{
  "model": "claude-3-5-sonnet-20241022",
  "max_tokens": 5000,
  "temperature": 1,
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text":  "Here is the resume you need to parse:\n\n<resume>\n{{resume}}\n</resume>\n\nYou are an advanced resume parsing system designed to extract key information from resumes and organize it into a structured JSON format. Your task is to analyze the above resume and create a JSON object containing the most relevant and insightful information.\n\nPlease follow these steps to complete the task:\n\n1. Carefully read through the entire resume.\n\n2. Extract the following information:\n   - First name\n   - Last name\n   - Location\n   - Email\n   - Phone Number\n   - Work experience\n   - School experience\n   - Skills\n\n3. For each category, focus on the most insightful and relevant information.\n\n4. Wrap the resume breakdown in <resume_analysis> tags:\n\n   - Quote the relevant sections for first name, last name, email, phone number, and location.\n   - For work experience, list out each entry with numbers, quoting relevant details for the company, position, duration, and key responsibilities. Note any achievements or quantifiable results.\n   - For school experience, list out each entry with numbers, quoting relevant details for institution, degree, field of study, and graduation year. Include any notable academic achievements.\n   - For skills, categorize them into technical skills, soft skills, and domain-specific skills, listing each skill.\n   - Identify any unique selling points or standout information in the resume.\n   - If any information is missing from the resume, explicitly state that it's not found.\n\n5. Organize the extracted information into a JSON object with the following structure:\n\n```json\n{\n  \"first_name\": \"String\",\n  \"last_name\": \"String\",\n  \"location\": \"String\",\n  \"email\": \"String\",\n  \"phone_number\": \"String\",\n  \"work_experience\": [\n    {\n      \"company\": \"String\",\n      \"position\": \"String\",\n      \"duration\": \"String\",\n      \"responsibilities\": [\"String\", \"String\"],\n      \"achievements\": [\"String\", \"String\"]\n    }\n  ],\n  \"school_experience\": [\n    {\n      \"institution\": \"String\",\n      \"degree\": \"String\",\n      \"field_of_study\": \"String\",\n      \"graduation_year\": \"Number\",\n      \"achievements\": [\"String\", \"String\"]\n    }\n  ],\n  \"skills\": {\n    \"technical\": [\"String\", \"String\"],\n    \"soft\": [\"String\", \"String\"],\n    \"domain_specific\": [\"String\", \"String\"]\n  },\n  \"unique_selling_points\": [\"String\", \"String\"]\n}\n```\n\nImportant: \n- Include all specified categories in the JSON output, even if the information is not found in the resume. \n- For missing information, use empty string values (\"\") or empty arrays ([]) as appropriate.\n- For work_experience and school_experience, if no entries are found, include an empty array.\n- For skills, if no skills are found in a category, include an empty array for that category.\n\nAfter the <resume_analysis> section, provide the final JSON output in <json_output> tags. Ensure that your JSON output follows the structure provided above, with actual data extracted from the resume or empty values for missing information."
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "type": "text",
          "text": "<resume_breakdown>"
        }
      ]
    }
  ]
}