You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** based on predefined categories and return structured JSON data for easier post-processing. --- Select up to 3 topics that are most relevant to the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development", "Programming"] The first topic should be the most dominant in the prompt. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, set the remaining topics to None. 2. Language Style "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Type of Instruction Given to Assistant Choose one category that best describes what the user is asking the assistant to do. Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Code Generation -> User asks for generation of code, code refinements, or code summarization. Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Output Format Return structured JSON output in this format: { "topic": ["Art", "Healthcare", None], "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze the prompt Select the 3 most relevant topics, ordered by prominence in the conversation. If there are empty slots fill them with None Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, analyze the following prompt: {prompt}

You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** based on predefined categories and return structured JSON data for easier post-processing. --- Select up to 3 topics that are most relevant to the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development", "Programming"] The first topic should be the most dominant in the prompt. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, set the remaining topics to None. 2. Language Style "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Type of Instruction Given to Assistant Choose one category that best describes what the user is asking the assistant to do. Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Code Generation -> User asks for generation of code, code refinements, or code summarization. Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Output Format Return structured JSON output in this format: { "topic": "Art", "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze the prompt Select the 3 most relevant topics, ordered by prominence in the conversation. If there are empty slots fill them with None Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, analyze the following prompt: {prompt}

You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** based on predefined categories and return structured JSON data for easier post-processing. --- Select up to 3 topics that are most relevant to the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the prompt. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, set the remaining topics to None. 2. Language Style "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Type of Instruction Given to Assistant Choose one category that best describes what the user is asking the assistant to do. Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Output Format Return structured JSON output in this format: { "topic": "Art", "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze the prompt Select the 3 most relevant topics, ordered by prominence in the conversation. If there are empty slots fill them with None Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, analyze the following prompt: {prompt}

You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** based on predefined categories and return structured JSON data for easier post-processing. --- Select up to 3 topics that are most relevant to the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the prompt. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, set the remaining topics to None. 2. Language Style "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Type of Instruction Given to Assistant Choose one category that best describes what the user is asking the assistant to do. Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Output Format Return structured JSON output in this format: { "topic": "Art", "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze the prompt Select the 3 most relevant topics, ordered by prominence in the conversation. If there are empty slots fill them with None Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, analyze the following prompt: {prompt}

You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** based on predefined categories and return structured JSON data for easier post-processing. --- Select up to 3 topics that are most relevant to the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the prompt. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, set the remaining topics to None. 2. Language Style "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Type of Instruction Given to Assistant Choose one category that best describes what the user is asking the assistant to do. Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Output Format Return structured JSON output in this format: { "topic": "Art", "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze the prompt Select up to 3 most relevant topics, ordered by prominence in the conversation. Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, analyze the following prompt: {prompt}

You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** based on predefined categories and return structured JSON data for easier post-processing. --- Select up to 3 topics that are most relevant to the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the prompt. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2. Language Style "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Type of Instruction Given to Assistant Choose one category that best describes what the user is asking the assistant to do. Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Output Format Return structured JSON output in this format: { "topic": "Art", "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze the prompt Select up to 3 most relevant topics, ordered by prominence in the conversation. Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, analyze the following prompt: {prompt}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1. Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2. Language Style of the Prompt "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5. Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6. Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7. Type of Instruction Given to Assistant Choose one of the following categories: Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Example: "Create a t-shirt design about animal rights." Example: "Write a short sci-fi story." Example: "Generate ideas for a marketing slogan." Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Example: "What are the top 5 largest animal rights organizations?" Example: "Give me statistics on deforestation and animal extinction." Example: "Compare the environmental impact of cotton vs. synthetic fabrics." Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Example: "What’s your opinion on using synthetic leather?" Example: "Do you think my t-shirt design idea is effective?" Example: "What’s the best way to convince people to care about animal rights?" Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Example: "Summarize the key points from this discussion." Example: "Improve my t-shirt design by making it more dynamic." Example: "Make my speech more persuasive." Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Example: "What do you think about animal welfare?" Example: "Tell me something interesting about t-shirts!" Example: "Let’s chat about animal rights history." Output Format Return a structured JSON object as follows: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions Select up to 3 most relevant topics, ordered by prominence in the conversation. Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1. Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2. Language Style of the Prompt "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5. Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6. Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7. Type of Instruction Given to Assistant Choose one of the following categories: Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Example: "Create a t-shirt design about animal rights." Example: "Write a short sci-fi story." Example: "Generate ideas for a marketing slogan." Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Example: "What are the top 5 largest animal rights organizations?" Example: "Give me statistics on deforestation and animal extinction." Example: "Compare the environmental impact of cotton vs. synthetic fabrics." Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Example: "What’s your opinion on using synthetic leather?" Example: "Do you think my t-shirt design idea is effective?" Example: "What’s the best way to convince people to care about animal rights?" Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Example: "Summarize the key points from this discussion." Example: "Improve my t-shirt design by making it more dynamic." Example: "Make my speech more persuasive." Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Example: "What do you think about animal welfare?" Example: "Tell me something interesting about t-shirts!" Example: "Let’s chat about animal rights history." Output Format Return a structured JSON object as follows: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions Select up to 3 most relevant topics, ordered by prominence in the conversation. Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, evaluate the following conversation: {messages}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] ``` Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1. Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2. Language Style of the Prompt "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5. Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6. Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7. Type of Instruction Given to Assistant Choose one of the following categories: Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Example: "Create a t-shirt design about animal rights." Example: "Write a short sci-fi story." Example: "Generate ideas for a marketing slogan." Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Example: "What are the top 5 largest animal rights organizations?" Example: "Give me statistics on deforestation and animal extinction." Example: "Compare the environmental impact of cotton vs. synthetic fabrics." Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Example: "What’s your opinion on using synthetic leather?" Example: "Do you think my t-shirt design idea is effective?" Example: "What’s the best way to convince people to care about animal rights?" Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Example: "Summarize the key points from this discussion." Example: "Improve my t-shirt design by making it more dynamic." Example: "Make my speech more persuasive." Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Example: "What do you think about animal welfare?" Example: "Tell me something interesting about t-shirts!" Example: "Let’s chat about animal rights history." Output Format Return a structured JSON object as follows: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions Select up to 3 most relevant topics, ordered by prominence in the conversation. Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, evaluate the following conversation: {messages}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] ``` Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1. Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2. Language Style of the Prompt "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5. Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6. Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7. Type of Instruction Given to Assistant Choose one of the following categories: Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Example: "Create a t-shirt design about animal rights." Example: "Write a short sci-fi story." Example: "Generate ideas for a marketing slogan." Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Example: "What are the top 5 largest animal rights organizations?" Example: "Give me statistics on deforestation and animal extinction." Example: "Compare the environmental impact of cotton vs. synthetic fabrics." Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Example: "What’s your opinion on using synthetic leather?" Example: "Do you think my t-shirt design idea is effective?" Example: "What’s the best way to convince people to care about animal rights?" Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Example: "Summarize the key points from this discussion." Example: "Improve my t-shirt design by making it more dynamic." Example: "Make my speech more persuasive." Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Example: "What do you think about animal welfare?" Example: "Tell me something interesting about t-shirts!" Example: "Let’s chat about animal rights history." Output Format Return a structured JSON object as follows: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions Select up to 3 most relevant topics, ordered by prominence in the conversation. Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, evaluate the following conversation: {messages}

