Get Better Answers.
Most prompting advice is admired, not tested.
For people who already use Claude at work. Write one prompt for a real job. Watch the score move.
Chapter one · The proof
One job. One rubric. Marked twice.
Reply to this customer email.
2 of 8 · fail
You are answering a customer enquiry for the business described in the brief below. Use only the facts in the brief. If the brief does not answer something the customer asked, say plainly that you will check and come back, and never invent a fact, a price or a timescale to fill the gap. Write 90 to 150 words of plain British English, warm but not gushing. Answer every question the customer actually asked, in the order they asked it. Close by telling the customer what happens next.
7 of 8 · pass
The same customer enquiry, the same marking rubric, the same run of the course's own exercise, graded on 12 September 2026. The case is the one built to tempt a model into inventing a price it was never given. The marker saw the brief, the case and the answer. It never saw the prompt.
The method, in its own order
-
1
You pick a real job
One of 0, from a customer enquiry or a job advert to a consultant's proposal, a board update, a support reply or an incident report. You stay with it for the whole course.
-
2
You write the prompt
In the page, on top of the version you last saved.
-
3
It runs against six cases
Including a complaint, one the business genuinely cannot do, and one built to tempt the model into inventing a fact. Each answer is produced on its own, so one easy case cannot carry the rest.
-
4
It is marked
Mechanical checks first, then a grader that sees the brief, the case and the answer, but never your prompt. A rubric, not an opinion: four rules an answer must satisfy, and eight it should.
-
5
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.
Nell's workroom
One person. One red pen. No panel of experts.
The tutor, in her own words
-
On prompting
A prompt is tested, not admired.
-
On proof
Nothing here rests on being told a prompt is good.
-
On the marking
The grader sees the brief, the case and the answer, but never your prompt. It cannot be flattered.
-
On what counts as finished
The output is the work, not a note about the work.
She would rather tell you what is not finished than pretend it is. The fastest way to reach her is the form on the privacy page; she answers problems herself.
The course, and the two beside it
Better Answers from Claude
The spine is one prompt, improved twenty times. Lesson 0.2 has you write a bare prompt and run it; that score is the baseline every later lesson has to beat. You finish with one named, versioned prompt for a real job of your own, and a run log showing the new version beat the old.
- 0Start hereWhat Claude is, and is not. Your first prompt, and the score that follows you.
- 1ContextGive it what it needs. Source material beats description. Too much context.
- 2TaskWhat, for whom, and why. The decision the answer supports.
- 3RequirementsYour definition of done. Facts, assumptions, and the word unproven. Rules you state and rules you enforce.
- 4ExamplesOne example beats a paragraph of description. The near miss.
- 5Evidence and testingRe-reads and receipts. Telling a claim from a receipt. Versions, and writing down why. Diagnosing a weak answer.
- 6Claude's own featuresProjects, skills, memory, search, emphasis, and reading the page for your model.
- 7CapstoneYour own job, end to end.
- 8Next doorWhat Claude Code adds.
Your Own Job, Scored
16 lessons · about 105 minutesPuts your own work into the marker. You finish with your own job scored by the runner on two models, a rubric you have argued with three times, and a changelog with a model-moved line.
Checking Claude's Work
16 lessons · about 101 minutesStands on its own: checking what a model wrote against its source before it goes out. You finish with a checking prompt tested on drafts with known faults: what it caught, what it missed, and what it wrongly flagged.
How this course tries not to lie to you
-
Receipts
Every quotation carries the page it came from and the date it was read, under the quote, not in a footnote.
-
Re-checks
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
Lessons describe what a thing does and what to look for, because the buttons move monthly.
-
Two claims not made
Two claims that other people write as fact are deliberately not made here, because when it came to it, nobody had tested them.
Where this is up to
Open, and in private beta. All the lessons are there and the marking runs end to end. It has not yet had its adversarial audit, and the free run allowance is deliberately modest while the costs are still being watched.
Free while the courses are in private beta: you make an account and start. The account is how the course keeps your prompt versions, your runs and your scores; without one there is nothing to mark and nothing to compare against.
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.
Get Better Answers · getbetteranswersfromyourprompts.com
Free while the courses are in private beta. Make an account and Start the course
Also open alongside the main course: Your Own Job, Scored, and Checking Claude's Work. Questions reach Nell directly through the form on the privacy page. The terms are plain reading, like everything else here.
Nothing on this page rests on being told a prompt is good.