Summary  
This chapter covers techniques for sanitizing and managing user inputs to AI tools—such as anonymization and avoiding direct inclusion of sensitive information—to ensure data privacy and compliance when interacting with third-party AI services.

General domain of usage  
Data privacy management in AI-driven workflows

Prompt engineering makes AI more useful. But knowing what not to put 
into a prompt is just as important as knowing how to write a good one.

When you type something into an AI tool, you are sending that text to 
an external server operated by a third-party company. Understanding 
what that means — and what risks it creates — is essential for anyone 
using AI at work.


## How AI Tools Handle Your Input

Most consumer-facing AI tools — including free tiers of ChatGPT, 
Claude, and Gemini — may use your conversations to improve their models, 
unless you explicitly opt out.

This means that text you enter could, in principle, be reviewed by 
humans at the company, used in training data, or stored for extended 
periods.

Enterprise versions of these tools (such as Microsoft Copilot for 
Microsoft 365, or Claude for Enterprise) typically offer stronger 
data privacy guarantees — including commitments not to use your data 
for training. But these require a paid organizational subscription and 
specific configuration.

If you are unsure which version your organization uses — ask your 
IT or security team before putting sensitive information into any AI tool.

## What You Should Never Enter into a Consumer AI Tool

As a general rule, treat AI chat interfaces the same way you would 
treat a public forum — assume the content could be seen by others.

Never enter:

- Personal data of clients, customers, or employees — names, emails, 
  phone numbers, ID numbers, addresses;
- Financial data — account numbers, transaction details, salary 
  information, budget figures that are not public;
- Health or medical information about any individual;
- Passwords, API keys, or authentication credentials of any kind;
- Confidential business information — unreleased product details, 
  M&A discussions, strategic plans, proprietary research;
- Legal documents containing privileged or confidential content.

## Safe Alternatives: How to Get the Help Without the Risk

Needing to protect sensitive data doesn't mean you can't use AI for 
those tasks. Here are practical workarounds:

- Anonymize before prompting — replace real names with placeholders 
  ("Client A," "Employee X") before pasting content into the AI;
- Describe the situation without the data — instead of pasting a 
  confidential document, describe the type of problem and ask for 
  a framework or approach;
- Use enterprise-grade tools — if your organization has licensed 
  Microsoft 365 Copilot or similar, those tools typically operate 
  under stricter data protection terms;
- Keep sensitive content local — use AI to draft structure and language, 
  then fill in the sensitive specifics yourself offline.

## Know Your Organization's Policy

Many organizations are developing or have already published internal 
AI usage policies. These typically specify:

- Which AI tools are approved for use at work;
- What categories of data can and cannot be entered;
- Whether a company-specific AI environment is available;
- How to report concerns or incidents related to AI use.

If your organization has such a policy — follow it. If it doesn't — 
apply the conservative defaults above until guidance is provided.

Which of the following types of information should you avoid entering into a consumer-facing AI tool like ChatGPT at work?

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.

Data Privacy. What You Should Never Share with AI

How AI Tools Handle Your Input

What You Should Never Enter into a Consumer AI Tool

Safe Alternatives: How to Get the Help Without the Risk

Know Your Organization's Policy