Lesson 1: Prompt Words: Context, Persona, Constraint, Few-Shot and More No sign-up needed.
Every course, exam and certificate is free. Premium only removes ads and adds extras.
Last updated
The AI words that confuse beginners, explained in plain English with everyday examples: prompt words like context and few-shot, how-AI-works words like LLM, token and knowledge cutoff, tool words like API key, JSON and CSV, image, video and voice words, and assistant words like agent and RAG. No code. Free certificate.
AI courses and AI news are full of words nobody stops to explain: context, persona, few-shot, token, knowledge cutoff, API key, JSON, image-to-video, agent, RAG. If you have ever felt lost in a lesson because of one word, this short course is for you. It explains the AI terms beginners meet most often, in plain English, with an everyday example for each and a note on where you will see it. The word list comes from real questions learners asked our lesson tutor. You will start with the words people use about prompts, like context, constraint, zero-shot, few-shot, task decomposition, iteration and hallucination. Next come the words about how AI works: LLM, GPT, model versus product, token, context window, knowledge cutoff, training, inference, benchmarks and open models. Then the tool and file words, like API, API key, JSON, CSV, Markdown and OCR, followed by image, video and voice words such as aspect ratio, diffusion, text-to-speech, voice cloning and deepfake. The last lesson covers agents, RAG, embeddings, fine-tuning and MCP, and gives you a simple method and a prompt to decode any new AI word yourself, in English or your own language. Five short lessons, quizzes, a final exam and a free certificate.
3 modules • 5 lessons
Finish every lesson and pass the final exam to earn this free, shareable certificate.
Certificate of Completion
has successfully completed
5 lessons · Final exam passed
Michail Ouroumis
Founder, FreeAcademy.ai
Sample preview. Your name appears on the certificate when you complete the course. Learn more
Teaching a class or training a team? Assign this course for free
Complete beginners, students and anyone who finds AI lessons too technical. You do not need any background in computers or coding.
A token is a small chunk of text, often a short word or part of a word, that an AI model reads and writes. AI apps count usage and limits in tokens. In English, 100 tokens is roughly 75 words.
An API key is a long secret code that lets an app use another service's API, a bit like a password for apps. Never share it, and replace it if it leaks.
ChatGPT is a product, the app you use. GPT is the family of models, the AI inside it. One product can offer several models.
About 40 minutes across five short lessons. Each lesson has a quiz, and there is a final exam with a free certificate when you pass.
A short, no-code, no-math explainer of the attention mechanism that powers ChatGPT, Claude, and Gemini. Understand query, key, and value, why models use many attention heads, how word order is encoded, and why transformers read your whole prompt at once.
Find out why ChatGPT, Claude, and Gemini feel helpful, polite, and safe instead of just completing text. A short, no-code course on reinforcement learning, supervised fine-tuning, reward models, PPO and DPO, and the side effects of alignment like sycophancy and reward hacking. The natural next step after How LLMs Actually Work.
Learn how much electricity and water AI really uses. See what one prompt costs compared with everyday things, where a data center's energy and water go, how training compares with daily use, why communities debate new data centers, how to use AI with less waste, and what comes next. No code. Free certificate.
Master Google Gemini from scratch, then go deeper. Learn what Gemini is, set up your account, write effective prompts, and use it across Google Workspace. Then run Deep Research reports you can actually trust, build and tune custom Gems, and analyze whole document sets and long video in one pass.
Understand the machine underneath modern AI without writing a line of code. Learn what a neuron does, why weights are the only place a model stores knowledge, how layers build their own concepts, and how training actually works through loss, gradient descent, and backpropagation.
Learn the principles, practices, and skills to use AI responsibly. Explore bias, fairness, privacy, transparency, hallucinations, deepfakes, AI agent permissions, human approval, and the EU AI Act through hands-on exercises with ChatGPT, Claude, and Gemini. Perfect for university students and early-career learners. No coding required, and you earn a free certificate to add to your LinkedIn and resume.
