🤖 AI Resume Screener — Google Forms to Automated Shortlisting & Email

Automatically score every job application with AI, update your tracking sheet, and send personalised emails to candidates — all without human review.

---

📖 Description

This workflow automates your entire first-round resume screening process. When a candidate submits your Google Form application, the workflow triggers, extracts their details, scores them against the job description using AI, writes the results back to your Google Sheet, and sends the right email — a congratulations to shortlisted candidates, a polite rejection to others.

Your HR team only reviews candidates the AI has already scored 7 or above.

Built for companies hiring across multiple roles simultaneously, HR teams wanting to reduce screening time, and startups with no dedicated recruiting staff.

---

✨ Key Features

• Google Sheets Trigger — fires automatically when a new application row is added
• Duplicate prevention — tracks processed rows with a Processed column, never scores the same application twice
• Multi-role support — built-in Job Description map for 5 roles, easily extendable
• AI scoring 1–10 — Google Gemini scores each candidate against the JD with strengths, weaknesses, recommendation
• Direct sheet write via API — writes score + grade + status to exact row using Google Sheets API
• Smart email routing — score ≥ 7 → shortlisted (HR alert + candidate email), score < 7 → rejection email
• Rate limit protection — Wait node between HR alert and candidate email prevents SMTP throttling
• Robust AI parsing — 3-layer fallback ensures AI output always produces a usable result

---

🔄 How It Works

New Google Form submission
          ↓
Google Sheets Trigger (rowAdded, polls every minute)
          ↓
Read All Rows → Filter Unprocessed Rows (col_18 / Processed ≠ 1)
          ↓
Extract Fields + Load Job Description
  → name, email, phone, position, experience, skills, cover note
  → loads matching JD from built-in map
          ↓
AI Resume Scorer (Google Gemini)
  → score: 1–10
  → grade: Strong Yes / Maybe / No
  → strengths, weaknesses, recommendation, summary
          ↓
Parse AI Output (3-layer fallback)
          ↓
Build Sheet Request → Write to Sheet via API
  → writes score, grade, strengths, weaknesses,
    recommendation, summary, status, timestamp, Processed=1
          ↓
Score ≥ 7?
  ✅ YES → Alert Email to HR + Wait 10s → Shortlist Email to Candidate
  ❌ NO  → Rejection Email to Candidate

---

🤖 AI Scoring System

The AI scores each candidate from 1 to 10 against the job description:

Score	Grade	Action
8–10	Strong Yes	Shortlisted ✅
7	Strong Yes / Maybe	Shortlisted ✅
5–6	Maybe	Rejected ❌
1–4	No	Rejected ❌

For each application the AI also provides:

• Strengths — what the candidate does well vs the JD
• Weaknesses — gaps or concerns
• Recommendation — e.g. "Invite for technical interview"
• Summary — 2–3 sentence overall assessment

---

📋 Built-in Job Descriptions

Five roles are pre-configured and auto-matched by position name:

Role	Key Requirements
Frontend Developer	2+ yrs React/Vue, HTML/CSS/JS, REST APIs, Git
Backend Developer	2+ yrs Node.js/Python/Java, PostgreSQL/MongoDB, Docker
UI/UX Designer	2+ yrs UI/UX, Figma or Adobe XD, portfolio
Project Manager	3+ yrs PM, PMP/Scrum preferred, Jira/Asana
Digital Marketing Executive	2+ yrs digital marketing, Google Ads, Meta Ads, GA4

Add more roles by editing the JD_MAP object in the Extract Fields + Load JD node.

---

📧 Email Templates

Shortlist Email (to candidate)

• Subject: Congratulations [Name] - You have been shortlisted!
• Navy blue header
• Score table (score/10, grade, position, experience, skills)
• Strengths highlighted in green
• AI assessment in blue
• Promise: HR contacts within 2 business days

HR Alert Email (internal)

• Subject: Strong Candidate - [Name] for [Position]
• Amber header — urgent feel
• Full candidate details + complete AI breakdown
• Strengths, weaknesses, recommendation, summary all included

Rejection Email (to candidate)

• Subject: Your application for [Position] - Update
• Grey header — professional and neutral
• Polite decline with encouragement
• No score or feedback shared

---

🛠 Setup Requirements

1. Google Form

Create a Google Form with these fields:

Field	Type
Full Name	Short answer
Email Address	Short answer
Phone Number	Short answer
Select the Position You Are Applying For	Dropdown
Years of Experience	Short answer
Relevant Skills	Long answer
Cover Note	Long answer

Link the form to a Google Sheet (Responses tab).

2. Google Sheet — Response Sheet Columns

The form creates columns A–H automatically. Add these columns manually for AI results:

Col	Header	Filled by
A	Timestamp	Google Forms
B	Select the Position...	Google Forms
C	Full Name	Google Forms
D	Email Address	Google Forms
E	Phone Number	Google Forms
F	Years of Experience	Google Forms
G	Relevant Skills	Google Forms
H	Upload CV	Google Forms
I	Cover Note	Google Forms
J	AI Score	This workflow
K	Grade	This workflow
L	Strengths	This workflow
M	Weaknesses	This workflow
N	Recommendation	This workflow
O	Summary	This workflow
P	Status	This workflow
Q	Processed At	This workflow
R	Processed	This workflow (1 = done)

Important: The workflow uses column R (Processed) to track which rows have been scored. Rows where R = 1 are skipped on subsequent triggers.

