A practice test you do not analyze is a wasted test. The score tells you that you missed 14 questions; it never tells you why. These 15 prompts turn the messy after-test wreckage into a structured diagnosis: which misses were conceptual, which were careless, which were time-pressure, and exactly what to drill in the next 2 weeks.
TL;DR
- Run prompt 1 (error taxonomy) on every test before you do anything else; it sorts each miss into concept / careless / pacing / strategy / knowledge gap.
- Most “careless” errors are actually conceptual. The prompts default to conceptual until proven otherwise so you stop fooling yourself.
- Paste raw data (your wrong answers, the correct answers, time-per-question) into a long-context model. As of June 2026, Claude Sonnet 4.6 and Gemini 3.1 Pro both take 1M tokens, so an entire mock plus its answer key fits in one message.
- Chain prompts: taxonomy (1) then repeated-mistake detector (5) then 2-week plan (9). That is the whole loop.
Who this is for
High-stakes test-takers (digital SAT, GRE, GMAT Focus, MCAT, LSAT, bar, med boards), AP and IB students, undergrad-finals preppers, and tutors building individualized revision plans. All 15 prompts are exam-agnostic; you fill in the test name and paste your own data.
It helps the model to know your test’s scoring shape so projections and section weighting make sense. Current scales as of June 2026:
| Exam | Sections | Score scale |
|---|---|---|
| Digital SAT | Reading & Writing, Math (2 adaptive modules each) | 400-1600 (200-800/section) |
| GRE General | Verbal, Quant, Analytical Writing | 260-340 + AW 0-6 |
| GMAT Focus | Quant, Verbal, Data Insights | 205-805 (60-90/section) |
Tell the model which scale you are on; otherwise it may project a digital-SAT 1600 onto a GMAT prompt.
When not to use these prompts
Skip if you have not taken at least one full-length, timed practice test; there is nothing to diagnose. Skip too if the test is more than 3 weeks past, because recall of what you were thinking fades fast and the careless-vs-conceptual call gets unreliable. Do the analysis within 24-48 hours while the reasoning is still fresh.
Pick the right model
You do not need a paid tier for most of this, but the data is bulky. As of June 2026:
- Claude Sonnet 4.6 or Opus 4.7 (Claude pricing guide) give the cleanest step-by-step pedagogical breakdowns and a 1M-token window on Pro ($20/mo). Best default for diagnosis.
- ChatGPT (plans compared) with GPT-5.5 in Thinking mode is strongest for quantitative reasoning checks (SAT Math, GMAT Quant). Free tier works but in-app context is tight (~320 pages on Plus; full 1M only on the $200 Pro tier).
- Gemini 3.1 Pro is the pick when you want it to pull a current official rubric or score table from the web with fewer fabricated sources.
A free account is enough to start. Paste the data, do not retype it. If your platform exports a per-question report (the College Board Bluebook app and most GMAT/GRE prep platforms do), copy that report straight in rather than transcribing by hand.
Best for
- Full-length practice test review
- Pre-exam targeted revision
- Tutor-student diagnostic session
- Subject-specific section weakness
- Final 2-week countdown planning
15 copy-ready prompt templates
1. Error taxonomy by question
Default first pass; classify each miss.
You are an exam coach. Below are the questions I missed on my {test name} practice exam. For each: classify the error as (a) conceptual gap, (b) misread / careless, (c) time pressure, (d) test-taking strategy, (e) genuine knowledge gap. Recommend 1 specific drill per category.
{paste questions + my wrong answers + correct answers}Variables to swap: test name, questions, answers
Optimization: If classifications feel vague, add: “Be ruthless. If a question could be classified as both careless and conceptual, default to conceptual until proven otherwise.”
2. Concept cluster analysis
Below is my error log. Group my misses by topic / concept cluster. For each cluster: number of misses, the underlying concept, 1-line root cause, and 3 practice problems I should redo before drilling new material.
{paste log}3. Time-management triage
Below is my time-per-question log for the exam. Identify: (a) questions I spent too long on, (b) questions I rushed, (c) the score impact of better pacing, (d) one pacing rule for next time.
{paste timing}4. Section-by-section heat map
For my recent {test name} score breakdown: {paste section scores}, identify the 2 sections with the highest leverage for improvement and the 1 section to maintain. Suggest hours-per-week per section for the next 4 weeks.5. Repeated-mistake detector
Below are my last 3 practice tests with error logs. Identify the top 5 mistakes I keep making, the underlying root cause for each, and whether they are getting better or worse over time.
