Recruitment AI
Tuyển dụng truyền thống tốn 23 giờ để hire 1 người. AI có thể giảm xuống còn 8 giờ - screen resumes, match candidates, và schedule interviews tự động.
🎯 Mục tiêu bài học
- Tự động hóa resume screening
- Setup AI candidate matching
- Build interview scheduling workflow
- Ensure fair & unbiased hiring
📊 The Recruitment Challenge
Traditional Hiring Process
Text
1┌─────────────────────────────────────────────┐2│ TRADITIONAL RECRUITMENT │3├─────────────────────────────────────────────┤4│ │5│ 📋 Job Posting (2 hrs) │6│ ↓ │7│ 📧 Receive Applications (ongoing) │8│ ↓ │9│ 👀 Manual Resume Review (8 hrs) │10│ ↓ (100 resumes × 5 min each) │11│ ✓ Shortlist Candidates (2 hrs) │12│ ↓ │13│ 📞 Phone Screening (5 hrs) │14│ ↓ (20 calls × 15 min) │15│ 📅 Schedule Interviews (3 hrs) │16│ ↓ │17│ 🎯 Conduct Interviews (varies) │18│ ↓ │19│ ✅ Make Decision (2 hrs) │20│ │21│ Total: 22-25 hours per hire │22│ Time to hire: 30-45 days │23└─────────────────────────────────────────────┘AI-Powered Recruitment
Text
1┌─────────────────────────────────────────────┐2│ AI-POWERED RECRUITMENT │3├─────────────────────────────────────────────┤4│ │5│ 📋 Job Posting (AI-assisted) (30 min) │6│ ↓ │7│ 🤖 Auto Resume Screening (instant) │8│ ↓ (100 resumes in 2 min) │9│ 🎯 AI Candidate Ranking (instant) │10│ ↓ │11│ 📅 Auto Interview Scheduling (30 min) │12│ ↓ │13│ 📝 AI Interview Prep (15 min) │14│ ↓ │15│ 🎯 Conduct Interviews (varies) │16│ ↓ │17│ ✅ AI-Assisted Decision (1 hr) │18│ │19│ Total: 6-8 hours per hire │20│ Time to hire: 15-20 days │21└─────────────────────────────────────────────┘Impact: Companies using AI recruitment see 75% reduction in time-to-hire và 35% improvement in quality of hire.
🛠️ AI Recruitment Tools
Tool Comparison
| Tool | Best For | Price | Key Feature |
|---|---|---|---|
| Manatal | SMB/Agencies | $15/user/mo | AI recommendations |
| HireVue | Enterprise | Custom | Video AI analysis |
| Lever | Mid-market | Custom | Full ATS + AI |
| Paradox (Olivia) | High-volume | Custom | Conversational AI |
| SeekOut | Tech hiring | $500/mo | Talent sourcing |
| Textio | Job posts | $500/mo | Inclusive writing |
No-Code Options
Text
1Budget-friendly AI recruitment:2 31. ChatGPT/Claude + Google Sheets4 - Resume parsing5 - Candidate scoring6 - Email templates7 Cost: ~$20/month8 92. Make.com + AI10 - Automated workflows11 - Integration with job boards12 - Candidate pipeline13 Cost: ~$50/month14 153. Manatal16 - Full ATS with AI17 - Resume parsing18 - Candidate matching19 Cost: $15/user/month📝 AI-Powered Job Descriptions
Generate Inclusive Job Posts
Prompt:
markdown
1Write a job description for a Senior Software Engineer 2position at a fintech startup.3 4Requirements:5- 5+ years experience6- Python and AWS expertise7- Team leadership8 9Make it:10- Inclusive and welcoming11- Clear about must-haves vs nice-to-haves12- Focused on what they'll accomplish, not just requirements13- Free of biased languageAI Output:
markdown
1# Senior Software Engineer2 3## About the Role4Join our engineering team to build the next generation 5of financial tools that help millions manage their money 6better. You'll lead key initiatives, mentor teammates, 7and directly impact our product roadmap.8 9## What You'll Do10- Design and build scalable backend systems in Python11- Lead technical projects from concept to production12- Mentor junior engineers and conduct code reviews13- Collaborate with product and design teams14- Drive best practices in code quality and testing15 16## What We're Looking For17 18**Must Have:**19- 5+ years of software development experience20- Strong Python programming skills21- Experience with AWS services22- Track record of shipping products23- Clear communication skills24 25**Nice to Have:**26- Fintech or financial services background27- Experience with event-driven architectures28- Contributions to open source projects29- Experience leading small teams30 31## Why Join Us32- Competitive salary + equity33- Remote-first culture34- Learning budget ($2,000/year)35- Health, dental, vision insurance36- Flexible PTO37 38## Our Commitment to Diversity39We believe diverse teams build better products. We 40welcome candidates from all backgrounds and are 41committed to inclusive hiring practices.42 43---44Location: Remote (US)45Type: Full-timeBias Check with AI
