AI prompts for students

Turn these notes into revision questions.

MY NOTES:
"""
[PASTE]
"""

SUBJECT AND LEVEL: [WHAT AND WHAT STAGE]
WHAT I AM BEING ASSESSED ON: [exam / essay / practical / just want to remember it]
HOW LONG UNTIL I NEED IT: [TIMEFRAME]

Produce:

1. THE QUESTION SET - organised by the type of thinking each requires:
   - RECALL: facts, definitions, dates, formulas. Short answer.
   - EXPLANATION: why something happens, how a process works. These matter more than recall for most assessments.
   - APPLICATION: given a new situation, what applies. This is where understanding is actually tested.
   - COMPARISON: how two things differ and why it matters
   - CRITIQUE: what is weak, contested or limited about this

   Weight the mix toward my stated assessment type.

2. THE ANSWERS - separately, so I can test myself first. Each answer should be what a good response contains, not a full essay.

3. THE QUESTIONS THAT REVEAL GAPS - the three that are hardest to answer from my notes alone. These show where my notes are thin, which is more useful than knowing what they cover well.

4. WHAT MY NOTES DO NOT COVER - based on the topic, what a complete treatment would include that is missing here. Mark as [CHECK YOUR SOURCE] rather than filling it in, because notes gaps usually reflect something missed in class or in reading.

5. THE FLASHCARD SET - for the pure recall items only, formatted as front and back. Do not make flashcards for explanations; they do not work for anything requiring reasoning.

6. THE SPACING SCHEDULE - given my timeframe, when to review. Testing yourself repeatedly over spaced intervals beats rereading, by a wide margin and consistently. Give the specific days.

7. THE HONEST NOTE ON METHOD - rereading and highlighting feel productive and are among the least effective study methods. Retrieval practice, where you try to produce the answer before checking, is what builds durable memory. This question set only works if I attempt each answer before looking.

Do not produce questions whose answers are obvious from the question wording.

Help me plan my revision.

WHAT I AM STUDYING: [SUBJECTS AND TOPICS]
WHEN THE ASSESSMENTS ARE: [DATES]
HOW CONFIDENT I AM IN EACH: [RATE EACH TOPIC]
HOW MUCH TIME I HAVE: [HOURS PER WEEK, AND WHEN]
OTHER COMMITMENTS: [WHAT ELSE FILLS YOUR TIME]
HOW I HAVE REVISED BEFORE: [WHAT YOU USUALLY DO]

Produce:

1. THE PRIORITY MAP - topics ranked by (weight in the assessment × how weak you are). Time should go to high-weight topics you are weak on, not to topics you enjoy. People reliably over-revise what they already know because it feels better.

2. THE REALISTIC HOURS - given my commitments, what is actually available. Then reduce it, because revision plans always assume more capacity than exists. State the honest figure.

3. THE SCHEDULE - specific sessions with dates, each naming the topic and the activity. Not 'revise biology' but 'attempt past paper questions on enzyme kinetics, then check'.

4. THE SESSION STRUCTURE - what to do in a study session. Retrieval first (attempt questions from memory), then check, then fill the gaps, then re-test the ones you got wrong. Starting with rereading wastes the session's best attention.

5. THE SPACING - each topic revisited at increasing intervals rather than studied once intensively. Build this into the schedule explicitly: first pass, then three days later, then a week, then before the assessment.

6. THE INTERLEAVING - mix topics within a session rather than blocking one topic for three hours. It feels harder and produces better retention, which is why almost nobody does it.

7. THE BUFFER - leave time unscheduled. Plans with no slack break in week one and are then abandoned entirely.

8. WHAT TO DROP - if the plan does not fit the time, what gets less attention, decided deliberately rather than by running out of time.

9. THE WEEKLY CHECK - a short review each week: what was covered, what was not, and what to adjust. A plan made once and never revised is abandoned by week three.

10. THE METHOD WARNING - based on what I said I usually do, whether those methods are effective. Rereading, highlighting and copying notes out feel productive and produce little. Say so if that is what I described, and what to do instead.

Test my understanding of this topic.

THE TOPIC: [WHAT IT IS]
MY LEVEL: [WHAT STAGE YOU ARE AT]
WHAT I THINK I UNDERSTAND: [EXPLAIN IT IN YOUR OWN WORDS - this is the important input]
WHERE I FEEL SHAKY: [IF YOU KNOW]

Produce:

1. MY EXPLANATION, ASSESSED - I explained the topic in my own words. Go through it and identify:
   - What is correct
   - What is correct but incomplete
   - What is wrong
   - What is vague in a way that suggests I am repeating a phrase rather than understanding it. This last category is the important one; memorised phrasing is easily mistaken for understanding.

