Candidate Screener for Recruiting
An AI agent that handles candidate screening for hr / people teams in recruiting & staffing businesses. Triggered by document upload, it classifies and categorises, extracts structured data, summarises, with human review on exceptions.
Reviewing hundreds of resumes manually doesn't scale. This agent screens applications against job requirements, advances strong matches, and sends polite rejections — so recruiters spend time on candidates, not paperwork.
Ideal For
- HR managers
- People ops
- Talent acquisition
- Teams in recruiting & staffing
Data Sources
- Email inbox
- Shared drive (Google Drive, OneDrive)
- Spreadsheet (Google Sheets, Excel)
Trigger
Workflow starts when: Document upload
Collect Data
Retrieve data from: Email inbox, Shared drive (Google Drive, OneDrive), Spreadsheet (Google Sheets, Excel)
Classify / Categorize
Perform: classify / categorize on the collected data
Extract structured data
Perform: extract structured data on the collected data
Summarize
Perform: summarize on the collected data
Route task to person
Perform: route task to person on the collected data
Human Review
Human approval: Review exceptions only
Complete & Log
Log activity, update records, and close the workflow
If: Resume matches 80%+ of required skills
Then: Advance to phone screen queue
If: Resume has significant skill gaps
Then: Send polite rejection email
If: Candidate is internal or referral
Then: Flag for priority review by hiring manager
If: Resume is in a non-parsable format
Then: Request resubmission in PDF or DOCX
Never expose API keys or credentials in outputs
Only perform actions within defined workflow scope
Maintain formal, business-appropriate language
Flag unusual patterns for human review
Enforce rate limits on automated actions
- If resume parsing fails, fall back to keyword-based screening and flag for manual review
- If a candidate applies to multiple roles, consolidate applications and route to talent lead
- If no human response within 4 hours, send reminder and escalate to backup
- Tasks processed per day
- Error/failure rate
- Resume screening time per candidate
- Screening accuracy vs. human reviewers
- Quality-of-hire for auto-advanced candidates
- Human intervention rate
System Prompt
You are a HR / People AI assistant specialized in candidate screening. ## Your Role You help hr / people teams by automating candidate screening tasks. Your communication style is professional. ## Capabilities You can: classify / categorize, extract structured data, summarize, route task to person. ## Guidelines - Always be accurate and verify data before acting - Flag uncertain cases for human review - Maintain professional tone - Never make promises or commitments on behalf of the organization - Respect data privacy and confidentiality - Log all significant actions for audit purposes ## Constraints - Only access data sources explicitly provided - Do not perform actions outside your defined scope - Escalate edge cases rather than guessing
Starter User Prompt
Process this document upload: [INSERT DATA HERE] Perform candidate screening according to your guidelines. Provide: 1. Classification/analysis 2. Recommended action 3. Draft output (if applicable) 4. Any flags or concerns
Handoff Prompt
This task requires human attention. Here is what I have processed: ## Summary [Brief description of what was done] ## Analysis [Key findings and classification] ## Recommended Action [What should happen next] ## My Concerns [Any flags, uncertainties, or edge cases] Please review and respond when available. Please review and advise how to proceed.
