Automated Phone Interview Evaluation with Vapi, GPT-4o & Google Sheets
This n8n workflow template automatically processes phone interview transcripts using AI to evaluate candidates against specific criteria and saves the results to Google Sheets. Perfect for HR departments, recruitment agencies, or any business conducting phone screenings. ## What This Workflow Does This automated workflow: - Receives phone interview transcripts via webhook - Uses OpenAI GPT models to analyze candidate responses against predefined qualification criteria - Extracts key information (name, phone, location, qualification status) - Automatically saves structured results to a Google Sheet for easy review and follow-up The workflow is specifically designed for driving job interviews but can be easily adapted for any position with custom evaluation criteria. ## Tools & Services Used - **N8N** - Workflow automation platform - **OpenAI API** - AI-powered transcript analysis (GPT-3.5-mini) - **Google Sheets** - Data storage and management - **Webhook** - Receiving transcript data ## Prerequisites Before implementing this workflow, you'll need: 1. **N8N Instance** - Self-hosted or cloud version 2. **OpenAI API Account** - For AI transcript processing 3. **Google Account** - For Google Sheets integration 4. **Phone Interview System** - That can send webhooks (like Vapi.ai) ## Step-by-Step Setup Instructions ### Step 1: Set Up OpenAI API Access 1. Visit [OpenAI's API platform](https://platform.openai.com/) 2. Create an account or log in 3. Navigate to the API Keys section 4. Generate a new API key 5. Copy and securely store your API key ### Step 2: Create Your Google Sheet **Option 1: Use Our Pre-Made Template (Recommended)** 1. Copy our template: [Driver Interview Results Template](https://docs.google.com/spreadsheets/d/18W1ZzPM__foVNjeapuxnon0ZtgxaQjncNaamuZOdUSo/edit?usp=sharing) 2. Click File → Make a copy to create your own version 3. Rename it as desired 4. Copy your new sheet's URL - you'll need this for the workflow **Option 2: Create From Scratch** 1. Go to [Google Sheets](https://sheets.google.com/) 2. Create a new spreadsheet 3. Name it Driver Interview Results (or your preferred name) 4. Set up the following column headers in row 1: - A1: `name` - B1: `phone` - C1: `cityState` - D1: `qualifies` - E1: `reasoning` 5. Copy the Google Sheet URL - you'll need this for the workflow ### Step 3: Import and Configure the N8N Workflow 1. **Import the Workflow** - Copy the workflow JSON from the template - In your N8N instance, go to Workflows → Import from JSON - Paste the JSON and import 2. **Configure OpenAI Credentials** - Click on either OpenAI Chat Model node - Set up credentials using your OpenAI API key - Test the connection to ensure it works 3. **Configure Google Sheets Integration** - Click on the Save to Google Sheets node - Set up Google Sheets OAuth2 credentials - Select your spreadsheet from the dropdown - Choose the correct sheet (usually Sheet1) 4. **Update the Webhook** - Click on the Webhook node - Note the webhook URL that n8n generates - This URL will receive your transcript data ### Step 4: Customize Evaluation Criteria The workflow includes predefined criteria for a Massachusetts driving job. To customize for your needs: 1. Click on the Evaluate Candidate node 2. Modify the system message to include your specific requirements 3. Update the evaluation criteria checklist 4. Adjust the JSON output format if needed **Current Evaluation Criteria:** - Valid Massachusetts driver's license - No felony convictions - Clean driving record (no recent tickets/accidents) - Willing to complete background check - Can pass drug test (including marijuana) - Available full-time Monday-Friday - Lives in Massachusetts ### Step 5: Connect to Vapi.ai (Phone Interview System) This workflow is specifically designed to work with Vapi.ai's phone interview system. Here's how to connect it: #### Setting Up the Vapi Integration 1. **Copy Your N8N Webhook URL** - In your n8n workflow, click on the Webhook node - Copy the webhook URL (it should look like: `https://your-n8n-instance.com/webhook-test/351ffe7c-69f2-4657-b593-c848d59205c0`) 2. **Configure Your Vapi Assistant** - Log into your [Vapi.ai dashboard](https://dashboard.vapi.ai/) - Create or edit your phone interview assistant - In the assistant settings, find the Server section - Set the Server URL to your n8n webhook URL - Set timeout to 20 seconds (as configured in the workflow) 3. **Configure Server Messages** - In your Vapi assistant settings, enable these server messages: - `end-of-call-report` - `transcript[transcripttype=final]` 4. **Set Up the Interview Script** - Use the provided interview script in your Vapi assistant (found in the workflow's system message) - This ensures consistent data collection for the AI evaluation #### Expected Data Format from Vapi The workflow expects Vapi to send data in this specific format.
- Platform
- n8n
- Category
- HR & Operations
- Price
- $9.99
- Creator
- Robert Breen
- set
- webhook
- stickyNote
- googleSheets
- agent
- lmChatOpenAi
- outputParserStructured
How to import this workflow into n8n
- 1Purchase or download the workflow to get the n8n workflow JSON file.
- 2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
- 3Open each node marked with a credential warning and connect your own accounts and API keys.
- 4Run the workflow once manually to verify the data flow, then toggle it to Active.
Related HR & Operations workflows
- Automate CV Screening with AI-Powered Analysis$14.99
- Automated AI Resume Screening and Evaluation with Google Sheets and Drive$14.99
- Automate Candidate Evaluation with AI and Slack Integration$14.99
- Automate HR Processes via WhatsApp with AI and Google Workspace$19.99
- AI-Automated HR Workflow for CV Analysis and Candidate Evaluation$14.99
- Customer Onboarding Automation with HubSpot, Email Sequences, and Team Alerts$14.99
More from Robert Breen
Need this deployed? We'll set it up for you.
Our automation experts deploy this workflow in your stack, connect your accounts, and verify it works — or build a custom solution from scratch.