Gemini AI with a custom prompt to evaluate plumber job fit and detect manipulative hidden prompts.


• Parse the AI response JSON output using Langchain Structured Output Parser node.


• Use an IF node to decide if the candidate qualifies for the next stage.

Outputs

• Structured JSON stating if candidate is qualified.


• Workflow branches—for qualified candidates, it proceeds further. For others, it stops or handles accordingly.

Beginner Step-by-Step: How to Use This Workflow in n8n

Download and Import

1. Download the workflow file from this page.


2. In the n8n editor, click on "Import from File" to upload it.

Set Up Credentials and IDs

1. Add Google Drive credentials so the workflow can access resume files.


2. Enter the Stirling PDF API key or instance URL if self-hosting is used.


3. Set up Google Gemini AI API credentials in the Langchain node.


4. Update the Google Drive Download Resume (Google Drive) node's fileId to match the resume file's ID.

Review Prompts and Settings

1. Check the Candidate Resume Analyser (Langchain ChainLLM) prompt and edit it if assessing for a different job role.


2. Verify the Resize Converted Image (Edit Image) settings for resizing percentages.

Testing and Activation

1. Run the workflow once by clicking the Test Workflow button.


2. Check the execution logs to confirm the process runs without errors and the qualification output appears.


3. Activate the workflow for production use.

Optionally, schedule triggers or connect other nodes for automation like sending interview invites. For self-hosting n8n, see self-host n8n.

Customizations and Tips

• You can edit the AI prompt to target other job titles, simply replace "the role of Plumber" with another title.


• Set Stirling PDF API to convert multiple pages if resumes have more than one page by using singleOrMultiple set to "multiple".


• Replace the Manual Trigger with a Gmail trigger node to auto-process resumes sent by email.


• Change resizing scale in the image node to balance processing speed and detail.


• Add nodes like Google Sheets or Slack to report candidate qualification results immediately.

Troubleshooting Common Problems

• Download fails: Check Google Drive file ID and permissions. Ensure credentials have right access.


• PDF to image API error 400: Verify multipart form data is correctly set. Confirm PDF binary is properly passed.


• AI parsing error: Make sure AI prompt returns formatted JSON that matches the parser schema. Update parser if prompt changes.


• Incorrect IF node branching: Confirm condition logic matches structure of AI output JSON.

Pre-Production Checklist

• Confirm Google Drive file access and valid file IDs.


• Verify Stirling PDF API availability and correct API key or self-hosting setup.


• Test Google Gemini AI API credentials and connectivity.


• Run full workflow test with sample resume having a hidden prompt.


• Backup workflow and store API keys securely.

Deployment Guide

After testing, activate the workflow in n8n editor.

Schedule it with cron triggers or connect to email or webhooks for live candidate screening.

Monitor n8n executions dashboard for errors and performance.

Summary of Benefits

✓ Saves recruitment time by automating resume review of PDFs with hidden prompts.

✓ Detects resume manipulations that fool normal ATS systems.

✓ Uses image-based AI reading for more accurate candidate qualification.

✓ Automatically branches workflow for further hiring steps.