3. Credentials Required

Credential	Used for	Free?
Google Sheets Trigger OAuth2	Detects new rows	Free
Google Sheets OAuth2	Read rows + write results	Free
Google Gemini (PaLM) API	AI resume scoring	Free tier available
SMTP	Sending emails	Depends on provider

4. Update Sheet ID

In the Read All Rows and Write to Sheet via API nodes, replace the Sheet ID with your own:

https://docs.google.com/spreadsheets/d/YOUR_SHEET_ID/...

5. Update Email Addresses

In all three email nodes, update:

• fromEmail — your HR sending address
• HR alert toEmail — your internal HR inbox
• SMTP credential — your email provider

---

⚙️ Workflow Nodes

Node	Type	Purpose
Google Sheets Trigger	Trigger	Fires on new row (polls every minute)
Read All Rows	Google Sheets	Reads all form responses
Filter Unprocessed Rows	Code	Skips rows where Processed = 1
Extract Fields + Load JD	Code	Extracts candidate data + matches JD
AI Resume Scorer	AI Agent	Scores candidate vs JD using Gemini
Google Gemini Chat Model	LLM	AI model for scoring
Parse AI Output	Code	Parses JSON with 3-layer fallback
Build Sheet Request	Code	Prepares API write request for exact row
Write to Sheet via API	HTTP Request	Writes results to columns J–R
Score ≥ 7?	IF	Routes by score
Alert Email - HR Team	Email Send	Notifies HR of strong candidates
Wait 10s	Wait	Prevents SMTP rate limiting
Shortlist Email - Candidate	Email Send	Congratulations to shortlisted
Rejection Email - Candidate	Email Send	Polite rejection to others

---

🔑 Key Technical Details

Why HTTP Request for sheet write instead of Google Sheets node?
The standard Google Sheets node cannot reliably write to a specific row by row number. Using the Sheets API PUT values/{range} endpoint writes to the exact cell range Form responses 1!J{rowNum}:R{rowNum} — always the correct row regardless of concurrent submissions.

Why Read All Rows then Filter instead of reading one row?
The Google Sheets Trigger fires on rowAdded but may not pass the exact new row data reliably. Reading all rows and filtering by Processed ≠ 1 is more reliable and handles backlog processing too.

The Processed column (R)
Set to 1 after scoring completes. This prevents re-processing if the trigger fires again before the workflow finishes, or if old unprocessed rows exist.

3-layer AI output fallback:

1. Direct JSON parse
2. Strip markdown fences then parse
3. Regex extract JSON block
4. Default values if all fail (score: 5, grade: Maybe)

---

📊 Sample Sheet Output After Scoring

Col J  (AI Score):      8
Col K  (Grade):         Strong Yes
Col L  (Strengths):     3+ yrs React experience; Strong TypeScript skills; Relevant API work
Col M  (Weaknesses):    No Docker experience mentioned; No TypeScript explicitly listed
Col N  (Recommendation): Invite for technical interview
Col O  (Summary):       Strong frontend candidate with solid React/Vue background. Experience aligns well with role requirements. Minor gaps in DevOps knowledge.
Col P  (Status):        Shortlisted
Col Q  (Processed At):  2026-03-18T10:30:00.000Z
Col R  (Processed):     1

---

🔧 Customisation

Add more roles:
Edit the JD_MAP object in Extract Fields + Load JD:

const JD_MAP = {
  'Your New Role': 'ROLE: ... REQUIREMENTS: ...',
  // add as many as needed
};

Change the score threshold:
In the Score ≥ 7? IF node, change rightValue: 5 to any number. Setting to 8 makes the bar higher (only Strong Yes candidates shortlisted).

Add a second HR alert channel:
After the HR Alert Email, add a Slack or Telegram node to ping your team instantly for high-scoring candidates.

Add calendar booking link:
Include a Calendly link in the shortlist email so candidates can self-schedule interviews immediately.

Extend with CV parsing:
Add a Google Drive node before the AI scorer to download the CV attachment, extract text, and include it in the AI prompt for more accurate scoring.

---

⚠️ Important Notes

• The Google Sheets Trigger polls every minute — there may be up to a 1-minute delay after form submission before scoring begins
• The Processed column must exist in your sheet (column R) before activating the workflow
• Trailing spaces in Google Forms column headers are common — the key.trim() normalization in the code handles this automatically
• The Wait node between HR alert and shortlist email is intentional — prevents hitting SMTP rate limits when processing multiple candidates

---

💡 Enhancement Ideas

• CV download + parse — download Google Drive CV attachment and include content in AI scoring
• Calendly integration — auto-create interview slot and include booking link in shortlist email
• Slack alert — instant Slack message to hiring manager for score ≥ 9 candidates
• Airtable sync — mirror all candidate data to an Airtable CRM for pipeline tracking
• Telegram bot — let HR check candidate status by texting a bot with the candidate email
• Multi-stage pipeline — add a second workflow that triggers when HR marks a candidate for second round

---

📦 Requirements Summary

• n8n (cloud or self-hosted)
• Google Workspace account (Forms + Sheets)
• Google AI Studio account for Gemini API key (free tier available)
• SMTP email account (Gmail, SendGrid, Mailtrap etc.)

---

Built with n8n · Google Gemini AI · Google Forms · Google Sheets · SMTP