EFFECTIVE/AT LIFE Start Module
← AI for Friends
01 REQUIRED

AI Foundations

The AI fluency to use Claude confidently and accurately in daily work — how AI models process information, how to write prompts that work on the first try, and which model to reach for.

55–70 min 4 lessons HR · Industrial Engineering · Legal · Marketing

By the end, you will

  • Understand how AI models work at a conceptual level, with no code involved
  • Write prompts that produce accurate, useful outputs on the first try
  • Pick the right AI model for each task based on speed, cost, and capability
  • Apply a validation habit to every AI output before acting on it

Lessons in this module

Key Concepts

Core terms introduced in this module. The lesson where each term is first defined is listed so you can return to the source explanation.

TermDefined InPlain English Meaning
PromptLesson 1.1The instruction or question you type to the AI.
Context WindowLesson 1.1The AI's working memory. How much text it can hold and process at once.
TokenLesson 1.1A chunk of text roughly equal to three-quarters of a word. Models measure capacity in tokens.
AgentLesson 1.1A pre-configured AI assistant with specific instructions and, sometimes, live connections to other apps.
MCP ServerLesson 1.1A live connection between your AI assistant and another app or system, such as your email or a project tracker.
Knowledge BaseLesson 1.1A collection of documents you provide to the AI. It searches them to answer your questions.
HallucinationLesson 1.2When the AI generates false information presented as fact — happens when it lacks real data and predicts instead.
Full Key Concepts reference
LLMLesson 1.1Large Language Model. The technical name for AI models that generate text.
Agentic LoopLesson 1.1The cycle where an agent reasons, selects tools, executes actions, and repeats until the task is complete.
Prompt EngineeringLesson 1.2Structuring HOW you ask — the wording, specificity, and format of your instruction.
Context EngineeringLesson 1.2Controlling WHAT information you give the AI to work with before it generates a response.
Zero-Shot PromptingLessons 1.2, 1.3Asking once with clear instructions and no examples provided. Works for well-defined tasks.
Few-Shot PromptingLessons 1.2, 1.3Providing examples of the desired output before asking the AI to produce new output. Improves consistency.
Role PromptingLessons 1.2, 1.3Assigning the AI an identity (e.g. "You are an HR specialist") to shape its tone, vocabulary, and priorities.
Chain-of-ThoughtLessons 1.2, 1.3Asking the AI to reason step by step before giving a final answer. Reduces errors on complex tasks.
Interview-Style PromptingLesson 1.3Asking the AI to interview you to gather context before producing output. Useful for complex or unclear tasks.
Meta PromptingLesson 1.3Asking the AI to write a prompt for you. Useful when you know the goal but not how to phrase the instruction.
COSTARSLesson 1.3A framework for building complex prompts: Context, Objective, Style, Tone, Audience, Response, Scope.
Claude (Haiku/Sonnet/Opus)Lesson 1.4Anthropic's model family, and your default for almost everything. Haiku is fast and cheap. Sonnet is the balanced default. Opus handles the most complex reasoning.
GeminiLesson 1.4Google's model family. The one niche exception worth knowing: Gemini handles video and audio natively, which no Claude model does.

Support Resources

ResourceLinkPurpose
Claudeclaude.aiSign up and use Claude in your browser
Claude Docscode.claude.com/docsOfficial documentation
Claude Supportsupport.claude.comHelp center and account support

Up next

Module 2: Setting Up Your Computer (optional)

View Module 2