Summary  
This chapter explains the contrast between deterministic programming functions that always produce the same output for a given input and the probabilistic nature of generative AI, and introduces the concept of the context window as the AI’s working memory.  

General domain of usage  
Conversational AI agents

When you type `=SUM(A1:A10)` in Excel, you always get the same answer. 
When you ask ChatGPT the same question twice, you might get two different 
responses. This isn't a flaw — it's the defining characteristic of 
generative AI, and understanding it changes how you work with it.


## Deterministic vs. Probabilistic Tools

**Traditional software** follows fixed rules:
- Same input → same output, every time;
- The result is predictable and auditable;
- Examples: excel formulas, database queries, search engines.

**Generative AI** is probabilistic:
- Same input → varied output, depending on context and randomness;
- Results are flexible and creative, but require verification;
- Examples: ChatGPT, Claude, Gemini, Copilot.

Neither approach is superior — they serve different purposes. The mistake 
is treating AI like a calculator, or expecting a calculator to be creative.

## The Context Window: AI's Working Memory

AI doesn't have a persistent memory. It only knows what's in the current 
conversation — this is called the **context window**.

- Everything you've written in the current chat is in the context window;
- The moment you start a new conversation, the AI has no memory of the previous one;
- Some tools offer optional memory features, but they're not on by default.

Imagine a brilliant consultant who reads everything you give 
them in a single meeting, then forgets the entire conversation when they 
walk out the door. The next meeting, you start from scratch.

Analogy

## What This Means in Practice

- **Always provide context in your message** — don't assume the AI knows 
  your role, your project, or your preferences;
- **Within a conversation, you can refer back** — the AI remembers 
  everything said in the current session;
- **Start fresh when topics change** — a cluttered, long conversation can 
  confuse the model;
- **Some tools offer memory** — ChatGPT and Claude have optional memory 
  features that persist across sessions, but these need to be enabled.


Which statements correctly describe the difference between deterministic and probabilistic tools, and provide accurate examples of each

Which statement best describes how generative AI remembers information during a conversation?

AI is no longer optional — it's part of how work gets done in 2026. This course gives you a practical foundation for working with AI tools confidently and responsibly. No coding required. You'll learn how modern AI actually works, how to get useful results from it, what to watch out for, and how to apply it in your specific role — whether you're in marketing, HR, analytics, or development.

Before using any AI tool effectively, you need to understand what it is — and what it isn't. This section demystifies large language models, cuts through the hype, and maps out the current landscape of AI tools so you can make informed choices from day one.

The quality of your output depends almost entirely on how you phrase your input. This section teaches you how to write clear, structured prompts — and how to refine them when the result isn't quite right. The most hands-on section of the course.

Knowing how to use AI also means knowing when not to trust it. This section covers the real risks — hallucinations, data privacy, bias — and builds the critical thinking habits that separate a thoughtful AI user from a reckless one.

The final section brings everything together through the lens of specific job functions. Each chapter shows exactly how AI is being used in a given field — with real examples, tool demos, and a closing chapter to help you build your own AI workflow.

Generative AI vs. Traditional Software

Deterministic vs. Probabilistic Tools

The Context Window: AI's Working Memory

What This Means in Practice

1. Which statements correctly describe the difference between deterministic and probabilistic tools, and provide accurate examples of each

2. Which statement best describes how generative AI remembers information during a conversation?