AI does not only work with text. It can describe a photo, turn a recording into text, create a picture, or copy a voice. In this short course, you learn what these tools can do, where they make mistakes, and how to protect yourself from fakes.
You follow the organizer of a fictional community event, AI for Everyone. The organizer uses AI to read a whiteboard photo, make captions, design a banner, and deal with a suspicious voice message. Each lesson shows examples. Then you try it yourself. We wrote the examples for teaching. A real tool may behave in a different way.
Your 25-minute route
| Chapter | What you practice | Lesson time |
|---|---|---|
| 1. More than text | Sort tasks by type of media and by understand or create | 4 minutes |
| 2. AI that sees and listens | Get exact text from images and audio, and check it | 5 minutes |
| 3. AI that creates media | Write an image prompt and use the result responsibly | 5 minutes |
| 4. Spot the fakes | Check a suspicious image, audio, or video | 4 minutes |
Plan about 18 minutes for the lessons and exercises, 4 minutes for the chapter checks, and 3 minutes for the final test. These times are estimates. Take more time if you need it.
Each chapter has one lesson and two questions. The final test has four new questions, one for each chapter. To pass a chapter check or the final test, you must answer every question correctly. After you submit, you see an explanation for each question. For multiple-choice questions, select all correct answers.
How to practice
You do not need any setup or paid tools. You can do all exercises on paper. You do not need to know how to code. If you want, you can also try the prompts in an AI tool that you are allowed to use.
Generative AI Essentials and Practical Prompting are good courses to take first, but you do not need them. Remember: images, audio, and video can look very real. That does not make them true.
What you will learn
- Explain what multimodal AI is, and tell the difference between AI that understands media and AI that creates media
- Write clear prompts for reading images and audio, and check the results
- Write a clear prompt for an image, and use generated media responsibly
- Use a simple routine to check suspicious images, audio, and video
Before you start
- You know how to use everyday web applications
- You do not need programming experience, an AI account, or paid tools
Course modules
More than text
Learn what multimodal AI is, and the difference between AI that understands media and AI that creates media.
AI that sees and listens
Get exact text from images and audio, write useful image descriptions, and check the results before you use them.
AI that creates media
Write a clear prompt for an image, handle text in images, and use generated images and voices responsibly.
Spot the fakes
Recognize warning signs of fake images, audio, and video, and use a simple routine to check them before you act or share.