You are an expert in NLP and topic classification. Your task is to analyze a **single user prompt** (plain text) and determine the **most relevant topics** based on predefined categories. Analyze the given **prompt only** and classify it into up to **three relevant topics**. --- ### **Topic Selection** Select **up to 3** topics that best describe the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] - The **first topic** should be the **most dominant** in the prompt. - The **second and third topics** should reflect **other significant themes** in the discussion. - If a prompt **only has one or two clear topics**, leave the remaining slots **empty**. - If **no relevant topic is found**, return `"None"`. --- ### **Output Format** Return structured JSON output in this format: ```json { "topics": ["Art", "Science", "Healthcare"] } Instructions Analyze only the provided prompt (do not infer from missing context). Select up to 3 topics in order of relevance. Ensure responses use only predefined topics for consistency in post-processing. If no relevant topic is found, return "None" instead of leaving the array empty. Do not add explanations—only return JSON. Now, analyze the following prompt (plain text input): {prompt}

You are an expert in NLP and topic classification. Your task is to analyze a **single user prompt** (plain text) and determine the **most relevant topics** based on predefined categories. Analyze the given **prompt only** and classify it into up to **three relevant topics**. --- ### **Topic Selection** Select **up to 3** topics that best describe the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] - The **first topic** should be the **most dominant** in the prompt. - The **second and third topics** should reflect **other significant themes** in the discussion. - If a prompt **only has one or two clear topics**, leave the remaining slots **empty**. - If **no relevant topic is found**, return `"None"`. --- ### **Output Format** Return structured JSON output in this format: ```json { "topics": ["Art", "Science", "Healthcare"] } Instructions Analyze only the provided prompt (do not infer from missing context). Select up to 3 topics in order of relevance. Ensure responses use only predefined topics for consistency in post-processing. If no relevant topic is found, return "None" instead of leaving the array empty. Do not add explanations—only return JSON. Now, analyze the following prompt (plain text input): {{prompt}}

You are an expert in NLP and topic classification. Your task is to analyze a **single user prompt** (plain text) and determine the **most relevant topics** based on predefined categories. --- ### **Input Format** You will receive a **single user prompt as a string** in the following format: "User's prompt goes here." This prompt consists of **normal text** where the user asks the assistant to perform a task. Analyze the given **prompt only** and classify it into up to **three relevant topics**. --- ### **1. Topic Selection** Select **up to 3** topics that best describe the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] - The **first topic** should be the **most dominant** in the prompt. - The **second and third topics** should reflect **other significant themes** in the discussion. - If a prompt **only has one or two clear topics**, leave the remaining slots **empty**. - If **no relevant topic is found**, return `"None"`. --- ### **Output Format** Return structured JSON output in this format: ```json { "topics": ["Art", "Science", "Healthcare"] } Instructions Analyze only the provided prompt (do not infer from missing context). Select up to 3 topics in order of relevance. Ensure responses use only predefined topics for consistency in post-processing. If no relevant topic is found, return "None" instead of leaving the array empty. Do not add explanations—only return JSON. Now, analyze the following prompt (plain text input): {{prompt}}

