Academy
AI Essentials: Understand Generative AI in 20 Minutes
A plain-language introduction to how generative AI really works, where it shines, where it fails, and how to use it responsibly on OUPI. No technical background needed — just the shared vocabulary every team member should have before using any AI feature.
Course outline
1
What a Model Actually Does
Understand that a large language model is a text predictor, not a knowledge database, so its strengths and failures make sense.
2
Tokens and the Context Window
Learn what tokens are and how the context window acts as the model's working memory for each request, affecting cost, speed and limits.
3
Hallucinations: Why AI Invents Things
Recognise that confident-sounding false statements are an inherent property of text prediction, not a fixable bug.
4
Grounding: Documents, Search and Tools
Discover how grounding techniques — knowledge bases, web search and tools — reduce hallucinations by giving the model verified material to work from.
5
Model vs Product, Temperature and Multimodal
Distinguish the model (engine) from the product built around it, and understand key settings like temperature and multimodal capabilities.
6
From Chat to Agents
Understand the difference between a one-shot chat answer and an agent that plans, uses tools and iterates toward a goal.
7
Your Data, Memory and Privacy
Know that models do not learn from your conversations, that data is sent only for the current request, and that sovereign model options exist.
8
The Golden Rule: AI Proposes, You Validate
Apply a practical framework for deciding what to delegate to AI and what to verify, based on the stakes of the output.
Take this course in OUPI
Progress, quiz and certificate in your account — 8 questions to check what you learned and earn a certificate, in your OUPI workspace.