Type hub
Explainer
- Intermediate Claude Explainer
Claude Sonnet and Opus, explained
If your Claude app or your work Copilot lets you pick between them, here is what actually changes when you switch.
- Intermediate Copilot Explainer
Copilot agents at work, explained
What Copilot Studio and the agent builders actually do, and the questions to ask before your organisation switches them on.
- Intermediate Any tool Explainer
MCP servers, explained
The standard plug that lets any AI assistant reach your files, tools and data, and what you're trusting when you use one.
- Advanced Any tool Explainer
Prompt injection: the new attack surface
Why letting an AI read untrusted content is risky, and how to limit the damage.
- Intermediate Copilot Explainer
Where does Copilot send your data?
Your prompts and files stay inside your organisation's own area of Microsoft's cloud. Web searches and connected add-ons do not.
- Beginner Copilot Explainer
Which Copilot is which?
Microsoft uses one name for several different products, and has just made it worse. A short map, so you know what you're actually using.
- Intermediate Any tool Explainer
Tokens and context windows, explained
Why an assistant 'forgets', and how much it can really hold at once.
- Intermediate Any tool Explainer
Prompt engineering, separated from the folklore
Why wording changes results, which techniques hold up, and how much of this you actually need.
- Intermediate ChatGPT Explainer
ChatGPT's data controls, explained
What OpenAI does with your chats by default, and the settings that change it.
- Intermediate Gemini Explainer
Gemini's data controls, explained
What Google does with what you type, and why the answer is completely different at work and at home.
- Intermediate Any tool Explainer
What AI actually costs the planet
A grounded look at AI's energy and water footprint, neither dismissive nor doom-laden.
- Intermediate Any tool Explainer
Who owns what AI makes?
The honest, unsettled state of AI and copyright, and how to stay on safe ground.
- Intermediate Any tool Explainer
Shadow AI: the unsanctioned-tool problem
Why staff paste sensitive data into random chatbots, and what to do about it.
- Beginner Any tool Explainer
AI and your job: an honest look
Past the hype and the doom: what actually changes, and how to stay ahead of it.
- Beginner Any tool Explainer
What is a large language model?
A plain-language explanation of how tools like Claude and ChatGPT actually work.
- Intermediate Any tool Explainer
What people mean by 'AI agents'
The jump from a chatbot that answers to a system that takes actions, and why that jump deserves more care.
- Advanced Any tool Explainer
Embeddings and RAG, without the jargon
How an assistant answers from your own documents instead of guessing from memory.
- Intermediate Any tool Explainer
Where AI bias comes from
Why models inherit human bias, where it shows up, and what you can actually do.
- Beginner Any tool Explainer
How an AI model is trained
Where the 'knowledge' comes from, stage by stage, and why the cut-off date matters.
Nothing matches these filters. Clear one to widen the search.