AI Recruiter

Screens every CV against your must-haves and drafts outreach to the best fits. Role: Recruiter / Sourcer.

Example shift, AI Recruiter · drafts wait for your reviewSynthetic example data

11:10
CV: M. Okafor · Senior Support LeadMeets 5/5 must-haves · score 86 · shortlisted
Draft ready
11:11
Outreach draft to M. OkaforNext step: 20-minute intro call
Draft ready
11:12
CV: R. SilvaMissing “Spanish C1” must-have · score 58 · below your bar
Needs you
11:14
CV: unreadable scanFlagged for a person to read; no score given
Needs you
11:15
Candidates sheet updated38 CVs screened: 9 shortlisted, 27 below bar, 2 flagged
Logged

Example week at “hiring push” volume: ≈ 13.8 h of first-pass work taken over (estimate)Open the setup guide

Implementation in your business

Behind your job post: candidates land in a sheet (from your form or ATS export); it screens each CV against your must-haves and drafts outreach.

Where it plugs in

Evidence-based CV screening (score, must-have checklist, strengths, gaps, interview questions) plus outreach drafts. A human decides.

What it needs

n8n (Cloud or self-hosted)
Google account: Sheets + Gmail
OpenAI API key
Job description, must-haves, nice-to-haves (Config)

What it outputs

Score and written reasons per candidate
Shortlist status in the sheet
Gmail outreach drafts for shortlisted candidates

Time saved (estimate)

≈ 60 h

per month at 150 CVs a week, 7 min by hand vs 1.5 min review. See assumptions.

Setup: about 15 minutes on n8n Cloud

Three steps, no code. The setup guide has the full checklist.

Step 1 · 1 min

Pick the AI Recruiter

Start the trial on Starter (this employee) or Workforce (all five). The download link and guide arrive by email.

Plans

Step 2 · 3 min

Import it

n8n Cloud or self-hosted: Workflows → Import from file. No n8n? Paste the instructions into a Custom GPT or Claude Project.

1 workflow file
Sheet templates (CSV)

Step 3 · 10 min

Connect your tools

Google Sheets
OpenAI
Gmail
Config: your details and rules

Full setup checklist

How it works

Import-tested and test-executed with stubbed services on n8n 2.44 before release.

Structured, explainable scoring. 70 points for must-haves (each marked met / partial / not met / unknown with CV evidence), 20 for nice-to-haves, 10 for clarity of impact.

Fairness rules built in. The prompt forbids using name, gender, age proxies, nationality, photos and similar, and marks missing info as unknown, not as a fail.

Advisory only. It never rejects or emails anyone. You get a ranked sheet and drafts; you decide.

What you get

ai-recruiter.n8n.json: Candidates tab (status = new) → download CV PDF or use pasted text → extract text → LLM scorecard against your must-haves → outreach Gmail draft for shortlisted candidates → sheet.
No-code version: Custom GPT / Claude Project instructions
Prompt library, sheet templates and a PDF setup guide

What it's worth to you

The value is time: the employee does the first pass and you keep the review. Two worked examples, every input an assumption:

Estimates from the assumptions in the table, not measured results. Review minutes = reading the agent's scorecard and skimming the CV. Every candidate is still reviewed by a person. No claims about quality of hire or time-to-hire.
Assumption (estimate)	One open role	Hiring push
CVs screened per week	30	150
Manual minutes per CV	5	7
Review minutes (you still review)	1.5	1.5
Share the employee handles	100%	100%
Hourly cost of whoever does it	$35	$45
AI running cost per CV	$0.03	$0.03
Hours taken over per week	1.8 h	13.8 h
Value of that time per month, after AI costs	≈ $262	≈ $2,662
After the $19 Starter plan	≈ $243	≈ $2,643

Try your own numbers

AI employee

Items per week

Minutes per item, done by hand Time yourself on 3 real examples.

Hourly cost of whoever does it ($)

More assumptions

Minutes to review each output You still review everything.

Share the employee handles (%) e.g. support emails answerable from your knowledge base.

AI running cost per item ($)

Plan cost per month ($) Starter is $19, Workforce $49 for all five.

Hours taken over per week-

Hours per month-

Value of that time per month-

Net per month after AI costs and plan-

Hours saved needed to cover the plan-

Formula: hours/week = volume × share handled × (manual − review minutes) ÷ 60 · hours/month = hours/week × 52 ÷ 12 · net = hours/month × hourly cost − AI running costs − plan cost. Time saved only; no claims about revenue, replies or hiring outcomes.

Questions

Does it work with my ATS?

v1 uses a Google Sheet. Most ATSs export CSV; Greenhouse, Lever and Workable also have APIs n8n can call. Email support if you want pointers.

Does it reject candidates?

No. It writes a scorecard and creates outreach drafts only. People make decisions.

Do I need n8n?

For the automated version, yes: n8n Cloud or the free self-hosted edition. Every employee also ships a no-code version for a ChatGPT Custom GPT or a Claude Project.

Does it act on its own?

It works in drafts and logs. Anything that reaches a customer, candidate or prospect is a draft you review and send.

What does it cost?

Starter is $19/month for this employee, Workforce $49/month for all five. Both have a 7-day free trial. You also pay your own AI usage (usually cents per item) and your n8n plan if you use n8n Cloud.

Guardrails

EU AI Act: AI used to screen or rank job applicants is classed as high-risk. Use this pack as decision support with meaningful human review; don't auto-reject. Tell candidates you use AI-assisted screening and keep records. Check your obligations with counsel. Not legal advice.
GDPR: CVs are personal data. Have a lawful basis, tell candidates how their data is processed (including by your LLM provider), and set a retention period.
Audit periodically: compare scores across groups you can lawfully monitor, and read a sample of not_a_fit scorecards by hand.

Put the AI Recruiter to work.

Start 7-day free trial$19/mo for this employee, or $49/mo for all five.