Text
1Prompt: "Review this job description for biased language"2 3AI Analysis:4┌─────────────────────────────────────────────┐5│ JOB DESCRIPTION BIAS CHECK │6├─────────────────────────────────────────────┤7│ │8│ ⚠️ Potentially Biased Language: │9│ │10│ "Rockstar developer" │11│ → Replace: "Skilled developer" │12│ → Reason: Gendered connotation │13│ │14│ "Young, dynamic team" │15│ → Replace: "Collaborative team" │16│ → Reason: Age discrimination │17│ │18│ "Must be native English speaker" │19│ → Replace: "Excellent English communication"│20│ → Reason: Nationality discrimination │21│ │22│ ✅ Good Practices Found: │23│ • Clear must-have vs nice-to-have │24│ • Focus on skills, not credentials │25│ • Inclusive benefits mentioned │26│ │27└─────────────────────────────────────────────┘📄 Resume Screening
AI Resume Parser Setup
Using Make.com + Claude:
Text
1Workflow:21. Resume received (email/form)32. Extract text from PDF43. Send to Claude API54. Parse structured data65. Score against job requirements76. Add to candidate databaseClaude Parsing Prompt:
markdown
1Parse this resume and extract information in JSON format:2 3{4 "name": "",5 "email": "",6 "phone": "",7 "location": "",8 "linkedin": "",9 "summary": "",10 "experience": [11 {12 "company": "",13 "title": "",14 "duration": "",15 "years": 0,16 "responsibilities": [],17 "achievements": []18 }19 ],20 "education": [21 {22 "institution": "",23 "degree": "",24 "field": "",25 "year": ""26 }27 ],28 "skills": {29 "technical": [],30 "soft": [],31 "languages": [],32 "certifications": []33 },34 "total_experience_years": 035}36 37Resume:38[paste resume text]AI Candidate Scoring
Scoring Prompt:
markdown
1Score this candidate against the job requirements.2 3Job Requirements:4- 5+ years Python experience (Required)5- AWS expertise (Required)6- Team leadership (Required)7- Fintech experience (Preferred)8- Open source contributions (Preferred)9 10Candidate Profile:11[parsed resume JSON]12 13Provide scoring:14{15 "overall_score": 0-100,16 "requirement_scores": {17 "python_experience": {18 "score": 0-100,19 "evidence": "",20 "years": 021 },22 "aws_expertise": {23 "score": 0-100,24 "evidence": ""25 },26 "team_leadership": {27 "score": 0-100,28 "evidence": ""29 },30 "fintech_experience": {31 "score": 0-100,32 "evidence": ""33 },34 "open_source": {35 "score": 0-100,36 "evidence": ""37 }38 },39 "strengths": [],40 "concerns": [],41 "recommendation": "Strong Match / Good Match / Weak Match / No Match",42 "suggested_interview_questions": []43}Batch Processing Pipeline
Text
1Google Sheets Setup:2├── Sheet 1: Raw Applications3│ └── Columns: Timestamp, Name, Email, Resume Link4│5├── Sheet 2: Parsed Candidates6│ └── Columns: Name, Email, Experience, Skills, Score7│8└── Sheet 3: Shortlist9 └── Columns: Name, Score, Status, Interview Date10 11Make.com Automation:121. New row in Sheet 1 (trigger)132. Download resume from link143. Extract text (PDF.co or similar)154. Send to Claude for parsing165. Send to Claude for scoring176. Add to Sheet 2187. IF score >= 70: Add to Sheet 3198. Send notification to recruiter📅 Interview Scheduling
Calendly + AI Integration
Setup:
Text
11. Create Calendly account22. Set availability for interviews33. Create event type: "Initial Interview"44. Get scheduling link5 6Automation:7Candidate passes screening → 8Auto-send email with Calendly link →9Candidate self-schedules →10Confirmation sent to all partiesAuto-Scheduling Email Template:
