jargon

Applied AI·Tokens

you count the tokens before sending rather than multiplying the word count by 1.3 and hoping.

Token counting

Draft summary, pending review

Computing how many tokens a string will consume before sending it, using the provider's tokeniser library or count endpoint. Required for cost estimates, context budgeting and truncation logic. Counting words and multiplying by 1.3 is a fallback, not a method.