When to make Claude think (and when not)
Thinking is the model talking to itself before answering. You pay for those tokens.
Worth it
Math, debugging, architecture, multi-step plans, anything where the first idea is usually wrong.
Not worth it
Lookups, rewording, formatting, yes/no questions.
In Claude Code
Ask for it in the prompt ("think hard about...") only for the hard step; keep the rest of the session plain.
A new disaster and its fix every day. Comment the word under a reel to get its guide.