markdown
1Subject: Interview Invitation - [Position] at [Company]2 3Hi [candidate_name],4 5Thank you for applying to the [position] role at 6[company]. We've reviewed your application and would 7love to learn more about you!8 9**Next Step: Schedule Your Interview**10 11Please select a time that works for you:12[Schedule Interview]([calendly_link])13 14**What to Expect:**15- 30-minute video call via Zoom16- Discussion about your experience17- Q&A about the role and company18 19**Interviewer:** [interviewer_name], [interviewer_title]20 21If none of the times work, reply to this email and 22we'll find an alternative.23 24Best regards,25[recruiter_name]26[company] Talent TeamSmart Scheduling with AI
Text
1Advanced Workflow:2 31. Candidate selected for interview42. AI checks:5 - Candidate timezone (from resume location)6 - Interviewer availability7 - Interview room availability8 - Buffer time between interviews93. AI suggests 3 optimal time slots104. Auto-send to candidate115. Candidate confirms126. Calendar events created for all parties137. Zoom link generated148. Reminder emails scheduled🤖 AI Interview Assistant
Pre-Interview Prep
Generate Interview Questions:
markdown
1Prompt: "Generate interview questions for Senior 2Software Engineer candidate based on their resume"3 4Candidate Background:5- 6 years at fintech companies6- Led team of 4 engineers7- Built payment processing system8- Python, AWS, PostgreSQL expertise9 10AI Output:11 12# Interview Guide: [Candidate Name]13 14## Technical Questions (30 min)15 161. **System Design**17 "Tell me about the payment processing system you 18 built. How did you handle scalability and reliability?"19 20 Follow-ups:21 - How did you handle failed transactions?22 - What was your peak transaction volume?23 242. **Python Expertise**25 "What's your approach to writing maintainable 26 Python code at scale?"27 28 Follow-ups:29 - Testing strategies?30 - Performance optimization techniques?31 323. **AWS Architecture**33 "Walk me through how you'd design a highly 34 available service on AWS"35 36## Leadership Questions (15 min)37 384. "Tell me about leading your team of 4. What was 39 your biggest challenge and how did you handle it?"40 415. "How do you balance coding vs team responsibilities?"42 43## Behavioral Questions (10 min)44 456. "Describe a time when you had to push back on a 46 product requirement. What was the outcome?"47 487. "Tell me about a project that failed. What did 49 you learn?"50 51## Red Flags to Watch For52- Vague answers about technical decisions53- Unable to explain past project contributions54- Signs of poor collaboration skillsInterview Feedback Template
markdown
1# Interview Feedback Form2 3**Candidate:** [Name]4**Position:** Senior Software Engineer5**Interviewer:** [Your name]6**Date:** [Date]7 8## Scoring (1-5 scale)9 10| Area | Score | Notes |11|------|-------|-------|12| Technical Skills | ⬜1 ⬜2 ⬜3 ⬜4 ⬜5 | |13| Problem Solving | ⬜1 ⬜2 ⬜3 ⬜4 ⬜5 | |14| Communication | ⬜1 ⬜2 ⬜3 ⬜4 ⬜5 | |15| Leadership | ⬜1 ⬜2 ⬜3 ⬜4 ⬜5 | |16| Culture Fit | ⬜1 ⬜2 ⬜3 ⬜4 ⬜5 | |17 18## Strengths19- 20- 21 22## Concerns23- 24- 25 26## Recommendation27⬜ Strong Hire28⬜ Hire29⬜ No Hire30⬜ Strong No Hire31 32## Notes for Next Interviewer33[What should next interviewer focus on?]📊 Candidate Pipeline Dashboard
Airtable/Notion Setup
Text
1Database: Candidates2 3Fields:4├── Name (text)5├── Email (email)6├── Position (link to Jobs)7├── Source (select: LinkedIn, Referral, Job Board)8├── Status (select)9│ ├── New Application10│ ├── AI Screening11│ ├── Recruiter Review12│ ├── Phone Screen13│ ├── Interview 114│ ├── Interview 215│ ├── Offer16│ ├── Hired17│ └── Rejected18├── AI Score (number)19├── Resume (attachment)20├── Parsed Data (JSON)21├── Interview Notes (long text)22├── Final Decision (select)23└── Offer Details (text)24 25Views:26├── Kanban by Status27├── Table: All Candidates28├── Calendar: Interviews29└── Gallery: ShortlistedRecruitment Metrics
