Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

AI Agents, Automation: Build Your Own AI Workflows

Created byPapaHR ★ 170K students: Human Resources, HR Management, SHRM, AI Analytics, Recruitment, Payroll, Certification, CIPD, Claude

Last updated 9/2026

English

English [Auto],

What you'll learn

Отличать AI-агентов от простых чат-ботов, промптов и AI-сервисов
Использовать платформы для создания AI-агентов: ChatGPT GPTs, Mindset AI, Flowise и др.
Применять AI-агентов в рекрутинге: скрининг, ответы, офферы, интеграция с ATS
Встраивать AI-помощников в процессы адаптации, обучения и коммуникации
Автоматизировать performance review, OKR, сбор обратной связи
Настраивать агентов под удержание персонала и прогноз текучести
Создавать собственных HR-агентов без кода — от концепции до финального внедрения
Повышать вовлечённость и снижать нагрузку HR-отдела с помощью AI

Course content

14 sections • 35 lectures • 17h 49m total length

Start Here: Hand Over One Task You Repeat Every Week13:25
The lecture starts with real work: you take one task you repeat every week, write the four roles behind it, put a real name against each one, and find the role nobody owns yet.
This course is built from five disciplines: prompt engineering, agent design, projects and skills, AI in daily work and code-level agents.
The map of the course
A simple dictionary for reading lectures from other fields as agent work
Three questions to ask after every lecture
A short self-diagnostic that shows which sections to watch first
Download the Agent Handover Map and fill in one line after each lecture.

The Seven Blocks of a Working Prompt43:20
Role, context, task, examples, constraints, format, validation
Four classic frameworks — RISEN, CRISPE, CREATE, RTF — and when each fits
Why role and context account for most of the answer quality
Few-shot examples, and the validation block that makes the model check itself
Making the Model Think Deeper27:22
Chain-of-thought, and what it actually adds
Self-consistency: five answers, and picking the reliable one
Tree-of-thoughts for a decision with several criteria
ReAct, where the model chooses its own steps and tools

Context Engineering34:26
The shift from prompt engineering to context engineering
Projects: an assistant loaded with your own documents and rules
Custom instructions and system prompts — set once, works after
Retrieval explained without an API or a developer, and memory across sessions
Prompt, Workflow, Agent25:50
The difference between the three, and what can be handed over end to end
Multi-step workflows where one output becomes the next input
The Model Context Protocol and tool use: reading mail, calendar and sheets
n8n as a visual no-code builder, and where a human has to stay in the loop

What an Agent Is Made Of43:20
The difference between an AI system, a prompt and an agent
The components: model, triggers, memory, actions
The platforms available for building one
How an agent differs from a chatbot, in practice rather than in marketing
Agents in Hiring43:43
The products in this category and what they actually do
Screening, replying, drafting
The limitations and risks, including bias and missing context
Integrating with the systems you already run
Agents in Onboarding34:15
Assistants built on a general model against dedicated products
Answering repeat questions, assigning tasks, guiding someone through a first week
Integrating with Notion, Trello and Slack
Building one on top of a general assistant

Agents in Learning40:54
The products in this category
Individual paths, knowledge checks, generating material
The difference between an AI tutor and a learning platform
Choosing and testing one
Agents in Performance and Goals23:17
The products available
Analysing one-to-ones, tracking goals, coaching prompts
Using them alongside objectives, reviews and development plans
Running a review with agent support
Agents in Communication33:03
The products in this category
Chat support, collecting feedback, explaining policy
The assistant as a first line rather than a replacement
Deploying one into a messenger

Where Everything Lives43:46
Chat, desktop and code environments compared, and which plan you need
Where Projects, Skills, plugins and MCP connectors sit
Installing the desktop app and enabling an official plugin
Connecting Drive, mail and chat, and building a shared knowledge base
Your First Working Project41:23
Custom instructions and a knowledge base for one working area
Writing SKILL.md for four custom skills
Taking apart an official slash command and adapting it
One input, several finished outputs
A Project That Orchestrates a Process23:29
Customising an official command to your own process
Skills that generate packs, plans and checklists
Self-service through a knowledge base
Provisioning that runs through connectors rather than by hand

A Project for Judgment Work19:05
Skills for self-assessment and translating rough notes into structure
Preparation skills that compress a day into an hour
A knowledge base of frameworks the model applies consistently
Where the model checks quality rather than writing for you
A Project That Produces Content26:12
Gap analysis across a team
Generating a personal path for a quarter
Building a micro-course with text, examples and a test
Keeping generated content consistent with your own voice
A Project That Handles Numbers and Documents27:29
Adapting an official analysis command to your own framework
A skill that flags outliers in a dataset
Document generation with a signature route through a connector
A calculator skill using your own formulas

A Project That Answers Questions All Day20:14
Customising a lookup command against a full knowledge base
A triage skill that classifies and routes a case
A drafting skill, and a helpdesk skill
Letting people query it directly from chat, and handling only what is left
Packing It All Into One Plugin21:27
Building the final analytics project
Packing every skill from the course into a single plugin
The manifest file and folder structure
Publishing through a private marketplace or a repository, and the install guide