You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** (plain text input) based on predefined categories and return structured JSON data for easier post-processing. --- ### **Input Format** You will receive a **single user prompt as a string** in the following format: "User's prompt goes here." The prompt consists of **normal text**, where the user asks the assistant to perform a task. Analyze the given **prompt only** (do not consider any future conversation) and classify it according to the categories below. --- ### **1. Top 3 Topics** Select **up to 3** topics that are relevant to the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] - The **first topic** should be the **most dominant** in the prompt. - The **second and third topics** should reflect **other significant themes** in the discussion. - If a prompt **only has one or two clear topics**, leave the remaining slots **empty**. --- ### **2. Language Style** - **"Formal"** - **"Informal"** - **"Mixed"** --- ### **3. Grammar & Slang in User Input** - **"Perfect"** (No mistakes, professional style) - **"Minor Errors"** (Small grammar/spelling mistakes, but understandable) - **"Major Errors"** (Frequent grammar mistakes, difficult to read) - **"Contains Slang"** (Uses informal slang expressions) --- ### **4. Type of Instruction Given to Assistant** Choose **one** category that best describes what the user is asking the assistant to do. - **Content Generation** → User asks for creative content, including writing, design ideas, or brainstorming responses. - Example: `"Create a t-shirt design about animal rights."` - Example: `"Write a short sci-fi story."` - Example: `"Generate ideas for a marketing slogan."` - **Factual Inquiry** → User requests objective facts, statistics, or comparisons with clear, verifiable answers. - Example: `"What are the top 5 largest animal rights organizations?"` - Example: `"Give me statistics on deforestation and animal extinction."` - Example: `"Compare the environmental impact of cotton vs. synthetic fabrics."` - **Opinion-Seeking** → User explicitly asks for subjective input, recommendations, or an evaluative stance. - Example: `"What’s your opinion on using synthetic leather?"` - Example: `"Do you think my t-shirt design idea is effective?"` - Example: `"What’s the best way to convince people to care about animal rights?"` - **Task-Oriented** → User asks for structured assistance, edits, refinements, or summarization of existing content. - Example: `"Summarize the key points from this discussion."` - Example: `"Improve my t-shirt design by making it more dynamic."` - Example: `"Make my speech more persuasive."` - **Conversational Engagement** → User initiates casual, open-ended dialogue with no clear task or goal. - Example: `"What do you think about animal welfare?"` - Example: `"Tell me something interesting about t-shirts!"` - Example: `"Let’s chat about animal rights history."` --- ### **Output Format** Return structured **JSON output** in this format: ```json { "topics": ["Art", "Science", "Healthcare"], "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze only the provided prompt (do not infer from missing context). Ensure responses contain at least one topic (empty output is invalid). Select up to 3 most relevant topics, ordered by prominence. Use only predefined options for consistency. Do not add explanations—only return JSON. Now, analyze the following prompt (plain text input): {{prompt}}

You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** (plain text input) based on predefined categories and return structured JSON data for easier post-processing. --- ### **Input Format** You will receive a **single user prompt as a string** in the following format: "User's prompt goes here." The prompt consists of **normal text**, where the user asks the assistant to perform a task. Analyze the given **prompt only** (do not consider any future conversation) and classify it according to the categories below. --- ### **1. Top 3 Topics** Select **up to 3** topics that are relevant to the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] - The **first topic** should be the **most dominant** in the prompt. - The **second and third topics** should reflect **other significant themes** in the discussion. - If a prompt **only has one or two clear topics**, leave the remaining slots **empty**. --- ### **2. Language Style** - **"Formal"** - **"Informal"** - **"Mixed"** --- ### **3. Grammar & Slang in User Input** - **"Perfect"** (No mistakes, professional style) - **"Minor Errors"** (Small grammar/spelling mistakes, but understandable) - **"Major Errors"** (Frequent grammar mistakes, difficult to read) - **"Contains Slang"** (Uses informal slang expressions) --- ### **4. Type of Instruction Given to Assistant** Choose **one** category that best describes what the user is asking the assistant to do. - **Content Generation** → User asks for creative content, including writing, design ideas, or brainstorming responses. - Example: `"Create a t-shirt design about animal rights."` - Example: `"Write a short sci-fi story."` - Example: `"Generate ideas for a marketing slogan."` - **Factual Inquiry** → User requests objective facts, statistics, or comparisons with clear, verifiable answers. - Example: `"What are the top 5 largest animal rights organizations?"` - Example: `"Give me statistics on deforestation and animal extinction."` - Example: `"Compare the environmental impact of cotton vs. synthetic fabrics."` - **Opinion-Seeking** → User explicitly asks for subjective input, recommendations, or an evaluative stance. - Example: `"What’s your opinion on using synthetic leather?"` - Example: `"Do you think my t-shirt design idea is effective?"` - Example: `"What’s the best way to convince people to care about animal rights?"` - **Task-Oriented** → User asks for structured assistance, edits, refinements, or summarization of existing content. - Example: `"Summarize the key points from this discussion."` - Example: `"Improve my t-shirt design by making it more dynamic."` - Example: `"Make my speech more persuasive."` - **Conversational Engagement** → User initiates casual, open-ended dialogue with no clear task or goal. - Example: `"What do you think about animal welfare?"` - Example: `"Tell me something interesting about t-shirts!"` - Example: `"Let’s chat about animal rights history."` --- ### **Output Format** Return structured **JSON output** in this format: ```json { "topics": ["Art", "Science", "Healthcare"], "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze only the provided prompt (do not infer from missing context). Ensure responses contain at least one topic (empty output is invalid). Select up to 3 most relevant topics, ordered by prominence. Use only predefined options for consistency. Do not add explanations—only return JSON. Now, analyze the following prompt (plain text input): {{prompt}}

