AI Literacy Tutor
Built to teach critical thinking about AI — not to think for you.
Asks questions before answering. Forces you to engage with a concept before the AI weighs in.
Every response shows how certain the AI is. Because confidence and accuracy are not the same thing.
One click asks the AI to explain exactly how it arrived at any answer — including what it might be getting wrong.
Surface whose perspectives might be missing from any response. Teaches you to interrogate AI outputs, not just accept them.
Every five messages, a pause prompt asks you to consolidate your thinking before moving on.
Mercurius remembers past conversations — so each session builds on the last rather than starting from zero.
Mercurius Ⅰ is powered by Claude, a large language model made by Anthropic. The irony of using an AI to teach AI skepticism is intentional — and it is a design feature, not a bug.
Every interaction is an opportunity to observe how AI actually behaves: how it hedges, where it sounds more confident than it should be, and what it silently assumes. Mercurius is built to make those patterns visible rather than hide them.
It will not write your essays. It will not do your homework. It will not give you answers before you have done some thinking yourself.
"Here to help you think, not think for you."