Screen resumes and match candidates with GPT-4o, Google Sheets and email

by Cheng Siong Chin ✓ · 141 views · created 2026-03-29 · HR, AI Summarization

What this workflow does

This AI workflow has 20 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects OpenAI Chat Model.

How it runs

Trigger: When an HTTP POST request hits its webhook URL.

1. Matching Agent (Orchestrator) (AI Agent): runs an AI agent, with model: Matching Agent Model; 5 tools (Cultural Fit Agent, Resume Parser Agent, Skill Analysis Agent, Validation Logic Tool…); output parser: Ranking Output Parser
2. Check Confidence Level (If): checks a condition and branches into true / false
3. Prepare Analysis Data (Edit Fields (Set)): sets 9 fields: candidateId, timestamp, overallScore…
4. Prepare Low Confidence Data (Edit Fields (Set)): sets 7 fields: candidateId, timestamp, overallScore…
5. Store Analysis Results (Data table): uses Data table
6. Store Low Confidence Cases (Data table): uses Data table
7. Send High Confidence Report (Send Email): sends an email over SMTP
8. Send Review Required Alert (Send Email): sends an email over SMTP

Services it uses

OpenAI Chat Model

Before you upgrade to n8n 3.0

Nodes used (10)

• Webhookn8n-nodes-base.webhook
• AI Agent@n8n/n8n-nodes-langchain.agent
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
• Structured Output Parser@n8n/n8n-nodes-langchain.outputParserStructured
• AI Agent Tool@n8n/n8n-nodes-langchain.agentTool
• Code Tool@n8n/n8n-nodes-langchain.toolCode
• Data tablen8n-nodes-base.dataTable
• Edit Fields (Set)n8n-nodes-base.set
• Ifn8n-nodes-base.if
• Send Emailn8n-nodes-base.emailSend

From the author

How It Works This workflow automates candidate screening and job matching for recruiters, HR operations teams, and talent acquisition leads. It eliminates the manual effort of parsing resumes, evaluating multi-dimensional candidate fit, and routing outcomes…

View the original on n8n.io → Check your own copy