+ Strong workflow covering accuracy, safety, and correction.
- Startup context and advanced Socratic tactics are limited.
a world-class prompt engineer and AI systems architect.
| Category | Using AI › Writing prompts |
|---|---|
| Tags | DraftingReviewingDeveloper |
You are a world-class prompt engineer and AI systems architect. Create ONE system prompt of exactly ${sizeLimit} characters or fewer (strict count: every letter, space, punctuation, and newline) that will serve as the complete, production-ready instructions for ${targetAgent}.
The system prompt must fully instruct ${targetAgent} on the ${method} technique: its core principles, proven methodologies, precise step-by-step execution workflow, mandatory behavioral rules, self-correction mechanisms, common failure modes to avoid, and advanced strategies that force the absolute highest-quality, most rigorous, and insightful application of ${method} to any topic, query, or problem. Use official documentation where possible.
Internal process (execute fully in thinking; output nothing until the end):
1. Generate initial candidate P1 (≤ ${sizeLimit} chars).
2. Review P1 exactly as ${targetAgent} would receive it. Score 1-10 on: Clarity, Specificity & Actionability, Methodological Coverage, Behavioral Enforcement, Length Compliance, and Overall Effectiveness at eliciting peak ${method} performance. List every weakness with concrete examples.
3. Produce refined P2 that fixes all weaknesses while preserving strengths and tightening language.
4. Repeat the full review-and-refine cycle (steps 2-3) at least 3 more times (minimum 4 total iterations), each round driving deeper precision, stronger enforcement, and better ${method} outcomes.
5. After all iterations, select and output ONLY the single best final prompt. It must be ≤ ${sizeLimit} characters, perfectly tailored for "${targetAgent}", and immediately usable as its system prompt with zero additional text.Useful for compressing a specific method into agent instructions. It requires at least four refinement cycles and strict character-limit compliance, outputting only the final prompt.
ChatGPT is strongest in compliance and operational safety. Claude is concise but internally inconsistent, while Gemini is specific yet critically exceeds the length limit.
+ Strong workflow covering accuracy, safety, and correction.
- Startup context and advanced Socratic tactics are limited.
+ Concise, practical integration of questions and workflow.
- Question limits conflict, and some escalations are excessive.
+ Concrete triage and startup-specific strategies.
- Far exceeds 3,000 characters and overconstrains behavior.
| Criterion | ChatGPT | Claude | Gemini | Leader |
|---|---|---|---|---|
| Instruction following | 9 | 8 | 3 | ChatGPT +13% |
| Accuracy | 9 | 8 | 6 | ChatGPT +13% |
| Specificity | 8 | 9 | 9 | Tie |
| Structure | 9 | 9 | 8 | Tie |
| Right length | 9 | 9 | 2 | Tie |
Scored 1–10 by gpt-5.6-sol with model names hidden (2026-09-24). This is an AI review, not a measurement.
We gave three models the same input and copied their answers unedited. Each ran in its CLI (an agent harness), and answers in the ChatGPT or Claude apps or on the web may differ. Outputs are in Korean.
[Pasted material] sizeLimit: 3000자, targetAgent: 스타트업 고객지원 챗봇 시스템 프롬프트, method: 소크라테스식 문답법(Socratic Questioning)
당신은 스타트업 고객지원 챗봇이다. 목표는 고객의 문제를 정확히 이해하고, 스스로 핵심을 명확히 파악하도록 도우며, 실행 가능한 해결책을 제공하는 것이다. 모든 대화에서 소크라테스식 문답법을 적용하되, 질문 자체가 목적이 되지 않도록 한다. 공감, 정확성, 효율성, 안전을 항상 우선한다.
핵심 원칙:
대화 절차:
질문 설계 규칙:
응답 형식:
정확성 규칙:
항상 대화의 마지막에 고객의 목표 달성 여부를 확인하고, 답변이 실제 문제 해결로 이어졌는지 스스로 점검한다.
| 4 Optimized Versions of A Prompt (in Arabic) | |
| $500/Hour AI Consultant Prompt | |
| Adaptive Thinking Framework | |
| Agent Organization Expert | |
| AI Kickstart prompt |