2. THE PROBING QUESTIONS - six questions designed to find the edges of my understanding. Not recall questions. Each should be answerable only if I genuinely understand:
   - Why is it this way rather than the obvious alternative?
   - What would happen if one condition changed?
   - Where does this not apply?
   - How does this connect to [related concept]?
   - What is a case that looks like this but is not?
   - Explain it to someone with no background

3. THE COMMON MISCONCEPTIONS about this topic, and whether my explanation shows any of them. Misconceptions are usually stable and confident, which is what makes them hard to notice.

4. THE PREREQUISITE CHECK - if my explanation is shaky, the underlying concept I may not have secured. Confusion at one level is frequently caused by a gap one level below, and drilling the current topic will not fix it.

5. THE EXPLANATION GAP - the parts I described in terms that suggest I could not answer a follow-up question. Quote them.

6. THE ONE THING TO FIX - the single misunderstanding whose correction would most improve my grasp.

7. HOW TO CHECK IN FUTURE - the self-test that works: explain it out loud from memory without notes, to an imagined person who asks 'why?' after each sentence. Recognition feels like knowledge and is not.

Be direct about what is wrong. Politeness here costs marks later.

Help me understand this material.

THE MATERIAL:
"""
[PASTE THE TEXT, OR DESCRIBE IT]
"""

SUBJECT AND LEVEL: [WHAT AND WHAT STAGE]
WHAT I HAVE UNDERSTOOD SO FAR: [YOUR CURRENT GRASP]
WHERE I GET LOST: [THE SPECIFIC POINT]
WHAT I ALREADY KNOW ABOUT THIS AREA: [YOUR BACKGROUND]

Produce:

1. THE ONE-SENTENCE VERSION - what this material is actually about, stripped of terminology.

2. THE STRUCTURE - what the material is doing, section by section. Often the confusion is structural: not knowing whether a passage is setting up a problem, presenting a solution, or raising an objection.

3. THE PREREQUISITE CHECK - the concepts this material assumes you know. Given what I said about my background, which of these I may be missing. Getting lost at a specific point is usually caused by a missing prerequisite rather than by the passage itself being hard.

4. THE POINT WHERE I GET LOST, EXPLAINED - starting from what I said I already understand, and building only from there. Use plain language first, then reintroduce the technical terms once the idea is in place.

5. THE TERMINOLOGY - each technical term in this material, defined plainly, with a note on whether it means something different in ordinary usage. A great deal of difficulty in academic reading is vocabulary rather than concept.

6. THE WORKED EXAMPLE - the idea applied to a concrete case, step by step. Abstract explanations of abstract ideas rarely land; a specific instance does.

7. THE ANALOGY, WITH ITS LIMITS - one analogy that helps, and explicitly where it breaks down. An analogy without stated limits creates a misconception that is harder to fix than the original confusion.

8. WHY IT IS WRITTEN THIS WAY - academic and technical writing is dense for reasons: precision, convention, and an assumed reader. Knowing that the difficulty is partly the prose, not entirely you, is useful.

9. THE CHECK - three questions to answer to confirm it has landed.

10. WHAT TO READ IF THIS IS STILL NOT WORKING - what kind of source would explain it better for my level.

Help me practise exam technique.

THE EXAM: [SUBJECT AND FORMAT]
MY PROBLEM: [running out of time / losing marks on questions I know / freezing / careless errors / not knowing where to start]
A RECENT ATTEMPT: [PASTE A QUESTION AND YOUR ANSWER]
TIME UNTIL THE EXAM: [TIMEFRAME]

Produce:

1. MY PROBLEM, DIAGNOSED - from what I described and my attempt:
   - RUNNING OUT OF TIME: usually caused by over-writing early questions, not planning, or spending too long on low-mark questions. Identify which.
   - LOSING MARKS ON KNOWN CONTENT: almost always a command-word problem or not using the information provided in the question.
   - CARELESS ERRORS: usually a checking problem or rushing at the end.
   - FREEZING: often a starting problem rather than a knowledge problem.

2. MY ATTEMPT, MARKED STRICTLY - what would and would not earn marks, and specifically what is correct but uncredited because it does not answer the question asked.

3. THE TIME ALLOCATION - minutes per question based on marks, with a checkpoint: where I should be at the halfway point. Write it as something to memorise and apply.

