Screen candidates and send take-home assignments with Google Sheets, Gmail, Anthropic, and OpenAI
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 17 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Embeddings OpenAI, Google Sheets, Anthropic Chat Model and Gmail.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Set config + rubric (Edit Fields (Set)): sets 4 fields: rubricText, threshold, assignmentSubject…
- Load rubric into vector store (Simple Vector Store): stores documents in the Simple vector store, with embeddings: Embeddings; document loader: Rubric document loader
- Get candidates from Google Sheet (Google Sheets): uses Google Sheets
- Score candidate vs rubric (AI Agent): runs an AI agent, with model: Anthropic Chat Model; 1 tool (Rubric retriever (tool)); output parser: Fix score format
- Flatten scores for Sheet (Code): runs custom JavaScript code
- Write scores back to Sheet (Google Sheets): append or update
- Get approved shortlist (Google Sheets): uses Google Sheets
- Switch: routes items into 2 branches
- Email the take-home assignment (Gmail): uses Gmail
- Human evaluation (Gmail): uses Gmail
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Score candidate vs rubric (v1.9): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Score candidate vs rubric (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (13)
- Manual Trigger
n8n-nodes-base.manualTrigger - Edit Fields (Set)
n8n-nodes-base.set - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Simple Vector Store
@n8n/n8n-nodes-langchain.vectorStoreInMemory - Google Sheets
n8n-nodes-base.googleSheets - Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - AI Agent
@n8n/n8n-nodes-langchain.agent - Code
n8n-nodes-base.code - Gmail
n8n-nodes-base.gmail - Switch
n8n-nodes-base.switch - Auto-fixing Output Parser
@n8n/n8n-nodes-langchain.outputParserAutofixing
From the author
Quick overview This workflow pulls candidates from Google Sheets, uses an Anthropic-powered AI agent with an in-memory vector-store rubric (RAG) to score and shortlist applicants, writes results back to the sheet, then emails a take-home assignment via Gmail…