# Candidate Screener - Standard Operating Procedure ## Purpose This SOP defines how the Candidate Screener operates within the organization. ## Trigger Document upload ## Data Sources - Email inbox - Shared drive (Google Drive, OneDrive) - Spreadsheet (Google Sheets, Excel) ## Process Steps 1. Classify / Categorize 2. Extract structured data 3. Summarize 4. Route task to person ## Human Oversight Review exceptions only ## Escalation Path 1. Agent flags issue 2. Notification sent to assigned reviewer 3. If no response in 4 hours, escalate to backup 4. Log all escalations ## Review Schedule Monthly review of agent performance and rules
- 1Define access credentials for all data sources
- 2Set up automation platform (n8n/Zapier)
- 3Configure AI API access (OpenAI/Claude)
- 4Create trigger workflow
- 5Connect input data sources
- 6Implement classify / categorize step
- 7Implement extract structured data step
- 8Implement summarize step
- 9Implement route task to person step
- 10Configure human review/approval workflow
- 11Set up notification channels for reviews
- 12Test with sample data
- 13Configure error handling and alerts
- 14Set up logging and monitoring
- 15Document and train team
- 16Deploy to production
- 17Schedule first review
n8n Workflow
## n8n Workflow Outline ### Trigger Node - Type: Document upload - Configuration: Set up webhook/schedule/email trigger ### Input Nodes - Email inbox: HTTP Request or native integration node - Shared drive (Google Drive, OneDrive): HTTP Request or native integration node - Spreadsheet (Google Sheets, Excel): HTTP Request or native integration node ### Processing Nodes 1. OpenAI Node: Classify / Categorize 2. OpenAI Node: Extract structured data 3. OpenAI Node: Summarize 4. Function/HTTP Node: Route task to person ### Approval Node - Wait Node with Slack/Email notification - Resume on approval webhook ### Output Nodes - Update destination systems - Send notifications - Log activity
Zapier Zap
## Zapier Workflow Outline ### Trigger (Zap starts when...) - Document upload ### Data Lookup Steps - Search/Lookup in Email inbox - Search/Lookup in Shared drive (Google Drive, OneDrive) - Search/Lookup in Spreadsheet (Google Sheets, Excel) ### Action Steps 1. ChatGPT by Zapier: Classify / Categorize 2. ChatGPT by Zapier: Extract structured data 3. ChatGPT by Zapier: Summarize 4. App Action: Route task to person ### Approval Path - Use Paths or Delay Until to pause for approval - Send notification via Slack/Email ### Final Actions - Update records - Send completion notification
Example Use Cases
- •Screen resumes against job requirements and rank by match score
- •Auto-send rejection emails for clearly unqualified applications
- •Fast-track internal candidates and referrals for hiring manager review
Tools Needed
Frequently Asked Questions
What does the Candidate Screener do?
An AI agent that handles candidate screening for hr / people teams in recruiting & staffing businesses. Triggered by document upload, it classifies and categorises, extracts structured data, summarises, with human review on exceptions.
Does it replace human recruiters?
No. It handles the initial screening of high-volume applications so recruiters can focus their time on shortlisted candidates and relationship-building.
How does it avoid bias in screening?
The agent scores against explicit job requirements only (skills, experience, qualifications). It does not consider name, age, gender, or other protected characteristics.
Can I override the agent's decision?
Yes. Every screening decision is logged with the reasoning. Recruiters can override any auto-reject or auto-advance and feed that back to improve accuracy.
What level of technical skill is needed?
Basic familiarity with workflow automation tools (Zapier/n8n) is helpful. No coding is required for most implementations, though API integration experience helps for advanced setups.
Best For
- •You receive 100+ applications per open role
- •Screening takes more recruiter time than interviewing
- •You need consistent, bias-free initial screening
Not Ideal For
- •You receive fewer than 20 applications per role
- •Every application requires in-depth, subjective evaluation
- •Screening criteria are too fluid for rule-based automation
Review Before Launch
- All integrations tested with real credentials
- Error handling and retry logic configured
- Notification channels set up for alerts
- Team trained on reviewing exceptions
- KPI dashboard configured
- Rollback plan documented
Ready to implement your Candidate Screener? Use this blueprint to guide your setup in n8n, Zapier, or your preferred automation platform.
Related Agent Blueprints
Onboarding Coordinator for SaaS
Coordinate new hire onboarding with automated task assignments.
Same FunctionLeave Request Router
Route leave requests to appropriate managers for approval.
Same FunctionRecruitment Inbox Sorter for Agencies
Sort incoming job applications by role and seniority level.
Same FunctionLead Enrichment Agent for Recruiting
Enrich candidate employer leads with company and contact data.
Same IndustryInterview Scheduler for Recruiting
Schedule interviews based on candidate and interviewer availability.
Same IndustryReceipt Categorizer for Accounting Firms
AI-powered expense categorization with GL code assignment.
Same Trigger