Text
1Dashboard Metrics:2 3Pipeline Overview:4├── Total Applications: 1565├── AI Screened: 156 (100%)6├── Passed Screening: 42 (27%)7├── Interviewed: 18 (12%)8├── Offers Extended: 4 (2.5%)9└── Accepted: 3 (1.9%)10 11Time Metrics:12├── Avg time to screen: 2 hours13├── Avg time to interview: 5 days14├── Avg time to offer: 14 days15└── Avg time to hire: 21 days16 17Quality Metrics:18├── Offer acceptance rate: 75%19├── 90-day retention: 95%20└── Hiring manager satisfaction: 4.5/521 22Source Performance:23├── LinkedIn: 45 candidates, 2 hires (4.4%)24├── Referrals: 23 candidates, 1 hire (4.3%)25├── Job boards: 88 candidates, 0 hires (0%)⚖️ Ethical AI Hiring
Avoiding Bias
Text
1⚠️ AI Bias Risks:2 31. Training Data Bias4 - Historical hiring patterns embedded5 - May perpetuate past discrimination6 72. Proxy Discrimination8 - ZIP code → socioeconomic status9 - University name → privilege10 - Name → gender/ethnicity11 123. Keyword Bias13 - "Golf" vs "Basketball"14 - "Assertive" vs "Collaborative"Best Practices
Text
1✅ Fair AI Hiring Practices:2 31. Blind Resume Review4 - Remove names, photos, addresses5 - Focus on skills and experience6 - AI screens on requirements only7 82. Diverse Training Data9 - Ensure AI trained on diverse hires10 - Regular bias audits11 - Multiple reviewers12 133. Structured Interviews14 - Same questions for all candidates15 - Scoring rubric16 - Multiple interviewers17 184. Human Override19 - AI recommends, human decides20 - Always review edge cases21 - Appeals process available22 235. Regular Audits24 - Track demographics through pipeline25 - Identify drop-off points26 - Adjust criteria if biasedLegal Note: In many jurisdictions, AI hiring tools must comply với anti-discrimination laws. Always consult legal counsel và conduct regular bias audits.
🔧 Complete Workflow Setup
Text
1End-to-End AI Recruitment:2 31. POST JOB4 └── AI generates inclusive job description5 62. RECEIVE APPLICATIONS7 └── Auto-acknowledge receipt8 93. AI SCREENING (Make.com)10 ├── Parse resume (Claude)11 ├── Score against requirements12 ├── Flag for human review if borderline13 └── Update candidate database14 154. RECRUITER REVIEW16 ├── Review AI-flagged candidates17 ├── Final shortlist decision18 └── Reject with personalized email19 205. SCHEDULE INTERVIEWS21 ├── Auto-send Calendly links22 ├── Candidate self-schedules23 └── Reminders automated24 256. INTERVIEW PREP26 ├── AI generates questions27 ├── Interviewer gets prep doc28 └── Candidate gets company info29 307. POST-INTERVIEW31 ├── Collect feedback32 ├── AI summarizes inputs33 └── Recommendation generated34 358. DECISION & OFFER36 ├── AI compiles all feedback37 ├── Hiring manager decides38 └── Offer letter generated (AI)39 409. ONBOARDING TRIGGER41 └── Accepted → Start onboarding workflow🎯 Bài tập thực hành
Task 1: Job Description (15 phút)
Text
11. Choose a role you're hiring for22. Use AI to generate job description33. Run bias check44. Refine based on feedbackTask 2: Resume Screening (30 phút)
Text
11. Create Google Sheet for candidates22. Set up Make.com workflow:3 - Email trigger4 - PDF extraction5 - Claude parsing6 - Score calculation73. Test with 3 sample resumesTask 3: Interview Scheduler (20 phút)
Text
11. Set up Calendly event type22. Create email template33. Build automation:4 - Candidate passes screening5 - Auto-send scheduling link64. Test end-to-end📚 Tổng kết
| Concept | Key Takeaway |
|---|---|
| Job Posts | AI generates inclusive, clear descriptions |
| Screening | 100 resumes in minutes, not hours |
| Scoring | Objective criteria, evidence-based |
| Scheduling | Self-service, automated reminders |
| Ethics | Human oversight, bias audits required |
Tiếp theo: Bài 14 - Employee Support - Xây dựng internal Q&A bot cho employees!
