AI for HR
Build two working AI agents for your HR team — no coding, no theory-only slides, and nothing that stays in the classroom.
A hands-on, no-code course that takes HR professionals from AI-curious to AI-capable in two full-day sessions. You build a real AI Recruiter that screens and ranks candidates, an HR Generalist that answers policy questions and files tickets, and a Compliance Guardian that audits both — all grounded in a complete fictional company corpus and governed by the EU AI Act and GDPR rules that make every guardrail a legal requirement.
Who it's for — HR professionals, HRBPs, talent acquisition partners, and HR leaders who want to use AI to do their actual job better — no coding background required.
- Explain how AI models work, why they hallucinate, and what HR must do about it — in your own words, to your CEO or board
- Map your HR processes to where retrieval, agents, and human review actually belong — and where they don't
- Build an AI Recruiter end-to-end in Dify: read a workforce plan, draft a JD, screen real résumés, cross-check interview minutes
- Build an HR Generalist agent: answer policy questions from your handbook, look up live PTO balances over MCP, and file HR tickets with a human-approval guardrail
- Build a Compliance Guardian that audits your other agents against the company guide and escalates doubtful answers to a human manager
- Apply EU AI Act and GDPR rules to AI in HR — know what's high-risk, what triggers Article 22, and the five deployer obligations
You leave with Two working HR agents plus a compliance auditor that supervises them.
These aren't demos — they're working agents you build hands-on and tailor to your own role, data, and custom spec.
AI Recruiter
A four-step screening pipeline that grounds in the workforce plan, revises the job description against real skill gaps, ranks every candidate with cited evidence, and cross-checks resumes against interview notes to flag discrepancies—always pausing for human review before anyone is contacted.
HR Generalist
A routing agent with three capabilities—answer policy questions from the handbook with citations, look up live data like PTO balances over MCP, and draft HR tickets that only file after a human says yes.
Compliance Guardian
A supervisor agent that audits another agent's answer against the governing policy, scores it 0–100 on grounding, policy-compliance, privacy, and scope, and escalates anything below threshold to a named human manager—never the final word itself.
How you build them, class by class
Foundations, RAG & Agents, and Your First Knowledge Base
- How LLMs generate text — tokens, context windows, temperature, system prompts, and hallucination
- The five-part prompt anatomy: role, context, task, constraints, format — and two prompting techniques that are guardrails
- Build a Dify knowledge base over 29 a realistic company HR documents and pressure-test it with real questions
- Build Eirini's AI Recruiter: ground in the workforce plan, draft a revised JD, screen and rank résumés, cross-check résumés against interview minutes
- Design the human-oversight checkpoints — Green / Amber / Red for each recruiter step — the same question regulators ask
Build Two Agents, Run a Graded Eval
- Build Katerina's HR Generalist: three capabilities (Answer, Look Up, Act) each with its own guardrail — nothing filed without human confirmation
- Connect the agent to live data over MCP so PTO balances are always current, not stale
- Build the Compliance Guardian: a supervisor agent that scores other agents' answers 0–100 and escalates the doubtful ones to a named human
- Wire all three agents together over 2-way MCP so the guardian can pull live sessions and workers can call the guardian for pre-checks
- Run both agents through a graded 10-question eval balanced for coverage, diversity, and criticality
- EU AI Act and GDPR: prohibited categories, high-risk HR duties (Art. 26), GDPR Art. 22, and the penalties that make every guardrail a legal requirement
The names the whole industry runs on.
Dify
One of the most popular open-source platforms for building AI agents — you assemble your recruiter, generalist, and guardian visually, no code required.
Gemini 2.5 Flash
Google's fast, low-cost model and the backbone of every agent you build — its free tier covers the entire course.
MCP (Model Context Protocol)
The fast-emerging open standard for connecting AI to live data and tools — how your agents pull real PTO balances and talk to each other.
Plus the rest of the working stack — Dify · Gemini 2.5 Flash · Claude · ChatGPT · Gemini · MCP (Model Context Protocol) · generate_eval_questions.py (corpus-driven balanced eval generator) · n8n · Flowise · LangFlow · Make · LangChain.
Your hands-on capstone: two working AI agents (the AI Recruiter and the HR Generalist), a Compliance Guardian that audits them, and a graded 10-question eval proving how good they actually are. The work is grounded in the full a realistic company corpus throughout. This is what your certificate is based on — not attendance.
Your certificate is based on what you build — not attendance.
Ready to build your AI agent?
A small, high-quality cohort for leaders — fully online, hands-on from minute one.