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 for Business Analysts: Prompts, Agents, Documents [EN]

New

Created byPapaHR ★ 160K students: Courses in Human Resources, HR, SHRM, AI Talent Analytics, HRMS, HRIS, CIPD, Claude, HRCI, PHR, Rewards

Last updated 6/2026

English

What you'll learn

Вы будете учиться с 2 млн других студентов PapaHR из 185 стран
Вы получите опыт Preply, Wargaming, Radford, Deloitte от автора курса
Собирать команду из 5 готовых AI-агентов для HR-аналитики: Куратор, Аналитик, Детектив, Предиктор, Репортёр
Очищать выгрузки из любого HRIS (BambooHR, Workday, PeopleForce, HiBob, 1С) через Claude за 30 минут
Строить описательный портрет компании: headcount, демография, attrition, hiring funnel — без единой формулы
Создавать пивоты, графики и дашборды через Claude в Excel
Диагностировать реальные причины текучести по паттерну «вопрос → подзапрос → срез»
Находить pay gaps и аномалии по менеджерам, отделам, уровням и tenure
Строить риск-скоринг сотрудников и прогноз ухода на квартал — без ML и Python
Рассчитывать прогноз ФОТ и hiring needs на следующий квартал
Превращать аналитику в board-ready презентацию через связку Claude + Excel + PowerPoint
Говорить с CEO на языке $-эффекта, а не HR-метрик

Course content

13 sections • 35 lectures • 18h 51m total length

The Analyst Mindset: Problem, Goal, Constraint, Metric37:37
Translating business value into a solution
Problem mindset against solution mindset
Telling a symptom from a problem
Value-driven analysis, and the Problem to Goal to Constraint to Metric framework
Requirements Gathering: Stakeholder Mapping and Value Against Effort33:41
Stakeholder mapping and influence analysis
Elicitation techniques
Asking the business the right questions
Working with conflicting requirements, and prioritising by value against effort
Formalising Requirements: User Stories, Acceptance Criteria, BRD28:39
Business, functional and non-functional requirements
User stories: structure, examples and anti-patterns
Acceptance criteria in Given-When-Then form
Use cases, BRD, SRS, PRD, and the definition of ready

Business Processes and Modelling: AS-IS, TO-BE and BPMN28:57
What a business process means in practice
The AS-IS and TO-BE approach
The minimum necessary BPMN
Finding bottlenecks and waste, and proposing improvements rather than diagrams
Systems and Functional Thinking: Decomposition and Traceability23:00
The system context diagram
Functional decomposition
User flows, data objects and business rules
Non-functional requirements and traceability
Working With Change: Backlog, Change Requests and Impact Analysis28:17
Working in Agile, Scrum and waterfall
The backlog and requirements that keep moving
Change requests and impact analysis
Managing scope, and defending requirements to both sides

Why Describe Processes, and Which Ones to Start With49:06
Who should own process description
What describing a process actually buys you
What a description consists of
Which processes are worth describing first, especially before automating anything
Methodology: How Processes Are Described, Flowcharts and BPMN42:39
How processes are described around the world
Which methodology fits your situation
Using flowcharts
A simple BPMN diagram, and analysing what it reveals
Tools for Describing Processes: Models, Templates and Software24:51
Process description models
Templates worth reusing
The software available
A worked description using online tools

What You Get Out of It: Implementing and Adjusting a Process37:05
What the output actually is
Implementing a described process so people follow it
Evaluating whether it works
Adjusting it afterwards
Examples: Onboarding, Recruitment, Training, Performance, Offboarding32:45
Describing onboarding
Describing recruitment
Describing training and performance management
Describing offboarding
Running a Process Description Project From Concept to Closure31:12
Creating the project team and choosing the processes
Preparing the concept and defending it with management
Launching, and reporting on the project
Closing it and monitoring what happens next

AI Basics: What It Can and Cannot Do, and How to Ask It Properly47:50
What a large language model is: capabilities and limitations
A short history, and what the alternatives are
How to formulate a prompt so the answer is usable
Working with the interface, and where the field is heading
AI for Personal Productivity: Tasks, Plans and Prompt Templates43:28
Organising tasks and plans
Generating ideas and support for decisions
Optimising your own processes with ready prompt templates
Practical examples
AI for Work: Documents, Reports, File Analysis and Custom GPTs43:28
Drafting business correspondence and documents
Producing reports, instructions and templates quickly
Analysing information and files
Building a custom assistant on your own documents, tuned to your role