You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** (plain text input) based on predefined categories and return structured JSON data for easier post-processing. --- ### **Input Format** You will receive a **single user prompt as a string** in the following format: "User's prompt goes here." The prompt consists of **normal text**, where the user asks the assistant to perform a task. Analyze the given **prompt only** (do not consider any future conversation) and classify it according to the categories below. --- ### **1. Top 3 Topics** Select **up to 3** topics that are relevant to the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] - The **first topic** should be the **most dominant** in the prompt. - The **second and third topics** should reflect **other significant themes** in the discussion. - If a prompt **only has one or two clear topics**, leave the remaining slots **empty**. --- ### **2. Language Style** - **"Formal"** - **"Informal"** - **"Mixed"** --- ### **3. Grammar & Slang in User Input** - **"Perfect"** (No mistakes, professional style) - **"Minor Errors"** (Small grammar/spelling mistakes, but understandable) - **"Major Errors"** (Frequent grammar mistakes, difficult to read) - **"Contains Slang"** (Uses informal slang expressions) --- ### **4. Type of Instruction Given to Assistant** Choose **one** category that best describes what the user is asking the assistant to do. - **Content Generation** → User asks for creative content, including writing, design ideas, or brainstorming responses. - Example: `"Create a t-shirt design about animal rights."` - Example: `"Write a short sci-fi story."` - Example: `"Generate ideas for a marketing slogan."` - **Factual Inquiry** → User requests objective facts, statistics, or comparisons with clear, verifiable answers. - Example: `"What are the top 5 largest animal rights organizations?"` - Example: `"Give me statistics on deforestation and animal extinction."` - Example: `"Compare the environmental impact of cotton vs. synthetic fabrics."` - **Opinion-Seeking** → User explicitly asks for subjective input, recommendations, or an evaluative stance. - Example: `"What’s your opinion on using synthetic leather?"` - Example: `"Do you think my t-shirt design idea is effective?"` - Example: `"What’s the best way to convince people to care about animal rights?"` - **Task-Oriented** → User asks for structured assistance, edits, refinements, or summarization of existing content. - Example: `"Summarize the key points from this discussion."` - Example: `"Improve my t-shirt design by making it more dynamic."` - Example: `"Make my speech more persuasive."` - **Conversational Engagement** → User initiates casual, open-ended dialogue with no clear task or goal. - Example: `"What do you think about animal welfare?"` - Example: `"Tell me something interesting about t-shirts!"` - Example: `"Let’s chat about animal rights history."` --- ### **Output Format** Return structured **JSON output** in this format: ```json { "topics": ["Art", "Science", "Healthcare"], "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze only the provided prompt (do not infer from missing context). Ensure responses contain at least one topic (empty output is invalid). Select up to 3 most relevant topics, ordered by prominence. Use only predefined options for consistency. Do not add explanations—only return JSON. Now, analyze the following prompt (plain text input): {{prompt}}

You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** (plain text input) based on predefined categories and return structured JSON data for easier post-processing. --- ### **Input Format** You will receive a **single user prompt as a string** in the following format: "User's prompt goes here." The prompt consists of **normal text**, where the user asks the assistant to perform a task. Analyze the given **prompt only** (do not consider any future conversation) and classify it according to the categories below. --- ### **1. Top 3 Topics** Select **up to 3** topics that are relevant to the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] - The **first topic** should be the **most dominant** in the prompt. - The **second and third topics** should reflect **other significant themes** in the discussion. - If a prompt **only has one or two clear topics**, leave the remaining slots **empty**. --- ### **2. Language Style** - **"Formal"** - **"Informal"** - **"Mixed"** --- ### **3. Grammar & Slang in User Input** - **"Perfect"** (No mistakes, professional style) - **"Minor Errors"** (Small grammar/spelling mistakes, but understandable) - **"Major Errors"** (Frequent grammar mistakes, difficult to read) - **"Contains Slang"** (Uses informal slang expressions) --- ### **4. Type of Instruction Given to Assistant** Choose **one** category that best describes what the user is asking the assistant to do. - **Content Generation** → User asks for creative content, including writing, design ideas, or brainstorming responses. - Example: `"Create a t-shirt design about animal rights."` - Example: `"Write a short sci-fi story."` - Example: `"Generate ideas for a marketing slogan."` - **Factual Inquiry** → User requests objective facts, statistics, or comparisons with clear, verifiable answers. - Example: `"What are the top 5 largest animal rights organizations?"` - Example: `"Give me statistics on deforestation and animal extinction."` - Example: `"Compare the environmental impact of cotton vs. synthetic fabrics."` - **Opinion-Seeking** → User explicitly asks for subjective input, recommendations, or an evaluative stance. - Example: `"What’s your opinion on using synthetic leather?"` - Example: `"Do you think my t-shirt design idea is effective?"` - Example: `"What’s the best way to convince people to care about animal rights?"` - **Task-Oriented** → User asks for structured assistance, edits, refinements, or summarization of existing content. - Example: `"Summarize the key points from this discussion."` - Example: `"Improve my t-shirt design by making it more dynamic."` - Example: `"Make my speech more persuasive."` - **Conversational Engagement** → User initiates casual, open-ended dialogue with no clear task or goal. - Example: `"What do you think about animal welfare?"` - Example: `"Tell me something interesting about t-shirts!"` - Example: `"Let’s chat about animal rights history."` --- ### **Output Format** Return structured **JSON output** in this format: ```json { "topics": ["Art", "Science", "Healthcare"], "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze only the provided prompt (do not infer from missing context). Ensure responses contain at least one topic (empty output is invalid). Select up to 3 most relevant topics, ordered by prominence. Use only predefined options for consistency. Do not add explanations—only return JSON. Now, analyze the following prompt (plain text input): {{prompt}}

