Day 1: AI Capabilities — What AI Can and Can't Do
Open the lab the instructor calls out from the slide. Auto-saves to this browser — refresh-safe.
Three labs today. Your instructor will tell you which one to open and when. Each one auto-saves to this browser — refresh-safe.
Sort 10 banking tasks. Predict the reliability.
Twelve banking tasks (two pre-sorted as instructor examples). For each of the other ten, pick a task shape — Draft, Summarize, Extract, Reason — and stick a 🟢🟡🔴 reliability prediction. We'll reveal the answer key after the break.
Same prompt. Two models.
Three pre-written prompts. Pick one with a single click, open Claude in one tab and another major model in another, run both, and fill in the side-by-side note: tone, hedging, format — and which you'd actually send.
Build your AI task-triage list.
Your sent mail from the last two weeks. Every recurring task, bucketed 🟢🟡🔴, with a one-line reason. Auto-saves, exports CSV — this list goes with you to Week 4.
Let the chef into your kitchen.
Connect Excalidraw to Claude and have it diagram a process you know cold — then validate it like this morning. A clean-looking box can still be invented. You can only catch the mistake in a process you actually understand.