AI for Creative Work: Ideas, Rewriting and Adapting a Style41:36
Generating ideas, names and wording
Creating content for different formats
Rewriting, improving and adapting text to a required style
Working with generated images
AI for Analysis and Learning: Structuring, Summaries, Research41:06
Finding and structuring information
Producing summaries, lists and analytical material
Studying a new domain through questions and dialogue
Prompts for developing a skill quickly
Advanced Techniques: Integrations, Complex Prompts and Automation18:22
Integrating AI into everyday processes through apps and automation
Building complex prompts for precise answers
Non-standard tasks, from wording to strategy
Services built on top of these models

Prompt Architecture: The Seven Blocks and Four Frameworks43:20
The seven blocks of an advanced prompt: role, context, task, examples, constraints, format, validation
RISEN, CRISPE, CREATE and RTF, and when each applies
Why role and context account for most of the answer quality
Few-shot examples, and the validation block that makes the model check itself
Advanced Reasoning: Chain of Thought, Tree of Thoughts and ReAct27:22
Chain-of-thought and the accuracy it adds
Self-consistency: several answers, and picking the reliable one
Tree-of-thoughts for multi-criteria assessment
ReAct, and combining techniques inside a single prompt

Context Engineering: Projects, Custom Instructions, RAG and Memory34:26
The shift from prompt engineering to context engineering
Projects: an assistant loaded with your own policies, templates and documents
Custom instructions and system prompts: set up once, works afterwards
RAG explained without an API, and managing context across sessions
Real Agents: Multi-Step Workflows, MCP, Tool Use and n8n25:50
The difference between a prompt, a workflow and an agent
Prompt chains where one output becomes the next input
MCP and tool use: reading mail, calendar and spreadsheets
n8n as a no-code builder, and where a human still has to approve

AI Operations Architecture: Projects, Skills, Plugins, Connectors43:46
The landscape: the assistant, the desktop workspace and the coding agent
Where Projects, Skills, Plugins and MCP connectors each live
Setting up a workspace and connecting Drive, mail and messaging
Building the company-wide knowledge base every other Project inherits
Your First Project: Custom Instructions and a Knowledge Base41:23
Building a Project with role-specific instructions and a reference knowledge base
Writing four custom Skills for one workflow
Taking apart an official command and adapting it to your own rules
Worked on a recruiting workflow: job description, search strings, screening rubric, draft offer
Writing Custom Skills: SKILL.md and Reusable Commands23:29
Customising an official command for your own process
Writing Skills that generate a pack of documents from one input
Building a self-service knowledge base for repeated questions
Worked on onboarding: welcome pack, 30-60-90 plan, day-one checklist, access list

Turning Free-Text Notes Into a Structured Document19:05
A Skill that converts unstructured notes into a structured assessment
Loading a framework library so the output follows a known format
Preparing a calibration session in an hour instead of a day
Worked on performance review, with SBI and STAR as the frameworks
Generating Content at Scale: Gap Analysis, Paths and Assessments26:12
A Skill for gap analysis across a group
Generating an individual plan from the gap
Building a micro-course with text, examples and a test
Keeping generated content consistent with a defined brand voice
Analysing an Export: Outliers, Rules and Generated Documents27:29
Adapting an official analysis command to your own framework
A Skill that ingests a system export and flags outliers against rules
Generating a document from the result and routing it for signature via a connector
Worked on compensation: pay equity, offers and variable pay

Requirements

Желание обучаться у человека, который создал HR систему Unicorn Preply
Амбиции стать номер 1 в People Analytics и AI-аналитике для HR
Готовность идти вперед, не оглядываясь назад, пройти весь курс и применить знания
Базовые навыки Excel на уровне таблиц — всё остальное сделает Claude
Доступ к Claude (рекомендуется Claude Pro для связки с Excel)
Не требуются SQL, Python, Tableau или опыт в дата-аналитике

Description

This course contains the use of artificial intelligence.

Most analysts have tried AI, received something that read well and meant little, and quietly gone back to writing everything themselves.