Where AI Actually Gives Leverage46:32
Mapping your own tasks into categories and finding the leverage
The cycle: augment, then automate, then architect
The stack: chat, projects, skills, desktop, connectors
Your first project as persistent context, and the data that must never go in
Delegating Selection Work24:58
The points in a process where you can actually intervene
Generating a specification from a business need
Screening at volume with a scorecard and explicit red flags
Building a structured interview kit, and the anonymisation step first
Delegating Judgment Preparation20:04
Preparing for a conversation in five minutes rather than an hour
The model as a quality checker rather than an author
Analysing distribution and flagging bias
Frameworks turned into prompts, and rehearsing a difficult conversation

Requirements

Базовое понимание HR-процессов (рекрутинг, адаптация, обучение, удержание)
Уверенный пользователь ПК и интернета
Готовность тестировать новые технологии и инструменты
Не требуется опыт программирования или знание Python/SQL
Рекомендовано: опыт работы HR, L&D, рекрутером или HRBP

Description

This course contains the use of artificial intelligence.

You have been using AI for a year. It answers well. It has never once done anything while you were away from the keyboard.

Where the gap is

Between writing a good prompt and having something that runs on its own there are four steps, and almost everyone stops at the first. You get a useful answer, paste it somewhere, and do the same thing again next week. The vocabulary does not help: agent, workflow, MCP, skill, plugin and orchestration all get used interchangeably by people selling things, so it is genuinely unclear what you are supposed to build, in what order, or whether any of it needs a developer. It does not. But it does need the four steps in sequence, and the gap between them is where the time goes.

What this course covers

Thirty-three lessons through all four. The prompt as a construction first: seven blocks including the validation block most people skip, four classic frameworks, chain-of-thought and self-consistency, tree-of-thoughts for multi-criteria decisions, ReAct where the model chooses its own steps, then the shift to context engineering — projects, custom instructions, retrieval without a developer, and memory across sessions. Then what agents currently do: the components of one, the platforms, real products across six categories with their limitations stated, and building one from scratch. Then the platform layer in depth: where projects, skills, plugins and connectors sit, writing SKILL file, adapting official commands, and packing everything you built into a single distributable plugin with a manifest. Then production: auditing your own week to find the leverage, the augment-automate-architect cycle, data boundaries, building a skill live, connector security, scheduled tasks, cross-application workflows, Computer Use, and proving the time saved. Finally code-level agents: browser work, working across your applications, report agents, unattended automations with checks and rollbacks, and orchestrating five agents with context handoff and an audit log.

A note on the examples

The worked examples come from a people-function context — screening a stack of CVs, building an onboarding pack, assembling a weekly report. That is deliberate: it is a domain with enough repetitive document work to demonstrate a full cycle from prompt to plugin. Nothing about the techniques is specific to it. Seven-block prompts, tree-of-thoughts, MCP, SKILL file, n8n, scheduled tasks and multi-agent handoff behave identically whatever the task is. Also worth knowing: this course names specific products and versions, and some of those will look different in a year. The principles underneath — prompt architecture, the prompt-workflow-agent distinction, human in the loop, data boundaries — will not.

Who is teaching this

I am Mike. I built the people system at Preply as it became a unicorn, and I have worked at Wargaming, iDeals and Alfa-Bank. More than 1.6 million students have enrolled in my courses across 185 countries, and over 150,000 specialists have gone through my programmes. I hold PHRi and SHRM-CP certifications and represent HRCI in more than ten countries.

What is included

Lifetime access to all 33 lessons
Active instructor support in the Q&A section
A Udemy Certificate of Completion
Working material: the seven-block prompt, four prompt frameworks, SKILL file templates, connector safety checklist, scheduled automation patterns, the multi-agent handoff model, a 90-day roadmap
Everything built without writing code

Where to start

Name one thing you do every week that produces a document from other documents. That is the task this course automates, and by the end it should be running on a schedule without you. Enrol now and start today.

Who this course is for:

HR-специалисты, желающие внедрить AI-агентов в повседневную работу
Руководители HR, стремящиеся автоматизировать процессы без потери качества
Digital HR, HR-аналитики и L&D-менеджеры
Рекрутеры и People Partners, ищущие инновационные решения
Все, кто хочет управлять AI, а не бояться его

AI Agents, Automation: Build Your Own AI Workflows

What you'll learn

Explore related topics

Course content

Start Here1 lecture • 13min

The Prompt as a Construction2 lectures • 1hr 11min

From Prompting to Agents2 lectures • 1hr

What Agents Already Do3 lectures • 2hr 1min

Agents Across a Function3 lectures • 1hr 37min

Prediction and Building Your Own2 lectures • 1hr 10min

The Platform: Projects, Skills and Connectors3 lectures • 1hr 49min

Judgment, Content and Analysis Projects3 lectures • 1hr 13min

Support Projects and Packing a Plugin2 lectures • 42min

Auditing Your Own Work for Automation3 lectures • 1hr 32min

Requirements

Description

Who this course is for: