AI Fundamentals

Objectives

• Understand how LLMs work: tokens, parameters, attention mechanisms
• Distinguish predictive models (ML) from generative models (LLMs), understand their strengths and limits (hallucinations, bias)
• Explore the multimodal capabilities and advanced features of AI platforms (ChatGPT, Claude, Gemini, Copilot)

What's covered

• How LLMs work: tokens, parameters, attention mechanisms
• Predictive models (ML) vs generative models (LLMs), hallucinations and bias
• Multimodal capabilities and advanced features of AI platforms (ChatGPT, Claude, Gemini, Copilot)

Objectives

• Structure a prompt: tags, context, task, output format, role and guardrails
• Master multishot prompting and Chain-of-Thought
• Track your progress with instant feedback on a dedicated platform

What's covered

• Structuring a prompt: tags, context, task, output format, role and guardrails
• Multishot prompting and Chain-of-Thought
• 7 progressive exercises with instant feedback on a dedicated platform

Objectives

• Apply the Use Case Mapping methodology to identify the right use case
• Build a custom AI assistant (Custom GPT) step by step
• Present and pit your assistant against others in the final battle

What's covered

• Use Case Mapping methodology to identify the right use case
• Step-by-step build of a custom AI assistant (Custom GPT)
• Final battle: presenting and pitting assistants against each other

Objectives

• Understand the energy and water footprint of AI models and adopt frugal usage
• Diagnose your team's maturity with AI (Dunning-Kruger effect, diffusion of innovations)
• Shift from a Tool-first to a Value-first approach and become a catalyst for adoption

What's covered

• Energy and water footprint of AI models, frugal usage
• Maturity diagnosis: Dunning-Kruger effect, diffusion of innovations
• Value-first vs Tool-first approach and the role of adoption catalyst