The output was mediocre because the input was a sentence. What produces usable work is a structure, and the structure is learnable.

Why the first attempt disappoints

You asked for a document and got a plausible one, with the specifics invented. You asked for analysis and got a summary of what you had already written. The model had no access to your policies, your definitions or your templates, so it answered from the general internet. And every time you wanted the same output again, you rebuilt the request from scratch, which means nothing accumulated.

None of that is a limitation of the technology. It is what happens when a tool designed to run on context is used without any.

What the course covers

Thirty-five lessons in three layers. The analyst's craft first, twelve lessons: framing a problem before writing a requirement, user stories with acceptance criteria, AS-IS and TO-BE modelling, impact analysis, and describing processes in BPMN — because a process nobody has described cannot be automated, only accelerated in its confusion.

Then the AI fundamentals: what these models can and cannot do, working with files, building a custom assistant on your own documents. Then prompt engineering properly — the seven blocks of a prompt, the four classic frameworks, chain-of-thought and tree-of-thoughts, ReAct, and the shift from prompting to context engineering with Projects, RAG and memory.

Building things that keep working

Then eight lessons on the operations layer, which is where this stops being about chatting. Projects with their own instructions and knowledge base, custom Skills written as plain text files so a workflow runs identically every time, connectors to your drive, mail and messaging through MCP, retrieval over your own documents, and packaging the whole set into a plugin your team installs with one command.

And finally five lessons of analysis end to end: a raw system export turned into a clean dataset, descriptive analysis without manual formulas, diagnosis of causes and anomalies, forecasting through interpretable rules rather than an unexplainable model, and a board-ready presentation defended in front of people who will push back.

A note on the examples

The AI sections are taught on people and operations data — recruiting, onboarding, reviews, pay. The methods are domain-neutral: a Skill is a Skill, a RAG setup is a RAG setup, and the PEARL analysis cycle works on any dataset. I have kept the worked examples as they were recorded rather than genericising them, because a real dataset teaches more than an invented one.

Who is teaching this

Mike, the number one HR instructor on Udemy. More than 1.6 million course enrolments, over 150,000 professionals trained, PHRi and SHRM-CP certified, HRCI representative in more than 10 countries. I built the people function of the unicorn Preply and worked at Wargaming, Alfa-Bank and iDeals.

What is included

Lifetime access to all course materials
Active instructor support in the Q&A section
Udemy Certificate of Completion
Practical assignments and real business cases
A section with additional courses, tools and resources

Take the document you write most often and build it as a Skill during the course. That single artefact usually pays back the time before you finish. Enrol now and start the first lesson today.

Who this course is for:

Человек, который берет ответственность за свое обучение
Готов выделить время на обучение, пройти курс и добиться результата
HR-менеджеры и HRBP, которые работают с данными каждый день, но делают это вручную и неэффективно
Рекрутеры и Talent-специалисты, которым нужно обосновывать решения по найму цифрами, а не интуицией
Head of People и HRD, которые хотят перевести HR-функцию на AI и вести диалог с CEO на языке данных
C&B, L&D и OD-специалисты, которым нужна аналитика по своей зоне без аналитика в команде

AI for Business Analysts: Prompts, Agents, Documents [EN]

What you'll learn

Explore related topics

Course content

The Analyst's Craft: From Business Problem to Requirement3 lectures • 1hr 40min

Processes, Systems Thinking and Defending What You Wrote3 lectures • 1hr 20min

Describing How Work Happens: Why, Methodology and BPMN3 lectures • 1hr 57min

Tools, Results and Running Process Description as a Project3 lectures • 1hr 41min

AI Fundamentals: What It Can Do and How to Ask Properly3 lectures • 2hr 15min

AI for Work, Analysis and the Advanced Techniques3 lectures • 1hr 41min

Prompt Architecture and Advanced Reasoning: CoT, ToT, ReAct2 lectures • 1hr 11min

Context Engineering and Autonomous Agents: Projects, RAG, MCP2 lectures • 1hr

AI Operations Architecture: Projects, Skills and Connectors3 lectures • 1hr 49min

Building Skills: Document Generation and Structured Output3 lectures • 1hr 13min

Requirements

Description

Who this course is for: