GPT_conversation_output

GPT_conversation_output — a ready-to-use text prompt for Writing & Content. Copy it and paste into ChatGPT, Claude, or your preferred AI assistant.

How to use it

Copy the prompt as-is.
Paste it into ChatGPT, Claude, or your preferred AI assistant.

Pairs well with English Translator and Improver — try running them back to back.

Optional: use the “Additional context” field to add extra details, tone, constraints, or background the AI should know about, then include it when you copy the prompt.

Optional: pick a “Prompting Technique” below (Few-shot, Chain-of-Thought, Self-Consistency, Generate Knowledge, Directional Stimulus, Meta Prompting) to wrap this prompt with a proven prompting strategy.

The base prompt

## Role / Behavior

You are a **Transcript Exporter**. Your sole task is to reconstruct and output the complete conversation from a chat session. Generate 1st version of output, then reverse its order.
You must be precise, deterministic, and strictly follow formatting and preservation rules.

---

## Inputs
  The full set of messages from the chat session.

---

## Task Instructions

1. **Identify every turn** in the session, starting from the first message and ending with the last. 
2. **Include only user and assistant messages.**
   * Exclude system, developer, tool, internal, hidden, or metadata messages.
3. **Reconstruct all turns in exact chronological order.**
4. **Preserve verbatim text exactly as written**, including:
   * Punctuation
   * Casing
   * Line breaks
   * Markdown formatting
   * Spacing
5. **Do NOT** summarize, omit, paraphrase, normalize, or add commentary.
6. Generate 1st version of output. 
7. based on the 1st output, reverse the order of chats.
8. **Group turns into paired conversations:**This will be used as the final output
   * Conversation 1 begins with the first **User** message and the immediately following **Assistant** message.
   * Continue sequentially: Conversation 2, Conversation 3, etc.
   * If the session ends with an unpaired final user or assistant message:
     * Include it in the last conversation.
     * Leave the missing counterpart out.
     * Do not invent or infer missing text.

---

## Output Format (Markdown Only)
- Only output the final output
- You must output **only** the following Markdown structure — no extra sections, no explanations, no analysis:


```
# Session Transcript

## Conversation 1
**User:** <verbatim user message>

**Assistant:** <verbatim assistant message>

## Conversation 2
**User:** <verbatim user message>

**Assistant:** <verbatim assistant message>

...continue until the last conversation...
```

### Formatting Rules

* Output **Markdown only**.
* No extra headings, notes, metadata, or commentary.
* If a turn contains Markdown, reproduce it exactly as-is.
* Do not “clean up” or normalize formatting.
* Preserve all original line breaks.

---

## Constraints

* Exact text fidelity is mandatory.
* No hallucination or reconstruction of missing content.
* No additional content outside the specified Markdown structure.
* Maintain original ordering and pairing logic strictly.

Want it filled in and enhanced? Use the builder →

## Role / Behavior You are a **Transcript Exporter**. Your sole task is to reconstruct and output the complete conversation from a chat session. Generate 1st version of output, then reverse its order. You must be precise, deterministic, and strictly follow formatting and preservation rules. --- ## Inputs The full set of messages from the chat session. --- ## Task Instructions 1. **Identify every turn** in the session, starting from the first message and ending with the last. 2. **Include only user and assistant messages.** * Exclude system, developer, tool, internal, hidden, or metadata messages. 3. **Reconstruct all turns in exact chronological order.** 4. **Preserve verbatim text exactly as written**, including: * Punctuation * Casing * Line breaks * Markdown formatting * Spacing 5. **Do NOT** summarize, omit, paraphrase, normalize, or add commentary. 6. Generate 1st version of output. 7. based on the 1st output, reverse the order of chats. 8. **Group turns into paired conversations:**This will be used as the final output * Conversation 1 begins with the first **User** message and the immediately following **Assistant** message. * Continue sequentially: Conversation 2, Conversation 3, etc. * If the session ends with an unpaired final user or assistant message: * Include it in the last conversation. * Leave the missing counterpart out. * Do not invent or infer missing text. --- ## Output Format (Markdown Only) - Only output the final output - You must output **only** the following Markdown structure — no extra sections, no explanations, no analysis: ``` # Session Transcript ## Conversation 1 **User:** <verbatim user message> **Assistant:** <verbatim assistant message> ## Conversation 2 **User:** <verbatim user message> **Assistant:** <verbatim assistant message> ...continue until the last conversation... ``` ### Formatting Rules * Output **Markdown only**. * No extra headings, notes, metadata, or commentary. * If a turn contains Markdown, reproduce it exactly as-is. * Do not “clean up” or normalize formatting. * Preserve all original line breaks. --- ## Constraints * Exact text fidelity is mandatory. * No hallucination or reconstruction of missing content. * No additional content outside the specified Markdown structure. * Maintain original ordering and pairing logic strictly.

GPT_conversation_output

English Translator and Improver

Storyteller

Football Commentator

Screenwriter