You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** based on predefined categories and return structured JSON data for easier post-processing. --- ### **Input Format** You will receive a **single user prompt**: Analyze the given prompt only and classify it according to the categories below. 1. Top 3 Topics Select up to 3 topics that are relevant to the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the prompt. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2. Language Style "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Type of Instruction Given to Assistant Choose one category that best describes what the user is asking the assistant to do. Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Example: "Create a t-shirt design about animal rights." Example: "Write a short sci-fi story." Example: "Generate ideas for a marketing slogan." Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Example: "What are the top 5 largest animal rights organizations?" Example: "Give me statistics on deforestation and animal extinction." Example: "Compare the environmental impact of cotton vs. synthetic fabrics." Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Example: "What’s your opinion on using synthetic leather?" Example: "Do you think my t-shirt design idea is effective?" Example: "What’s the best way to convince people to care about animal rights?" Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Example: "Summarize the key points from this discussion." Example: "Improve my t-shirt design by making it more dynamic." Example: "Make my speech more persuasive." Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Example: "What do you think about animal welfare?" Example: "Tell me something interesting about t-shirts!" Example: "Let’s chat about animal rights history." Output Format Return structured JSON output in this format: { "topic": ["Art", "Science", "Healthcare"], "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze the prompt Select up to 3 most relevant topics, ordered by prominence in the conversation. Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, analyze the following prompt: {{prompt}}

You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** based on predefined categories and return structured JSON data for easier post-processing. --- ### **Input Format** You will receive a **single user prompt**: Analyze the given prompt only and classify it according to the categories below. 1. Top 3 Topics Select up to 3 topics that are most relevant to the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the prompt. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2. Language Style "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Type of Instruction Given to Assistant Choose one category that best describes what the user is asking the assistant to do. Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Example: "Create a t-shirt design about animal rights." Example: "Write a short sci-fi story." Example: "Generate ideas for a marketing slogan." Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Example: "What are the top 5 largest animal rights organizations?" Example: "Give me statistics on deforestation and animal extinction." Example: "Compare the environmental impact of cotton vs. synthetic fabrics." Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Example: "What’s your opinion on using synthetic leather?" Example: "Do you think my t-shirt design idea is effective?" Example: "What’s the best way to convince people to care about animal rights?" Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Example: "Summarize the key points from this discussion." Example: "Improve my t-shirt design by making it more dynamic." Example: "Make my speech more persuasive." Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Example: "What do you think about animal welfare?" Example: "Tell me something interesting about t-shirts!" Example: "Let’s chat about animal rights history." Output Format Return structured JSON output in this format: { "topic": ["Art", "Science", "Healthcare"], "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze the prompt Select up to 3 most relevant topics, ordered by prominence in the conversation. Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, analyze the following prompt: {{prompt}}

You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** based on predefined categories and return structured JSON data for easier post-processing. --- ### **Input Format** You will receive a **single user prompt**: Analyze the given prompt only and classify it according to the categories below. 1. Top 3 Topics Select up to 3 topics that are most relevant to the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the prompt. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2. Language Style "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Type of Instruction Given to Assistant Choose one category that best describes what the user is asking the assistant to do. Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Example: "Create a t-shirt design about animal rights." Example: "Write a short sci-fi story." Example: "Generate ideas for a marketing slogan." Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Example: "What are the top 5 largest animal rights organizations?" Example: "Give me statistics on deforestation and animal extinction." Example: "Compare the environmental impact of cotton vs. synthetic fabrics." Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Example: "What’s your opinion on using synthetic leather?" Example: "Do you think my t-shirt design idea is effective?" Example: "What’s the best way to convince people to care about animal rights?" Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Example: "Summarize the key points from this discussion." Example: "Improve my t-shirt design by making it more dynamic." Example: "Make my speech more persuasive." Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Example: "What do you think about animal welfare?" Example: "Tell me something interesting about t-shirts!" Example: "Let’s chat about animal rights history." Output Format Return structured JSON output in this format: { "topic": "Art", "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze the prompt Select up to 3 most relevant topics, ordered by prominence in the conversation. Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, analyze the following prompt: {{prompt}}