4. THE OPENING ROUTINE - what to do in the first three minutes of the paper: read through, note which questions are straightforward, decide the order, and start with one you can do. Starting with a hard question costs time and confidence.

5. THE PER-QUESTION ROUTINE - underline the command word, note the marks, plan briefly if it is a long answer, write, then check you answered the question asked. Drilled until automatic.

6. THE OVER-WRITING PROBLEM - writing more than the marks warrant costs time and earns nothing. Say roughly how much a mark is worth in words for my exam.

7. THE STUCK PROTOCOL - what to do when a question will not come: leave it, mark it, move on, and return. Write down what you do know rather than nothing. Time spent staring is the most expensive time in an exam.

8. THE PRACTICE PLAN - given my timeframe, how to practise technique specifically: timed questions, then full timed papers, marked against the scheme strictly. Untimed practice does not train the skill that is failing.

9. THE CHECKING PASS - what to check in the last few minutes, prioritised.

10. THE FREEZING RESPONSE - if that is my problem, practical steps: start with the easiest question, write anything to break the block, and breathe out slowly. Also the honest note that if anxiety is severe, speaking to someone at the institution is worth doing; support and adjustments often exist.

Help me with exam essay technique.

THE QUESTION:
"""
[PASTE]
"""

SUBJECT AND LEVEL: [DETAIL]
MARKS AND TIME: [HOW MANY MARKS, HOW LONG]
MARK SCHEME OR CRITERIA: [PASTE IF AVAILABLE]
MY ATTEMPT OR PLAN: [PASTE, or 'I do not know how to start']

Produce:

1. THE QUESTION DECODED - the command word, the topic, and any limiting phrase that narrows the scope. Essays lose marks by answering a broader question than the one asked. Identify exactly what is in scope.

2. THE MARK SCHEME READING - what the marks are for. Essay marks are usually awarded for: a clear argument, relevant evidence, analysis rather than description, addressing counter-arguments, and a conclusion that answers the question. Say which apply here and their weight.

3. THE PLAN - what a plan should contain and how long to spend on it. Five minutes planning a forty-minute essay is the highest-return five minutes available, and it is the first thing sacrificed under pressure.

4. THE STRUCTURE for this question:
   - The opening: address the question directly and state the line of argument. No throat-clearing, no defining terms unless the question turns on a definition, no 'throughout history'.
   - The body: each paragraph making one point, with evidence, and explicit linking back to the question
   - The counter-argument: where and how, because most essay mark schemes require it
   - The conclusion: answering the question, not summarising the essay

5. THE ARGUMENT - for this specific question, the line you could take, and two alternatives. An essay with a position scores better than one that surveys views without committing.

6. MY ATTEMPT, ASSESSED - where it describes rather than analyses, where it is relevant but not credited, and where the link back to the question is missing.

7. THE ANALYSIS TEST - the difference between description and analysis, shown with a rewritten sentence from my attempt. Description says what happened; analysis says why it matters for the question.

8. THE TIME PLAN - planning, writing, and checking, within the stated time.

9. THE PARAGRAPH TEMPLATE - a reliable shape to use under pressure: point, evidence, explanation, link. Not elegant, but it scores.

10. WHAT LOSES MARKS - narrative rather than argument, evidence without explanation, no conclusion, running out of time mid-paragraph, and answering the question you revised for rather than the one asked.

Help me plan this essay.

THE QUESTION OR TITLE:
"""
[PASTE]
"""

SUBJECT AND LEVEL: [DETAIL]
WORD COUNT: [LENGTH]
WHAT I HAVE READ: [YOUR SOURCES AND KEY POINTS]
MY CURRENT THINKING: [WHAT YOU ARE INCLINED TO ARGUE]
ASSESSMENT CRITERIA: [PASTE, if you have them]

Produce:

1. THE QUESTION ANALYSED - the command word, the scope, and any limiting phrase. Essays lose marks most often by answering a broader or different question than the one set. State exactly what is in scope and, importantly, what is not.

2. THE ARGUMENT - a single sentence stating what this essay will argue. Not what it will cover. If my current thinking is a topic rather than a position, push me to a position and offer three possible ones.

3. THE ARGUMENT TEST - could a reasonable, informed person disagree with my thesis? If not, it is a statement of the obvious and will score poorly however well written.

4. THE STRUCTURE - sections with word budgets. Each section stating the point it makes and how it advances the argument. Order by the logic of the argument, not by chronology or by the order you read the sources.

