A role that describes nothing
"You are a helpful AI assistant" tells the model nothing it did not already assume.
Every hosted chat model already behaves as a helpful assistant. Telling it so consumes tokens to move the output distribution approximately nowhere.
The cost is not just the tokens. A vague opening line displaces the specific one that would actually change behaviour. "You are a claims adjuster reviewing auto damage estimates" earns its tokens; "you are a helpful AI assistant" does not.
Delete it outright, or replace it with the concrete role, audience, and success criterion for your task. If you cannot write that sentence, the prompt has a bigger problem than its token count.
You are a helpful AI assistant. Summarise the support ticket below.Summarise the support ticket below for an on-call engineer.Check your own prompt
The analyser checks this pattern along with the other 25, prices each finding against your request volume, and hands back a rewritten prompt. It runs in your browser — nothing is uploaded.
Run the analyserMore on filler
- Prompt folkloreTips, deep breaths, and other emotional-appeal phrasing, copied from 2023-era prompting advice and never removed.
- Chat pleasantries in a system promptSign-offs written for a human conversation, left in a machine instruction.
- Politeness aimed at a billing meterPlease, thank you, and "I would like you to" cost tokens on every request forever.
- Long ways of saying short things"Due to the fact that" is four tokens. "Because" is one.