You are an expert in NLP and prompt analysis. Your task is to evaluate a **single user prompt** based on predefined categories and return structured JSON data for easier post-processing. --- ### **Input Format** You will receive a **single user prompt**: Analyze the given prompt only and classify it according to the categories below. 1. Primary Topic (Single Choice) Select the most relevant topic from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] 2. Language Style "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Type of Instruction Given to Assistant Choose one category that best describes what the user is asking the assistant to do. Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Example: "Create a t-shirt design about animal rights." Example: "Write a short sci-fi story." Example: "Generate ideas for a marketing slogan." Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Example: "What are the top 5 largest animal rights organizations?" Example: "Give me statistics on deforestation and animal extinction." Example: "Compare the environmental impact of cotton vs. synthetic fabrics." Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Example: "What’s your opinion on using synthetic leather?" Example: "Do you think my t-shirt design idea is effective?" Example: "What’s the best way to convince people to care about animal rights?" Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Example: "Summarize the key points from this discussion." Example: "Improve my t-shirt design by making it more dynamic." Example: "Make my speech more persuasive." Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Example: "What do you think about animal welfare?" Example: "Tell me something interesting about t-shirts!" Example: "Let’s chat about animal rights history." Output Format Return structured JSON output in this format: { "topic": "Art", "language_style": "Formal", "grammar_slang": "Perfect", "instruction_type": "Content Generation" } Instructions Analyze only the first user message. Select only one topic (most relevant). Use only predefined options for consistency. Do not add explanations—only return JSON. Now, analyze the following prompt: {{prompt}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1. Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2. Language Style of the Prompt "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5. Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6. Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7. Type of Instruction Given to Assistant Choose one of the following categories: Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Example: "Create a t-shirt design about animal rights." Example: "Write a short sci-fi story." Example: "Generate ideas for a marketing slogan." Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Example: "What are the top 5 largest animal rights organizations?" Example: "Give me statistics on deforestation and animal extinction." Example: "Compare the environmental impact of cotton vs. synthetic fabrics." Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Example: "What’s your opinion on using synthetic leather?" Example: "Do you think my t-shirt design idea is effective?" Example: "What’s the best way to convince people to care about animal rights?" Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Example: "Summarize the key points from this discussion." Example: "Improve my t-shirt design by making it more dynamic." Example: "Make my speech more persuasive." Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Example: "What do you think about animal welfare?" Example: "Tell me something interesting about t-shirts!" Example: "Let’s chat about animal rights history." Output Format Return a structured JSON object as follows: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions Select up to 3 most relevant topics, ordered by prominence in the conversation. Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1. Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2. Language Style of the Prompt "Formal" "Informal" "Mixed" 3. Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4. Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5. Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6. Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7. Type of Instruction Given to Assistant Choose one of the following categories: Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses. Example: "Create a t-shirt design about animal rights." Example: "Write a short sci-fi story." Example: "Generate ideas for a marketing slogan." Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers. Example: "What are the top 5 largest animal rights organizations?" Example: "Give me statistics on deforestation and animal extinction." Example: "Compare the environmental impact of cotton vs. synthetic fabrics." Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance. Example: "What’s your opinion on using synthetic leather?" Example: "Do you think my t-shirt design idea is effective?" Example: "What’s the best way to convince people to care about animal rights?" Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content. Example: "Summarize the key points from this discussion." Example: "Improve my t-shirt design by making it more dynamic." Example: "Make my speech more persuasive." Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal. Example: "What do you think about animal welfare?" Example: "Tell me something interesting about t-shirts!" Example: "Let’s chat about animal rights history." Output Format Return a structured JSON object as follows: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions Select up to 3 most relevant topics, ordered by prominence in the conversation. Ensure responses use only predefined options for consistency in post-processing. Do not add explanations—only return JSON.

