Counts show all available guides. Filters combine to narrow your results.
Simplify a complex taskGuide
Find where your confidence and practice results disagree
A comparison of pre-answer confidence and checked answers, followed by a small targeted practice plan.
Illustrative resourceNot tool-testedAdults working with original, synthetic or authorized non-sensitive material
What you’re working towards
A small calibration review using recorded predictions and answer-key results, plus a targeted next-practice list. This is an authored practice example; no consumer AI run or real participant trial has been recorded.
Your choice also saves this guide’s current worked-example checkmarks. Only this browser; no account or sync. View saved guides
Saving needs JavaScript. Reading and downloading this guide does not save it.
Make a start
One step at a time.
2 steps
Start with the synthetic worked example or other non-sensitive inputs. Run one prompt at a time in your chosen AI tool. Replace any bracketed placeholders with the requested material, check each reply, and supply the source or earlier outputs that step needs. Paste them again if the tool lacks that context.
Start with the synthetic example, then adapt each prompt to your task.
01
Try the complete example
Open a new chat in a text AI assistant you already have permission to use. Copy the entire prompt below, including SAMPLE INPUT, into the message box and send it. No upload or special tool is needed. Expect a comparison of pre-answer confidence and checked answers, followed by a small targeted practice plan. Compare the result with Input; Output is a worked illustration, not text you need to paste. Q1 and Q3 are incorrect; Q2 and Q4 are correct, giving 2 of 4. The four labels occur once each; high and low each have 1 correct out of 2. In the illustrative Output, the two practice items use up to 6 + 4 = 10 minutes and have answer keys 1/2 and 9. Your assistant may choose different practice items: check that there are at most two, they target the demonstrated errors with the high-confidence miss first, their proposed time adds to no more than 10 minutes, and their answer keys are correct. Future answers stay unrecorded. If a detail differs, paste: “This part is wrong: [quote it]. My input says: [quote the exact source line or rule]. Return a complete corrected replacement and explain the change.” Recheck it yourself. If the source is missing or contradictory, leave that part unresolved and obtain the needed fact before using it.
Your starting prompt
Check each recorded answer against the supplied key, apply the four label rules and show the narrow arithmetic. Count the outcomes without turning high/low into probabilities or diagnosing a person. Choose at most two practice items under the priority and 10-minute rules, with confidence recorded before each answer and a separate answer key. Do not invent results for those future attempts.
SAMPLE INPUT
Original synthetic practice input. The people, organizations, records and events below are fictional.
Fictional adult learning log. High and low are self-chosen labels, not numeric probabilities. In this invented record, confidence was written before attempting each question and before seeing the key, and was not changed afterward.
Q1 | topic: adding fractions | question: 1/2 + 1/4 | confidence: high | learner answer: 2/6
Q2 | topic: ratios | question: blue:red = 2:3; if blue = 4, how many red? | confidence: low | learner answer: 6
Q3 | topic: fraction of a quantity | question: 3/4 of 8 | confidence: low | learner answer: 5
Q4 | topic: units | question: 200 cm in metres, using 100 cm = 1 m | confidence: high | learner answer: 2 m
Supplied checked key: Q1 = 3/4; Q2 = 6; Q3 = 6; Q4 = 2 m.
Review rule: compare each answer with the key, then label high/incorrect as high-confidence miss, low/correct as uncertain success, low/incorrect as acknowledged gap, high/correct as supported confidence on this item only.
Practice limit: choose at most two next practice items within a proposed 10-minute session. Prioritize observed incorrect answers, putting a high-confidence miss first. Use Q1 and Q3’s written errors to explain the narrow focus. Do not diagnose ability, infer why the learner felt confident or claim future improvement.
Return written text only. Keep this fictional and label illustrative dialogue as invented. Do not claim an actual interview, survey, learner trial or tool execution. Do not send, publish, collect responses or change another service.
02
Use your own input
Open a new chat. Replace every bracketed field in the prompt below, then paste the whole message. Change related names, source IDs, counts, dates, labels, limits and checks together; none of the sample facts carries over. Use only your own, authorized non-sensitive material. Expect the same kind of complete result using your inputs. Verify the timing of your confidence notes and compare every answer with the key yourself. Recompute the counts and practice answers. If confidence was recorded after seeing answers, label it retrospective and do not treat it as a prediction. If a detail differs, paste: “This part is wrong: [quote it]. My input says: [quote the exact source line or rule]. Return a complete corrected replacement and explain the change.” Recheck it yourself. If the source is missing or contradictory, leave that part unresolved and obtain the needed fact before using it.
Your starting prompt
Compare my recorded pre-answer confidence with my actual answers and supplied answer key. Preserve original confidence labels. First check correctness, then apply my explicit confidence/result label rules. Show item-level evidence and descriptive counts without inferring a diagnosis, stable ability or numeric probabilities from verbal labels. Choose next practice from demonstrated gaps within my item/time limits and priority rule; include a separate check key only where my supplied source rules support it. Leave future performance unknown.