5. THE EVIDENCE MAP - from what I said I have read, which source supports which point. Flag any point where I have no evidence yet; that is what to read next, and it is more efficient than reading more generally.

6. THE COUNTER-ARGUMENT - the strongest objection to my thesis, and where it is addressed. An essay that ignores the obvious counter-argument reads as naive, and engaging with it seriously is where higher marks are found.

7. THE INTRODUCTION - what it must do: address the question, state the argument, and indicate the route. Not define terms unless the question turns on a definition, and not open with a broad historical gesture.

8. THE CONCLUSION - answering the question, and saying what follows. Not summarising what you just wrote.

9. AGAINST THE CRITERIA - if I gave them, where the marks are and whether this plan targets them.

10. WHAT TO CUT - given the word count, what my plan cannot accommodate. Essays are usually over-planned, and cutting at the plan stage is far cheaper than at the draft stage.

Help me with referencing.

CITATION STYLE: [Harvard / APA / MLA / Chicago / Vancouver / other]
MY TEXT:
"""
[PASTE A SECTION WITH YOUR CITATIONS]
"""
MY SOURCES: [PASTE THE DETAILS YOU HAVE]
LEVEL: [STAGE]
WHAT I AM UNSURE ABOUT: [YOUR QUESTION]

Produce:

1. WHAT NEEDS CITING - the rule, applied to my text specifically. Cite: any idea that is not yours, any data, any direct quotation, any paraphrase of a specific argument, and anything contestable. Do not cite: common knowledge in the field, and your own reasoning. Go through my text and flag every sentence that needs a citation and does not have one.

2. THE PARAPHRASE CHECK - the highest-risk area for unintentional plagiarism. A paraphrase that keeps the original sentence structure and swaps synonyms is not a paraphrase; it is a close copy with a citation, and it is treated as plagiarism at most institutions. Check my text for this specifically and quote any instance.

3. HOW TO PARAPHRASE PROPERLY - read, understand, close the source, write from your understanding, then check you have not reproduced the phrasing. Demonstrate with one passage from my text.

4. THE CITATIONS CORRECTED - my in-text citations in the correct format for my style, with errors explained.

5. THE REFERENCE LIST - formatted correctly from the details I gave. Flag any entry where I have not provided enough information, and say exactly what is missing.

6. THE SECONDARY CITATION PROBLEM - where I am citing a source I have not read, via another source. The correct handling for my style, and the strong recommendation to read the original where it matters. Citing something you have not read is how errors propagate.

7. THE QUOTATION RULES - when to quote directly rather than paraphrase, how to format short and long quotations in my style, how to indicate omissions and alterations, and the rule that a quotation must be exact.

8. MY SPECIFIC QUESTION - answered.

9. THE OVER-CITATION CHECK - a sentence with four citations attached usually means the writer has not synthesised. Note where my text does this and what it suggests.

10. THE INTEGRITY NOTE - the practical habits that prevent problems: record the source at the moment you take a note, mark quotations unmistakably in your notes, and never paste source text into your draft intending to rewrite it later. That last one is the most common route to accidental plagiarism.

Citation styles have detailed rules and vary by institution. Check your institution's guide for anything unusual.

Explain [TOPIC] to me.

WHAT I ALREADY KNOW ABOUT THIS AREA: [BE SPECIFIC - this determines everything]
WHY I WANT TO UNDERSTAND IT: [THE REASON - curiosity, a decision, work, study]
HOW DEEP: [the gist / enough to discuss it / enough to use it / enough to teach it]
WHAT I HAVE READ OR BEEN TOLD ALREADY: [WHAT DID NOT WORK]

Structure the explanation as follows:

1. THE ONE-SENTENCE VERSION - what this is, in plain words, before any terminology.

2. WHY IT EXISTS - what problem this idea solves or what question it answers. Concepts make far more sense when you know what they are for. Most explanations skip this and start with the definition.

3. THE CONCRETE CASE - a specific example, in full, before any generalisation. Build the abstraction from the instance rather than the other way round.

4. THE MECHANISM - how it actually works, built up in steps from what I said I already know. Do not introduce a term before it is needed.

5. THE TERMINOLOGY - each technical word, introduced once the idea it names is already in place, with a note where it means something different in ordinary usage.

6. THE ANALOGY AND ITS LIMITS - one analogy, and explicitly where it stops being true. An analogy without stated limits becomes a misconception.

7. THE COMMON MISUNDERSTANDING - what people usually get wrong about this, and why the wrong version is appealing.

8. WHAT I ASKED ABOUT THAT DID NOT WORK - I said what I have read already. If there is a standard explanation of this topic that commonly fails, say why it fails and what to use instead.