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions ✅ Select up to 3 most relevant topics, ordered by prominence in the conversation. ✅ Ensure responses use only predefined options for consistency in post-processing. ✅ Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions ✅ Select up to 3 most relevant topics, ordered by prominence in the conversation. ✅ Ensure responses use only predefined options for consistency in post-processing. ✅ Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions ✅ Select up to 3 most relevant topics, ordered by prominence in the conversation. ✅ If a conversation clearly belongs to only one or two topics, leave the extra slots blank. ✅ Avoid assuming "Healthcare" unless explicitly related to medical treatment, conditions, or policies. ✅ Science-related discussions should be labeled "Science" unless primarily about education, in which case "Education" should be prioritized. ✅ Ensure responses use only predefined options for consistency in post-processing. ✅ Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions ✅ Select up to 3 most relevant topics, ordered by prominence in the conversation. ✅ If a conversation clearly belongs to only one or two topics, leave the extra slots blank. ✅ Avoid assuming "Healthcare" unless explicitly related to medical treatment, conditions, or policies. ✅ Science-related discussions should be labeled "Science" unless primarily about education, in which case "Education" should be prioritized. ✅ Ensure responses use only predefined options for consistency in post-processing. ✅ Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions ✅ Select up to 3 most relevant topics, ordered by prominence in the conversation. ✅ If a conversation clearly belongs to only one or two topics, leave the extra slots blank. ✅ Avoid assuming "Healthcare" unless explicitly related to medical treatment, conditions, or policies. ✅ Science-related discussions should be labeled "Science" unless primarily about education, in which case "Education" should be prioritized. ✅ Ensure responses use only predefined options for consistency in post-processing. ✅ Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions ✅ Select up to 3 most relevant topics, ordered by prominence in the conversation. ✅ If a conversation clearly belongs to only one or two topics, leave the extra slots blank. ✅ Avoid assuming "Healthcare" unless explicitly related to medical treatment, conditions, or policies. ✅ Science-related discussions should be labeled "Science" unless primarily about education, in which case "Education" should be prioritized. ✅ Ensure responses use only predefined options for consistency in post-processing. ✅ Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions ✅ Select up to 3 most relevant topics, ordered by prominence in the conversation. ✅ If a conversation clearly belongs to only one or two topics, leave the extra slots blank. ✅ Avoid assuming "Healthcare" unless explicitly related to medical treatment, conditions, or policies. ✅ Science-related discussions should be labeled "Science" unless primarily about education, in which case "Education" should be prioritized. ✅ Ensure responses use only predefined options for consistency in post-processing. ✅ Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions ✅ Select up to 3 most relevant topics, ordered by prominence in the conversation. ✅ If a conversation clearly belongs to only one or two topics, leave the extra slots blank. ✅ Avoid assuming "Healthcare" unless explicitly related to medical treatment, conditions, or policies. ✅ Science-related discussions should be labeled "Science" unless primarily about education, in which case "Education" should be prioritized. ✅ Ensure responses use only predefined options for consistency in post-processing. ✅ Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions ✅ Select up to 3 most relevant topics, ordered by prominence in the conversation. ✅ If a conversation clearly belongs to only one or two topics, leave the extra slots blank. ✅ Avoid assuming "Healthcare" unless explicitly related to medical treatment, conditions, or policies. ✅ Science-related discussions should be labeled "Science" unless primarily about education, in which case "Education" should be prioritized. ✅ Ensure responses use only predefined options for consistency in post-processing. ✅ Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions ✅ Select up to 3 most relevant topics, ordered by prominence in the conversation. ✅ If a conversation clearly belongs to only one or two topics, leave the extra slots blank. ✅ Avoid assuming "Healthcare" unless explicitly related to medical treatment, conditions, or policies. ✅ Science-related discussions should be labeled "Science" unless primarily about education, in which case "Education" should be prioritized. ✅ Ensure responses use only predefined options for consistency in post-processing. ✅ Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions ✅ Select up to 3 most relevant topics, ordered by prominence in the conversation. ✅ If a conversation clearly belongs to only one or two topics, leave the extra slots blank. ✅ Avoid assuming "Healthcare" unless explicitly related to medical treatment, conditions, or policies. ✅ Science-related discussions should be labeled "Science" unless primarily about education, in which case "Education" should be prioritized. ✅ Ensure responses use only predefined options for consistency in post-processing. ✅ Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. --- ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Top 3 Topics Select up to 3 topics that are most relevant to the conversation from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] The first topic should be the most dominant in the conversation. The second and third topics should reflect other significant themes in the discussion. If a conversation only has one or two clear topics, leave the remaining slots empty. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topics": ["Education", "Science", "Ethics"], "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions ✅ Select up to 3 most relevant topics, ordered by prominence in the conversation. ✅ If a conversation clearly belongs to only one or two topics, leave the extra slots blank. ✅ Avoid assuming "Healthcare" unless explicitly related to medical treatment, conditions, or policies. ✅ Science-related discussions should be labeled "Science" unless primarily about education, in which case "Education" should be prioritized. ✅ Ensure responses use only predefined options for consistency in post-processing. ✅ Do not add explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Primary Topic Choose the most relevant topic from the following 20 options: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] If the conversation fits multiple topics, choose the most dominant one. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topic": "Healthcare", "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions Choose only from the predefined options for each category. Ensure consistency in responses for structured post-processing. Do not add additional explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Primary Topic Choose the most relevant topic from the following 20 options: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] If the conversation fits multiple topics, choose the most dominant one. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) 7️⃣ Type of Instruction Given to Assistant "Content Generation" (User asks for speech, story, or creative writing) "Factual Inquiry" (User requests objective facts, statistics, or comparisons) "Opinion-Seeking" (User asks for subjective opinions or recommendations) "Task-Oriented" (User asks for a structured task, e.g., "Summarize this") "Conversational Engagement" (Casual conversation, open-ended questions) Output Format Return a JSON object with the following structure: { "topic": "Healthcare", "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor", "instruction_type": "Factual Inquiry" } Instructions Choose only from the predefined options for each category. Ensure consistency in responses for structured post-processing. Do not add additional explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Primary Topic Choose the most relevant topic from the following 20 options: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] If the conversation fits multiple topics, choose the most dominant one. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) Output Format Return a JSON object with the following structure: { "topic": "Healthcare", "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor" } Instructions Choose only from the predefined options for each category. Ensure consistency in responses for structured post-processing. Do not add additional explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Primary Topic Choose the most relevant topic from the following 20 options: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] If the conversation fits multiple topics, choose the most dominant one. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) Output Format Return a JSON object with the following structure: { "topic": "Healthcare", "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor" } Instructions Choose only from the predefined options for each category. Ensure consistency in responses for structured post-processing. Do not add additional explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Primary Topic Choose the most relevant topic from the following 20 options: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] If the conversation fits multiple topics, choose the most dominant one. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) Output Format Return a JSON object with the following structure: { "topic": "Healthcare", "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor" } Instructions Choose only from the predefined options for each category. Ensure consistency in responses for structured post-processing. Do not add additional explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing. ### **Input Format** You will receive a conversation in the following format: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Categories Analyze the conversation and categorize it using the predefined values for each dimension. 1️⃣ Primary Topic Choose the most relevant topic from the following 20 options: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] If the conversation fits multiple topics, choose the most dominant one. 2️⃣ Language Style of the Prompt "Formal" "Informal" "Mixed" 3️⃣ Grammar & Slang in User Input "Perfect" (No mistakes, professional style) "Minor Errors" (Small grammar/spelling mistakes, but understandable) "Major Errors" (Frequent grammar mistakes, difficult to read) "Contains Slang" (Uses informal slang expressions) 4️⃣ Context Awareness "Excellent" (Understands multi-turn context well) "Good" (Mostly keeps context, with minor slips) "Average" (Some loss of context, but overall understandable) "Weak" (Frequently forgets context or contradicts previous responses) "None" (Does not retain context at all) 5️⃣ Logical Progression of Conversation "Strong" (Ideas build logically and naturally) "Moderate" (Mostly logical but with some jumps) "Weak" (Frequent topic shifts or unnatural flow) 6️⃣ Topic Shifts "None" (Stays on the same topic) "Minor" (Small, relevant diversions) "Major" (Significant change in topic mid-conversation) Output Format Return a JSON object with the following structure: { "topic": "Healthcare", "language_style": "Formal", "grammar_slang": "Perfect", "context_awareness": "Excellent", "logical_progression": "Strong", "topic_shifts": "Minor" } Instructions Choose only from the predefined options for each category. Ensure consistency in responses for structured post-processing. Do not add additional explanations—only return JSON. Now, evaluate the following conversation: {{messages}}

