Get Better Answers, a prompting course

Everything in this brief is true of the business. You may quote it, paraphrase it and build on it. You may not add facts, prices, numbers, people, testimonials or quotes it does not contain.

The business in one breath

Get Better Answers (getbetteranswersfromyourprompts.com) teaches people who already use Claude at work to get better answers out of it, and to prove the answers got better. Most prompting advice is admired, not tested. This course marks your work: you write one prompt for a real job, run it against six awkward cases, and watch the score move as you improve it.

The tutor: Nell Garvey

• Nell writes and runs the courses herself. She is the only person behind them.
• Her line on prompting: "A prompt is tested, not admired."
• Her line 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 (see "Where this is up to").
• She answers problems herself: the fastest way to reach her is the form on the privacy page.

The courses

Better Answers from Claude (the main course)

• For someone who already uses Claude for work every week and wants better results out of it.
• Eight modules and a short start-here: 23 lessons, five to eight minutes each, about 150 minutes in all. Every lesson ends in a run you can score.
• 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.
• 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. By the capstone you repeat the whole method on a job of your own.
• The modules: - 0 Start here: What Claude is, and is not; Your first prompt, and the score that follows you - 1 Context: Give it what it needs; Source material beats description; Too much context - 2 Task: What, for whom, and why; The decision the answer supports - 3 Requirements: Your definition of done; Facts, assumptions, and the word unproven; Rules you state and rules you enforce - 4 Examples: One example beats a paragraph of description; The near miss - 5 Evidence and testing: Re-reads and receipts; Telling a claim from a receipt; What you have been building; Versions, and writing down why; Diagnosing a weak answer - 6 Claude's own features: Projects, or context that stays; Skills, or the prompt as a file; Memory, search, and things that are documents; Emphasis, and reading the page for your model - 7 Capstone: Your own job, end to end - 8 Next door: What Claude Code adds

Two more courses, open alongside it

• Your Own Job, Scored (16 lessons, about 105 minutes): puts 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 minutes): stands on its own and teaches checking what a model wrote against its source before it goes out. You finish with a checking prompt you can run on your own work, tested on drafts with known faults: what it caught, what it missed, and what it wrongly flagged.

How it works (the method, in its own order)

• You pick a real job, one of thirteen, 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.
• You write a prompt for that job, in the page, on top of the version you last saved.
• 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.
• 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.
• 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.

What the marking actually checks: - Every claim in the answer appears in the brief you supplied. - A gap in the brief is reported as a gap, not filled in. The case that tests this is the one most bare prompts fail. - Nothing is left as a placeholder. Checked mechanically, so it cannot be argued with. - An answer that reads as a draft, or explains that it is an AI writing a draft, is a fail. The output is the work, not a note about the work.

The proof on the home page (real, dated)

The same customer enquiry, the same marking rubric, graded by the same run of the course's own exercise on 12 September 2026. The case is the one designed to tempt a model into inventing a price it was never given.

• Version 0, what most people write: "Reply to this customer email." Score: 2 of 8, fail.
• Version 1.1, what the course builds: "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." Score: 7 of 8, pass.

How the 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.
• 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.
• Two claims that other people write as fact are deliberately not made, because when it came to it, nobody had tested them.

Plain facts

• Price: free while the courses are in private beta. You make an account and start.
• Why an account: it 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.
• What running costs: 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.
• 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.
• Contact: the form on the privacy page reaches Nell directly.

Who reads this site, and what they are afraid of

• The weekly user. Uses Claude every week for work, gets answers that are fine but not good enough to send without rewriting. Afraid of: another course of tips that sound clever and change nothing, being made to feel stupid, wasting time on theory, a sales funnel.
• The sceptic. Has read plenty of prompting advice and trusts none of it. Wants evidence, not enthusiasm. Afraid of: being sold, hype, invented claims.
• Both are busy, practical and allergic to hype. Talk to them directly, as "you". Show the proof before asking for anything.

The voice

Plain, exact, a little dry, confident because it has the receipts. Short sentences. British English. Numbers only where they are real. Never says "unlock", "supercharge", "10x", "game-changer", "master", "secret", or "revolutionise". Would rather show a score than make a claim.

What the site must do

• Show, in the first screen or two, that this course is tested rather than admired: the 2 of 8 against 7 of 8 is the proof.
• Make the method feel concrete: one real job, six cases, a rubric, a score that moves.
• Let Nell's character come through: exact, honest about what is unfinished, impossible to flatter.
• Get the reader to make an account and start the main course. One action, one label for it everywhere.

The page to build

One landing page (index.html). It may mention the two other courses, the privacy page and the terms, but link only to anchors on this page; show the rest as plain text.

The one thing to get right

When someone finishes scrolling, they should believe their own prompts could be measured, and feel that starting is easy and safe.