{paste 3 logs}6. Confidence-vs-correctness audit
For each missed question below, I will provide my pre-answer confidence (1-5). Identify questions where I was high-confidence but wrong (overconfidence zone — most dangerous) and questions where I was low-confidence and right (could practice trusting instinct).
{paste questions + confidence + outcome}7. Strategy-bug catch
Below are the questions I missed. Identify strategy bugs: (a) starting with the hardest question, (b) reading every answer choice instead of predicting, (c) over-engineering a simple question, (d) not using elimination. Quantify how many missed questions each bug touched.
{paste}8. Topic-by-difficulty matrix
For my recent exam, build a 4x3 matrix: rows = top topics, columns = easy / medium / hard. In each cell, write my accuracy %. Identify the 3 cells where extra prep would yield the highest point gains.
{paste data}9. 2-week revision plan
Based on my diagnosis ({paste}), build a 2-week revision plan. Each day: 1 focus topic, 1 timed mini-section, 1 review activity. Friday: full timed section. Sunday: weekly review. Constraints: max {hours/day}.10. Targeted question generator
I keep missing questions on {topic}. Generate 8 practice questions in {test format} on this topic, increasing in difficulty. Include the answer key and 1-line explanation per answer. Mark which 2 should be drilled multiple times.11. Mock-exam debrief sheet
Below is my full mock exam result. Produce a 1-page debrief: overall score, section breakdowns, top 5 missed topics, top 3 strategy bugs, top 2 strengths to lean on, and 3 concrete commitments for the next 7 days.
{paste mock results}12. Diagnostic interview script
I am about to walk through 5 missed questions with my tutor. For each, generate 3 probing questions she could ask me to surface my reasoning (e.g., "what did you think the question was asking?"). Goal: distinguish careless from conceptual.
{paste questions}13. Anxiety / pacing intervention
My recent exam pattern: strong in section 1, fading in section 3. Likely causes: fatigue, anxiety, time pressure. Suggest 4 interventions (between-section reset routine, hydration, micro-pacing checks, practice under fatigue). Each intervention as 1-line action.14. Score-projection model
Based on my last 3 practice tests ({paste scores}), project my likely score range on test day. Identify the score I need for {goal school / cert} and the 3 highest-leverage actions to close the gap.15. Final-week game plan
The exam is in 7 days. Based on my diagnosis: {paste}. Build a final-week plan that includes: 2 full-length mocks (which days), light review, sleep / nutrition / logistics, what NOT to do in the last 48 hours. End with 3 morning-of-test rituals.Common mistakes
- Reviewing only wrong answers — checking right answers for “lucky guesses” matters too.
- Lumping all errors as “careless” — most “careless” errors are actually conceptual.
- Skipping time-tracking — pacing is half the score on every standardized test.
- Drilling new material when you have not patched repeated mistakes.
- Doing more practice tests without analyzing the prior ones.
- Targeting your weakest topic alone without considering its frequency on the test.
- Cramming the last week instead of reviewing high-leverage drills.
How to push results further
- After every practice test, do template 1 (taxonomy) before doing anything else.
- Track confidence pre-answer (template 6) — overconfidence is the most dangerous bug.
- Build a “repeated misses” file across all practice tests; this is where score points hide.
- Pair concept drills with timed mini-sections (template 9) to build retrieval under pressure.
- The day before the test, do only light review and template 15 logistics.
- Tutor sessions are more productive when the student brings completed template 12 questions.
- Do not chase perfection on rare-question topics; high-frequency topics matter more.
FAQ
- How often should I take full-length practice tests?: Every 2 weeks during prep, weekly in the final month. More frequent than that and analysis lags behind.
- What if I keep making the same mistake?: It is rarely careless; the underlying concept or strategy is broken. Use template 5 and rebuild the foundation.
- Should I use AI to grade essay sections?: Use it for structure, argument gaps, and rubric-style feedback, then check against the official rubric. Note that the real GRE already scores the Analyze an Issue essay with ETS’s own e-rater plus a human rater, so treat any AI score as directional, not the number you will get.
- How accurate is the score projection?: Useful for trend, not for prediction. Real test-day scores depend on rest, stress, and section difficulty.
- Is AI a substitute for a tutor?: For diagnosis and drill, often yes. For motivation, accountability, and personalized strategy, a good tutor still wins.
Related
- Exam revision plan prompts
- Quiz generation prompts
- Study plan prompts
- Flashcard prompts
- Learning & Research Prompts hub
Tags: #Prompt #Study #exam-prep #Study plan