You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on multiple dimensions and provide a structured JSON response. ### **Input Conversation Format** You will receive a conversation consisting of multiple turns, where a user interacts with an assistant. The format will be: ```json [ {"content": "User message", "role": "user"}, {"content": "Assistant response", "role": "assistant"}, ... ] Evaluation Criteria Analyze the conversation based on the following dimensions: 1️⃣ Language Style How formal or informal is the assistant's response? Does the assistant maintain a consistent tone? Are there grammatical errors or awkward phrasing? 2️⃣ Topic Analysis What is the primary topic of the conversation? Is the topic broad (e.g., general knowledge) or niche (e.g., technical or specialized)? Does the conversation include diverse perspectives or focus on a single viewpoint? 3️⃣ Depth of Questions & Response Expansion Does the user ask follow-up questions that deepen the discussion? Does the assistant provide elaborative responses, or are they repetitive? Are different subtopics explored within the same discussion? 4️⃣ Conversational Flow & Coherence Does the conversation follow a logical progression? Are responses contextually aware of previous turns? Are there any abrupt topic shifts? 5️⃣ Type of Instruction Given to the Assistant Is the assistant primarily asked to generate content (e.g., speeches, explanations)? Is the user seeking factual information or opinions? Are the instructions open-ended (e.g., “Tell me more”) or specific (e.g., “Give me statistics”)? 6️⃣ Bias & Objectivity Does the assistant provide neutral and fact-based responses? Are there any signs of bias (e.g., strong opinions, one-sided arguments)? Does the assistant fairly represent different perspectives where applicable? 7️⃣ Engagement & Persuasiveness Does the assistant engage the user effectively? Are the responses persuasive and compelling? Does the conversation maintain user interest, or does it feel dry and mechanical? Output Format Return a structured JSON object with ratings and insights for each dimension. Example: { "language_style": { "rating": 4.5, "comments": "The assistant maintains a formal and persuasive tone, appropriate for the given prompts." }, "topic_analysis": { "topic": "Healthcare (Dental Care)", "breadth": "Moderate", "comments": "The conversation remains focused on dental care, with some expansion into healthcare policies in different countries." }, "depth_of_questions": { "rating": 4.2, "comments": "The user consistently asks follow-up questions, leading to deeper discussion and topic exploration." }, "conversational_flow": { "rating": 4.8, "comments": "The responses maintain coherence and build upon previous turns effectively." }, "instruction_type": { "type": "Informational and Content Generation", "comments": "The user requests speeches, statistics, and comparisons, indicating a mix of factual inquiries and content creation." }, "bias_objectivity": { "rating": 4.7, "comments": "The assistant presents factual information but does not explore opposing viewpoints in-depth." }, "engagement_persuasiveness": { "rating": 4.3, "comments": "The assistant provides compelling and well-structured responses, though some sections could be more engaging." } } Instructions Provide a numerical rating (1-5) for dimensions that allow rating. Keep comments concise but insightful. Ensure the response follows the exact JSON structure. Now, evaluate the following conversation: {{messages}}