Artificial Intelligence — Mandragore Academy

Artificial Intelligence

← Mandragore Academy

Master the AI that transforms business.

Artificial intelligence is reshaping how every industry works. Mandragore Academy's Learning Workspaces help you understand, practice, and master the leading AI tools through guided learning paths enhanced by intelligent conversational support, designed to turn knowledge into real, job-ready skills.

Get ready for the jobs of today — and tomorrow.

Choose your course and build skills you can apply to your work right away.

Independent training — not affiliated with or certified by the vendors of the solutions featured.

Discover our Artificial Intelligence courses

Your personal Learning Workspace is created automatically upon your first purchase.

Choose your tool

ChatGPT

Master ChatGPT

165 courses available View courses

Claude AI

Master Claude AI

46 courses available View courses

Machine Learning

Master Machine Learning

15 courses available View courses

AI Agents & Agentic Systems

Master AI Agents

15 courses available View courses

Catalog preview

Discover ChatGPT

Generative AI, GPT models, interface, limitations, best practices.

What is ChatGPT? Generative AI and the GPT models The different models and when to use them Getting to know the ChatGPT interface +4

Writing Effective Prompts

Objective, context, role, constraints, format, iteration.

Setting a clear objective Giving the right context Assigning ChatGPT a role Adding constraints and criteria +4

Prompt Engineering

Zero-shot, complex tasks, multi-step prompts, prompt library.

Zero-shot, one-shot and few-shot prompting Breaking down a complex task Designing multi-step prompts Generating several possible solutions +4

Discover Claude

Anthropic, Constitutional AI, Haiku/Sonnet/Opus, differences vs ChatGPT.

What is Claude? Haiku, Sonnet, Opus models Claude vs ChatGPT Constitutional AI +4

Writing effective Claude prompts

Role, objective, context, format, examples, XML tags — Claude's specifics.

Role and persona Clear objective Context and background Constraints and format +3

Claude Prompt Engineering

Zero/Few Shot, Chain of Thought, Extended Thinking, Constitutional prompting.

Zero Shot / One Shot / Few Shot Chain of Thought Tree of Thought Extended Thinking — visible reasoning +3

Understand Machine Learning and scope a problem

turn a business need into a measurable Machine Learning problem and decide whether ML is really the right approach

Understand what Machine Learning really brings Distinguish supervised and unsupervised learning Identify classification, regression and other problem families Define features, target, observations and predictions +4

Prepare and explore data for Machine Learning

build a usable dataset without introducing bias, data leakage or inconsistencies

Explore distributions, types and data quality Handle missing values and outliers Prepare numerical and categorical variables Encode categories without introducing future information +4

Build a first reproducible ML pipeline

chain preprocessing, training, prediction and evaluation into a reproducible workflow

Set up a reproducible ML environment Build a baseline with scikit-learn Create preprocessing transformations Assemble preprocessing and model with Pipeline +4

Understand AI agents and scope a use case

distinguish assistant, workflow and agent, then decide whether agentic autonomy actually adds value

Understand what sets apart assistant, workflow and agent Identify goal, environment, tools and state Understand the perceive, decide, act, observe loop Define an acceptable level of autonomy +4

Design an agent's instructions and behavior

define agentic behavior that is predictable, testable and bounded by explicit rules

Define the agent's role, goal and responsibility Structure constraints and standing rules Separate instructions, context and user data Define structured outputs and expected schemas +4

Give an agent tools and structured actions

let an agent act on external systems with typed, validated and controlled tools

Understand the tool-calling cycle Turn a function into a typed tool Define reliable parameters, descriptions and schemas Connect an external API as a tool +4

See the full catalogue