token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
Why it matters
Projects attach a persistent 200K tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → corpus and custom instructions to a set of conversations, so groundingTying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.Full definition → documents and role framing no longer get re-pasted into every chat.
