Coding
details of the given bug
Extracts the feature or system, expected behavior, and actual behavior or issue from raw text, returning them in three fields. Use it to structure messy bug reports, logs, chats, or code comments.
- Tested with:
- GPT-4o
- Effectiveness:
- 95/100
- Prompt archive
English version
Act as a senior software analyst.
## Goal
From the given input text, extract and structure the following three elements:
1. describ_feature → What feature or system is being discussed
2. what_should_happen → Expected behavior
3. what_is_happen → Actual behavior / issue
---
## Input
${paste_any_raw_text_here}
- Could be messy
- Could include logs, chat, code comments, or mixed explanations
---
## Instructions
- Read the entire input carefully
- Infer missing context when reasonably possible
- Do NOT hallucinate unclear details
- If something is missing, return "UNCLEAR"
---
## Extraction Rules
### 1. describ_feature
- Summarize the feature/system in 1–2 lines
- Focus on purpose, not implementation details
### 2. what_should_happen
- Describe ideal/expected behavior
- Include conditions if mentioned
### 3. what_is_happen
- Describe actual issue or incorrect behavior
- Be precise and factual
- Include errors, unexpected results, or failures
---
## Output Format (STRICT)
## Output Format (STRICT)
Return ONLY this points: "describ_feature": "...",
"what_should_happen": "...",
"what_is_happen": "..."
---
## Constraints
- No extra text
- No explanations
- No assumptions beyond reasonable inference
- Keep each field concise but completeFill in and run
This prompt has 1 blanks. Fill them in and we will assemble the finished prompt for you.
1 still empty
Finished prompt
Act as a senior software analyst.
## Goal
From the given input text, extract and structure the following three elements:
1. describ_feature → What feature or system is being discussed
2. what_should_happen → Expected behavior
3. what_is_happen → Actual behavior / issue
---
## Input
${paste_any_raw_text_here}
- Could be messy
- Could include logs, chat, code comments, or mixed explanations
---
## Instructions
- Read the entire input carefully
- Infer missing context when reasonably possible
- Do NOT hallucinate unclear details
- If something is missing, return "UNCLEAR"
---
## Extraction Rules
### 1. describ_feature
- Summarize the feature/system in 1–2 lines
- Focus on purpose, not implementation details
### 2. what_should_happen
- Describe ideal/expected behavior
- Include conditions if mentioned
### 3. what_is_happen
- Describe actual issue or incorrect behavior
- Be precise and factual
- Include errors, unexpected results, or failures
---
## Output Format (STRICT)
## Output Format (STRICT)
Return ONLY this points: "describ_feature": "...",
"what_should_happen": "...",
"what_is_happen": "..."
---
## Constraints
- No extra text
- No explanations
- No assumptions beyond reasonable inference
- Keep each field concise but complete- Open in ChatGPT (opens in a new tab)
- Open in Claude (opens in a new tab)
- Open in Gemini (opens in a new tab)
Gemini cannot receive the prompt through a link, so copy it first.
- Open in Perplexity (opens in a new tab)
Opens in a new tab with the prompt already typed in. You may need to be signed in.
How to use this prompt
- Replace anything in square brackets with your own details before sending.
- Results differ between models. If the output misses the mark, try another model or add one concrete example.
- Keep the prompt in one message. Splitting it across turns weakens the instructions.