# Personal benchmark paragraph: revision

Your comment on "A personal benchmark is a set of tasks from your actual work, paired with the checks you use to judge a good result" was "this doesn't mean anything."

## Why it doesn't land

- It explains the **parts** ("tasks," "checks") and never says what the thing **does for you**. "Tasks" and "checks" are our internal words, so a new reader has nothing to picture.
- It doesn't say why a *personal* benchmark is needed when public benchmarks already exist, which is the point of the whole section.
- Your Rick pitch already has a clearer version: public benchmarks are SAT scores, and a personal benchmark is a reference check. I used that.

## Revised paragraph (drop-in replacement)

> **What is a personal benchmark?**
> A personal benchmark tells you which AI does your job best, judged by your standards instead of someone else's. Public benchmarks are like SAT scores. They help you tell a 1600 from a 900, but they don't help much when every top model scores around 1570. When you hire, what you want is a reference check from someone who has seen the candidate do work like yours. A personal benchmark is that reference check for AI models. Say you edit articles. One test might be asking a model for feedback on an opening you actually published, then grading its answer with questions you already ask yourself: Does the headline make the strongest claim? Is the wording concrete? Run that test on every model and you can see which one meets your bar. Each time you correct an AI, that correction can become another test, so the benchmark gets sharper the more you work.

About 150 words, up from about 90. The editing example is barely changed. The new part is the first four sentences.

## Shorter option (if the full doc needs to stay under 500 words)

Replace only the flagged sentence with:

> A personal benchmark tells you which AI does your job best, judged by your standards. Public benchmarks are an SAT score; this is a reference check.

Then keep the rest of the paragraph as written.

## Notes and assumptions

- "Around 1570" and the SAT/reference-check analogy come from your pitch to Rick. That transcript came through Granola Chat and wasn't checked against audio, so treat the numbers as illustration, not a quote.
- "Can become another test" keeps the automatic, one-click capture framed as something you're aiming for. Your list above describes it as ambition, and Every Checks runs internally today.
- I avoided the "replace you / work for you" contrast here because your closing section already uses it. That way the definition sets up the ending without repeating it.