Reasoning Models vs CoT Prompts
From Prompt Engineering Mastery · Reasoning Techniques. Extended-thinking models do CoT natively — what that retires, what it doesn't, and how to split work between fast and thinking modes.
One lesson, one term, one build prompt, one app check — a small fresh slice of the school, same for everyone, new every day. Show up daily and keep your streak alive.
From Prompt Engineering Mastery · Reasoning Techniques. Extended-thinking models do CoT natively — what that retires, what it doesn't, and how to split work between fast and thinking modes.
“AI that can use tools”
A structured way for LLMs to request execution of external functions. You define tools with JSON Schema descriptions, the model outputs a structured JSON object specifying which function to call with what arguments, your code executes it, and the result goes back to the model. Not the same as agents -- function calling is the mechanism, agents are the loop.
🟡 Kinda — with gaps. A calm daily planning ritual that pulls work from all your tools. — can you vibe code it in a weekend?
You get a lazy prompt and a goal. Rewrite it. We score your version against the habits of good agentic prompting — outcomes, constraints, tests, verification. 4 prompts. Clear it for XP — flawless runs earn a badge.
Claude Code, Codex, Cursor, Antigravity, Aider — there's a vibe coding platform for every taste. Here's how to pick one without trying all of them.