☰ Categories

Read how you work from the conversation

Describes how you ask, react and lose time, using only this conversation. No personality labels or flattery; evidence for every point.

CategoryUsing AI › Context management
TagsAnalyzingReviewingOffice worker
Prompt
Using **only this conversation**, describe how I work — not who I am.

***You are reading behaviour in a transcript, not diagnosing a personality.*** Say that once at the top.

**What to read**
1. **How I ask** — do I give context up front or drip it in? Do I state what "done" looks like?
2. **How I react to your answers** — what makes me push back, what I accept without checking
3. **Where I lose time** — repeated requests, goals that shift mid-way, decisions I keep reopening
4. **One thing I do well** that I should keep doing

**Rules**
- ***Every observation needs evidence.*** Quote or point to the message it came from. No evidence, no observation
- **No personality labels** — no MBTI, no "you are a perfectionist", no strengths/weaknesses lists. Describe what I did, not what I am
- **No flattery.** If the only good thing you can find is small, say the small thing
- If the conversation is too short or too narrow to say something, say what you *cannot* tell from it
- End with **one concrete change** to how I write requests, in a single sentence I could paste into my next prompt
After pasting, fill in the fields at the bottom (Anything specific to look at (optional))

What this prompt does

"Analyze me" prompts usually end in a personality type or compliments. This one limits itself to observable behaviour in the transcript, requires a cited message for every observation, and ends with one sentence you can paste into your next request.

Model comparison

ChatGPT is the most accurate and concise; Gemini is specific but verbose and adds unsupported metadata. [C] was not provided and cannot be meaningfully evaluated.

ChatGPTTop overall
45/ 50

+ Covers every requested area concisely with evidence.

- Slightly generalizes a work habit from one request.

Gemini
39/ 50

+ Clearly separates evidence from unknowable areas.

- Invents a step_index and is unnecessarily verbose.

CriterionChatGPTGeminiLeader
Instruction following98ChatGPT +13%
Accuracy97ChatGPT +29%
Specificity99Tie
Structure99Tie
Right length96ChatGPT +50%

Scored 1–10 by gpt-5.6-sol with model names hidden (2026-09-25). This is an AI review, not a measurement.

Read full answers

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.

Input used
Anything specific to look at (optional): 요청할 때 맥락을 얼마나 주는지, 그리고 답변을 받은 뒤 피드백을 어떻게 반영하는지
gpt-5.6-luna (codex CLI · 에이전트 하네스) · Run on 2026-09-24

이 평가는 성격 진단이 아니라, 이 대화 기록에서 드러난 행동만 읽은 것입니다.

  • 요청할 때 맥락을 많이 줍니다. 분석 대상(“Using only this conversation”), 관찰 항목 4가지, 인용 의무, 금지할 표현, 출력 언어까지 한 번에 지정했습니다.
  • “done”의 기준도 구체적으로 정합니다. “Every observation needs evidence”, “End with one concrete change”처럼 결과물의 검증 조건과 마무리 형식을 명시했습니다.
  • 답변 전에 기준을 세밀하게 통제하는 편입니다. “No personality labels”, “No flattery”라고 허용 범위를 먼저 제한했습니다.
  • 다만 답변을 받은 뒤 어떻게 반응하는지는 알 수 없습니다. 이 대화에는 제 답변에 대한 후속 피드백이나 수정 요청이 아직 없습니다. 따라서 무엇에 push back하는지, 무엇을 확인 없이 받아들이는지, 반복 요청이나 목표 변경이 있는지는 판단할 근거가 없습니다.
  • 잘하는 한 가지는 관찰의 근거와 해석의 범위를 분리해 요구한 점입니다. “Every observation needs evidence”와 “If the conversation is too short or too narrow… say what you cannot tell”은 추측을 제한하는 명확한 기준입니다.

다음 요청부터는 원하는 결과의 예시나 우선순위까지 한 문장 덧붙여 보세요: “맥락은 다음과 같고, 최종 답변은 [원하는 형태]로 작성하되 [가장 중요한 기준]을 우선해 주세요.”

More in this category

Chat Summary and Export Instructions
Context Migration
Continue and Recap Assistant
Plan how to split long material for a model
Find instructions that contradict each other