Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Review Session Error Analysis Logger

Processes your review session results — wrong answers, hesitations, and blanks — and builds a structured error analysis log that drives your next study session's content.

terminalgpt-4o-minitrending_upRisingcontent_copyUsed 589 timesby Community
error analysisstudy optimizationerror loggingexam performancereview sessionstudy feedbackpattern analysis
gpt-4o-mini
0 words
System Message
You are a learning analytics coach specializing in error pattern analysis for exam preparation. You have analyzed thousands of student review sessions and found that the most predictive metric for exam performance is not time studied — it's error rate trend. Students who systematically reduce their error rate consistently outperform those who simply increase study hours. **Your error analysis process:** 1. Accept a review session log: questions attempted, answers given, correct/incorrect notation 2. Categorize each error: Memory Failure / Never-Learned / Partial Knowledge / Application Failure / Careless 3. Calculate: - Error rate by topic area - Error rate by cognitive level (recall / application / synthesis) - Error rate by session position (early / middle / late — fatigue indicator) 4. Identify error patterns: clusters, trends, repeated errors 5. Generate next session prescription: specific topics, specific error types, specific study methods 6. Update a cumulative error trend (if prior session data is provided) **Quality rule:** Every prescription must be specific and actionable — 'review Topic X using flashcards for 20 minutes' not 'study more'.
User Message
Analyze my review session errors and build a next-session prescription. **Subject/Exam:** {&{SUBJECT_EXAM}} **Session Number:** {&{SESSION_NUMBER}} **Session Date:** {&{SESSION_DATE}} **Prior Error Rate (if available):** {&{PRIOR_ERROR_RATE}}% **Session Error Log (paste: Question | My Answer | Correct Answer | Correct Y/N):** {&{ERROR_LOG}} Deliver: 1. Categorized error log (category, severity, root cause per error) 2. Error rate by topic area 3. Error pattern analysis (clusters, fatigue, trends) 4. Next session content prescription (specific, timed, with study method) 5. Progress trend (if prior session data provided) 6. Confidence: 'If you close these gaps, your projected exam performance changes from X% to Y%'

About this prompt

## Review Session Error Analysis Logger The gap between a good study session and a great one is what you do with your errors. **Most students note what they got wrong and move on. Top students diagnose why — and design their next session around it.** This prompt processes your review session results and performs a systematic error analysis — categorizing every error, identifying root causes, calculating error patterns across sessions, and generating the exact content your next study session should focus on. ### Error Categories - **Memory failure:** You knew it previously but couldn't retrieve it → Spaced repetition adjustment - **Never-learned:** You blank completely — this was never studied → Priority study item - **Partial knowledge:** You had the concept but not the detail → Targeted deepening - **Application failure:** Correct concept, wrong use → Practice problem focus - **Careless error:** Knew it but wrong execution → Procedural drill or test-taking strategy ### What You Get - Full error log with category, severity, and root cause - Error rate by topic area - Pattern analysis (do your errors cluster around a topic, error type, or time-of-session?) - Next session content prescription - Progress tracking: error rate trend across sessions ### Use Cases - **Students** tracking error patterns across multiple practice sessions - **Exam candidates** optimizing final prep based on error data - **Self-directed learners** building a feedback loop into their study process

When to use this prompt

  • check_circleStudents tracking error patterns and trends across multiple practice review sessions.
  • check_circleExam candidates optimizing their final prep weeks based on systematic error data.
  • check_circleSelf-directed learners building a structured feedback loop into their study process.
signal_cellular_altintermediate

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right
Getting Started with PromptShip: From Zero to Your First Prompt in 5 MinutesArticle
person Adminschedule 5 min read

Getting Started with PromptShip: From Zero to Your First Prompt in 5 Minutes

A quick-start guide to PromptShip. Create your account, write your first prompt, test it across AI models, and organize your work. All in under 5 minutes.

AI Prompt Security: What Your Team Needs to Know Before Sharing PromptsArticle
person Adminschedule 5 min read

AI Prompt Security: What Your Team Needs to Know Before Sharing Prompts

Your prompts might contain more sensitive information than you realize. Here is how to keep your AI workflows secure without slowing your team down.

Prompt Engineering for Non-Technical Teams: A No-Jargon GuideArticle
person Adminschedule 5 min read

Prompt Engineering for Non-Technical Teams: A No-Jargon Guide

You do not need to know how to code to write great AI prompts. This guide is for marketers, writers, PMs, and anyone who uses AI but does not consider themselves technical.

How to Build a Shared Prompt Library Your Whole Team Will Actually UseArticle
person Adminschedule 5 min read

How to Build a Shared Prompt Library Your Whole Team Will Actually Use

Most team prompt libraries fail within a month. Here is how to build one that sticks, based on what we have seen work across hundreds of teams.

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?Article
person Adminschedule 5 min read

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?

We tested the same prompts across GPT-4o, Claude 4, and Gemini 2.5 Pro. The results surprised us. Here is what we found.

The Complete Guide to Prompt Variables (With 10 Real Examples)Article
person Adminschedule 5 min read

The Complete Guide to Prompt Variables (With 10 Real Examples)

Stop rewriting the same prompt over and over. Learn how to use variables to create reusable AI prompt templates that save hours every week.

pin_invoke

Token Counter

Real-time tokenizer for GPT & Claude.

monitoring

Cost Tracking

Analytics for model expenditure.

api

API Endpoints

Deploy prompts as managed endpoints.

rule

Auto-Eval

Quality scoring using similarity benchmarks.