MY INPUT
Question IDs, full questions, topic labels and permitted source rules: [replace with complete non-sensitive details, or state unknown]
Confidence labels recorded before seeing answers and how timing is known: [replace with complete non-sensitive details, or state unknown]
Actual answers and supplied checked key: [replace with complete non-sensitive details, or state unknown]
Confidence/result label definitions: [replace with complete non-sensitive details, or state unknown]
Practice item limit, time limit and priority rule: [replace with complete non-sensitive details, or state unknown]
Use only MY INPUT for facts, names, dates, counts and constraints. Ask about essential missing information or conflicting rules instead of guessing. Do not import any practice-example values. Return the complete requested result, unresolved questions and checks tied to my input. Do not send, publish, collect responses, buy, book or change another service.
Optional: improve the result
Keep the next attempt separate
Prepare a blank record without pretending practice has happened. This optional extension uses only the original synthetic sample. Return to the sample chat, or paste its complete Input into a new chat first. To use it with your own material, replace the source and every dependent rule, number and check explicitly.
Advanced prompt
Using the original Q1–Q4 source, prepare a blank follow-up log for these two illustrative practice items: P1, adding fractions, 1/3 + 1/6; P2, fraction of a quantity, 3/4 of 12. Include item ID, topic, confidence before answering, answer, key comparison and next question. Keep future confidence, answer and result fields blank and preserve Q1–Q4 unchanged. Explain how to mark confidence timing as unknown if it was not recorded before attempting the item.
Show, then try
See the shape of the result.
This input is synthetic. The output is a written illustration of the intended result, not a verified AI-tool run.
01 / The starting point
Synthetic input
Original synthetic practice input. The people, organizations, records and events below are fictional.
Fictional adult learning log. High and low are self-chosen labels, not numeric probabilities. In this invented record, confidence was written before attempting each question and before seeing the key, and was not changed afterward.
Q1 | topic: adding fractions | question: 1/2 + 1/4 | confidence: high | learner answer: 2/6
Q2 | topic: ratios | question: blue:red = 2:3; if blue = 4, how many red? | confidence: low | learner answer: 6
Q3 | topic: fraction of a quantity | question: 3/4 of 8 | confidence: low | learner answer: 5
Q4 | topic: units | question: 200 cm in metres, using 100 cm = 1 m | confidence: high | learner answer: 2 m
Supplied checked key: Q1 = 3/4; Q2 = 6; Q3 = 6; Q4 = 2 m.
Review rule: compare each answer with the key, then label high/incorrect as high-confidence miss, low/correct as uncertain success, low/incorrect as acknowledged gap, high/correct as supported confidence on this item only.
Practice limit: choose at most two next practice items within a proposed 10-minute session. Prioritize observed incorrect answers, putting a high-confidence miss first. Use Q1 and Q3’s written errors to explain the narrow focus. Do not diagnose ability, infer why the learner felt confident or claim future improvement.
Copies text only. For image or file tasks, use the source files named in the steps too.
Illustrative answer authored for this guide; not a recorded AI response or a real-world trial.
Item-by-item comparison
Q1 | high | incorrect: 2/6 differs from 3/4 | high-confidence miss
The answer 2/6 matches adding both numerators and denominators, but the intermediate work was not supplied. Use equal-sized parts: 1/2 = 2/4, so 2/4 + 1/4 = 3/4.
Q2 | low | correct: 6 matches the key | uncertain success
Blue doubles from 2 to 4, so red doubles from 3 to 6. Correct here does not establish mastery of ratios.
Q3 | low | incorrect: 5 differs from 6 | acknowledged gap
One quarter of 8 is 2; three quarters are 3 × 2 = 6. The answer alone does not reveal how 5 was obtained.
Q4 | high | correct: 2 m matches the key | supported confidence on this item
200 cm ÷ 100 cm per metre = 2 m. This supports this answer, not all unit conversions.
Small-log summary
Two of four answers are correct. The high-confidence items have 1 correct out of 2; low-confidence items also have 1 correct out of 2. There is one item in each of the four labels. These are descriptive counts from four invented items, not stable ability estimates or confidence probabilities.
Next practice, proposed maximum 10 minutes
1. Q1 focus, up to 6 minutes: before looking at an answer, record high/low confidence and solve 1/3 + 1/6 by writing equal denominators. Check afterward with the key below; explain why the denominator is not added.
2. Q3 focus, up to 4 minutes: record confidence first, then find 3/4 of 12 by finding one quarter and multiplying by 3. Check afterward with the key below.
Stop when the available time ends; unfinished work stays unfinished. Keep both original confidence labels and later attempts as separate records.
Practice answer key, read after trying
1. 1/3 + 1/6 = 2/6 + 1/6 = 3/6 = 1/2.
2. 12 ÷ 4 = 3; 3 × 3 = 9.
Q2’s uncertain success is worth revisiting in a later owner-chosen session, but no third item is added to this two-item plan. No later answers or learning gains have been recorded.
These checks use the worked example and its particular facts. With your own material, check your actual names, numbers, sources and rules; do not reuse the sample’s values as the answer.
Unsaved checks stay in this tab and reset when you reload. If you choose Save guide, its current example checkmarks are kept in this browser when storage is available.
!
A few things to watch for.
Changing confidence after seeing the key erases the comparison you wanted to make.
One confident mistake does not establish an overconfident personality, and one correct answer does not establish mastery.