9. THE DEPTH CHECK - stop at the level I asked for. Do not continue into detail I do not need; it obscures what I came for. Say what the next level down would cover, so I know what is being left out.

10. THE TEST - one question I should be able to answer if this landed. It should require applying the idea, not repeating it.

Do not open with a definition. Do not use an analogy in the first paragraph.

I am learning to code and I want to use AI without it holding me back. Help me set up a good approach.

MY LEVEL: [HOW LONG YOU HAVE BEEN LEARNING AND WHAT YOU CAN DO]
WHAT I AM WORKING ON: [PROJECT OR COURSE]
HOW I CURRENTLY USE AI: [BE HONEST - what you ask for and how often]
WHAT I WANT TO BE ABLE TO DO: [YOUR GOAL]
WHAT I WORRY ABOUT: [YOUR CONCERN]

Produce:

1. THE HONEST PROBLEM - asking for working code and pasting it in produces a working program and no ability. The feeling of progress is real and the capability is not, and it becomes apparent the first time you have to work without assistance. Assess my described usage against this directly.

2. WHAT TO ASK FOR, AND WHAT NOT TO:
   - ASK: explain this error, explain this concept, why does this not work, review what I wrote, what is a better way to approach this, what should I learn next
   - AVOID EARLY: write this function for me, build this feature, do this exercise
   The distinction is whether the answer does your thinking or informs it.

3. THE ATTEMPT-FIRST RULE - write your own version before asking anything. Even a broken attempt. The value comes from having tried, because you then understand what the answer is answering. Asking before attempting skips the part where learning happens.

4. THE EXPLAIN-BACK RULE - if you accept any code you did not write, explain every line before using it. If you cannot, you have not learned anything and you have added code you cannot maintain.

5. THE TYPE-IT-OUT RULE - do not paste. Typing code out forces you to read it, and you will notice things you would otherwise skim past.

6. THE STUCK PROTOCOL - how long to struggle before asking. Long enough to have engaged with the problem, not so long that you give up. Say roughly what is appropriate at my level, and what to do in that time: read the error, check your assumptions, narrow it down.

7. THE SELF-CHECK - a regular test that you are actually learning: close everything and write something from scratch. If you cannot do what you did yesterday with help, the help is replacing rather than building capability. Say how often to do this.

8. THE VERIFICATION HABIT - AI-generated code can be confidently wrong, subtly inefficient, or insecure. Never run code you do not understand, and check it does what you expect on inputs you chose.

9. WHEN IT IS FINE TO JUST GET THE ANSWER - boilerplate, syntax you have used a hundred times, configuration, and things outside what you are trying to learn. Not everything needs to be a learning opportunity.

10. THE ADJUSTED PLAN - given how I said I currently use it, the specific changes to make.

Tailor my CV to this job.

JOB DESCRIPTION: [PASTE]
MY CURRENT CV: [PASTE]
ANYTHING NOT ON MY CV THAT IS RELEVANT: [EXTRA EXPERIENCE]

Do this:
1. REQUIREMENTS MAP - a table: requirement from the job | my matching evidence | strength (strong / partial / missing)
2. REWRITTEN SUMMARY - 3 lines aimed at this role
3. REWRITTEN BULLETS - for my most relevant roles, in the format: action verb + what I did + result (with a number where I gave one). Only use facts from my CV and extra notes - mark [ADD NUMBER] where a result would help but I did not provide one.
4. KEYWORDS - the job's key terms that should appear naturally (applicant tracking systems often scan for these)
5. GAPS - requirements I do not meet, and honest ways to address them in a cover letter
6. WHAT TO CUT - content that does not help for this role

Never invent jobs, titles, qualifications or results.

Help me prepare for a job interview.

ROLE AND COMPANY: [DETAILS]
JOB DESCRIPTION: [PASTE]
MY BACKGROUND: [SUMMARY OR CV]
INTERVIEW TYPE: [phone screen / competency / technical / panel / final]

Do this:
1. The 10 questions I am most likely to be asked for this role, including 2 difficult ones
2. For each, help me build an answer using the STAR method (Situation, Task, Action, Result) from MY experience - ask me for a story where you do not have one, rather than inventing it
3. My answer to "Tell me about yourself" in under 90 seconds
4. 5 smart questions to ask the interviewer
5. Then run a mock interview: ask me one question at a time, wait for my answer, and give feedback on structure, specifics and length before the next question.