
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.
Tools in this lecture
Files to download (1)
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
Tools in this lecture
Files to download (3)
Ready to use on the slides (11)
Models and methods explained (2)
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
Tools in this lecture
Files to download (3)
Ready to use on the slides (8)
Models and methods explained (4)
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
Tools in this lecture
Files to download (3)
Ready to use on the slides (9)
Services and apps shown in this lecture (1)
Models and methods explained (2)
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
Tools in this lecture
Files to download (4)
Ready to use on the slides (7)
Services and apps shown in this lecture (1)
Models and methods explained (3)
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
Tools in this lecture
Ready to use on the slides (5)
Services and apps shown in this lecture (1)
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
Tools in this lecture
Ready to use on the slides (3)
Services and apps shown in this lecture (1)
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
Tools in this lecture
Ready to use on the slides (4)
Services and apps shown in this lecture (3)
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
Tools in this lecture
Ready to use on the slides (2)
Services and apps shown in this lecture (3)
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
Tools in this lecture
Ready to use on the slides (4)
Services and apps shown in this lecture (2)
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
Tools in this lecture
Ready to use on the slides (1)
The products in this category
Predicting departures and flagging strain early
Training on internal data, and the care that requires
Modelling a forecast
Tools in this lecture
Ready to use on the slides (2)
Services and apps shown in this lecture (1)
Models and methods explained (1)
Choosing a platform
Agent architecture: goal, memory, actions, interface
Building one for a single real task
The final project: an agent that is actually yours
Tools in this lecture
Ready to use on the slides (1)
Services and apps shown in this lecture (1)
Models and methods explained (1)
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
Tools in this lecture
Files to download (3)
Ready to use on the slides (5)
Services and apps shown in this lecture (1)
Models and methods explained (2)
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
Tools in this lecture
Files to download (4)
Ready to use on the slides (12)
Services and apps shown in this lecture (1)
Models and methods explained (2)
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
Tools in this lecture
Files to download (3)
Ready to use on the slides (12)
Services and apps shown in this lecture (3)
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
Tools in this lecture
Files to download (3)
Ready to use on the slides (14)
Services and apps shown in this lecture (1)
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
Tools in this lecture
Files to download (3)
Ready to use on the slides (13)
Services and apps shown in this lecture (1)
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
Tools in this lecture
Files to download (3)
Ready to use on the slides (6)
Services and apps shown in this lecture (1)
Models and methods explained (1)
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
Tools in this lecture
Files to download (3)
Ready to use on the slides (7)
Services and apps shown in this lecture (1)
Models and methods explained (1)
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
Tools in this lecture
Files to download (3)
Ready to use on the slides (11)
Services and apps shown in this lecture (1)
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
Tools in this lecture
Files to download (2)
Ready to use on the slides (11)
Services and apps shown in this lecture (1)
Models and methods explained (5)
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
Tools in this lecture
Files to download (3)
Ready to use on the slides (15)
Services and apps shown in this lecture (1)
Models and methods explained (3)
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
Tools in this lecture
Files to download (3)
Ready to use on the slides (10)
Services and apps shown in this lecture (1)
Models and methods explained (4)
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. Here are 404 tools to change that: 273 ready-to-use AI prompts, workflows, checklists and templates, 79 working files, 39 models and methods, and 13 services shown on screen.
Open a lecture, take the prompt or the setup checklist, and build your first project today.
Why most people stop at the first step
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 tomorrow. The context lives in your head, the checks happen when you remember, and nothing runs at night.
What changes after this course
Your prompts are built, not improvised. Your knowledge lives in projects and skills, connectors bring in the data, and agents run on a schedule, report back and alert you when something fails. You know which part of your week to automate next, and you check the output before anyone else sees it.
What is inside: 404 tools, counted lecture by lecture
You do not have to take this number on trust. Open any lecture and read its description: every tool inside is listed there by name.
Where the tools are
Prompting as construction (2 sections, 61 tools). Prompt architecture, techniques and the move from prompting to agents.
Agents in practice (3 sections, 32 tools). What agents already do across a function, prediction and the first agent of your own.
The platform: projects, skills and connectors (3 sections, 114 tools). Projects for judgment, content and analysis, support projects and packing a plugin.
Finding what to automate (2 sections, 103 tools). Auditing your own work, analysis and communication with AI.
Building and orchestrating agents (3 sections, 110 tools). Your own agents, code-level agents, reporting, scheduling and orchestration.
Who is teaching
I am Mike, the #1 HR instructor on Udemy, with 1,800,000+ course enrollments from 170,000 students, and the author of about 200 books on Amazon. I built the people system at Preply as it became a unicorn and worked at Wargaming, iDeals and Alfa-Bank across 20 years in HR. I hold PHRi, SHRM-CP and HCI sHRBP certifications and represent HRCI in Eastern Europe. I am also a founder and lead the strategy of my own academy.
When everyone around me started writing about Claude, I registered, ran two or three of my own tasks, used up all the tokens and took the $20 subscription. Then I moved to $100 a month and a week later to $200, and I do not regret it: the time I save grew from 10 hours a week to 20, then 40, and now about 80. When a task takes too long, I ask Claude for a retrospective: what slowed us down, and what to change next time.
How to use the course
Go through the prompting sections first, then set up one project and one agent on a task from your own week. Section and lecture titles show how many tools are inside, and each lecture description lists them by name.
What is included
Where to start
Write down three tasks you repeated last week, then open the section on auditing your work for automation and pick the first one to hand over. Enrol now and start your first lesson today.