How it works
The course marks your work, and shows you the marking.
Nothing here rests on being told a prompt is good. Every lesson produces a version, every version is run against the same six cases, and every run is scored the same way.
One run, end to end
1. You write
A prompt for the job you picked, in the page, on top of the version you last saved.
2. It runs
Your prompt meets all six cases. Each answer is produced on its own, so one easy case cannot carry the rest.
3. It is marked
Mechanical checks first, then a grader that sees the brief, the case and the answer, but never your prompt. It cannot be flattered.
4. It is logged
Version, case, pass or fail, and the score out of eight. Your log is the evidence the course worked, or did not.
How this course tries not to lie to you
- Every quotation carries the page it came from and the date it was read.
Under the quote, not in a footnote. When you check it, you find it or you find it changed. Either is honest.
- A script re-fetches every quoted page on a schedule and fails when the sentence is gone.
A stale course should be a job on someone’s list, not a surprise for a reader.
- No screenshots of the interface.
Lessons describe what a thing does and what to look for, because the buttons move monthly.
- Claims about the product that nobody has checked.
Two claims that other people write as fact are deliberately not made here, because when it came to it, nobody had tested them.
What it costs to run
Marking is not free: one exercise is twelve model calls, six to answer and six to grade. Every account gets a capped number of runs, enough to finish every exercise with room to retry and redo. The cap is a number on a settings page, not a promise, and the runner refuses politely and says why when an account or the course as a whole reaches its ceiling.