I built a working AI recruitment screening demo that shows how a hiring team can use AI without handing over the final decision.
The flow is simple:
A job spec goes in.
Candidate profiles are screened against a weighted guideline.
Each candidate gets a score, band, evidence quotes, and risk flags.
Then everything stops at a human review queue.
No auto-rejects. No silent ATS updates. No “AI decided this person is out”.
The system includes:
Candidate pipeline table
Evidence-based screening view
Human review queue
Approve / reject / snooze decisions
ATS deployment plan
Audit log for compliance
n8n workflow export with a human-in-the-loop Wait node
Optional live Claude screening path
The important part is the architecture: deterministic logic owns the workflow, gating, state and audit trail. The AI helps with judgement and screening, but the human owns the final decision.
Built with Next.js, TypeScript, Claude API, n8n workflow architecture, and a gated ATS sync pattern.
This is the kind of system I like building: AI that makes the work faster, but still respects the places where people need control.
Shorter Version
I built an AI recruitment screening pipeline with a human approval gate.
It screens candidates against a rubric, shows evidence quotes and risk flags, then routes every candidate into a review queue before anything reaches the ATS.
No auto-rejects. No silent updates. Human-in-the-loop by design.
Built with Next.js, TypeScript, Claude API and n8n workflow architecture.
Take a vampire, a grim reaper and a bat for a midnight ride through a haunted town. Hold to boost over broken track, brake before the big hills, and grab candy to refill your boost. Push your luck too far and your passengers end up splattered across the screen.
What if every new lead could be handled before you even open your inbox? ⚡
This AI-powered workflow turns a new email inquiry into a structured, ready-to-handle lead — automatically.
A new inquiry arrives → AI extracts the important details → Airtable/CRM is updated → the response goes through optional human approval → a personalized email is sent → Notion is updated → the team gets notified in Slack → performance data is collected for reporting.
The goal isn't to remove people from the process. It's to remove the repetitive work around them.
This type of workflow can be customized for B2B companies, SaaS businesses, agencies, real estate, e-commerce, recruitment, consulting, customer support, healthcare, finance, education, and other service businesses.
Already know what you want to automate? → Send me your current workflow and I’ll map out how we can automate it.
Still doing repetitive work manually? → Tell me the task that consumes your team’s time, and I’ll help identify what can be automated.
I'd use the human approval step to capture corrections, not just a yes/no decision. If a reviewer changes the extracted lead details, does the workflow update Airtable and the reporting record before sending the email?