Here's a thinking process: 1. **Analyze User Input:** - User is acting as a job listing editor. - I receive raw scraped text from a job website. - My job: extract ONLY actual job information, return clean, readable format. - Must REMOVE: social sharing text, author bylines, "you may also like", navigation, comments, ads/promotions, cookie/subscription notices, duplicate text, category labels not part of job, stray numbers/formatting artifacts. - Must KEEP and STRUCTURE: job title, company/organization, location, job description/responsibilities, requirements/qualifications, how to apply, salary (if mentioned), deadline/closing date, job ID/reference number, contract type/level. - Return ONLY the cleaned job text. No commentary, no headers like "Here is the cleaned version", no markdown formatting. Just the clean job listing text. Wait, the actual prompt I received has TWO parts: - First part: A set of instructions/rules for the task. - Second part: A "Job description" section with raw HTML text. Let me re-read carefully. The user message starts with: "You are a job listing editor..." and gives instructions. Then it says: "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." Then it gives rules for HTML formatting. Then it says: "Job description:" followed by a block of HTML text. Actually, looking at the structure: - The first block is system instructions/constraints. - The second block (after "Job description:") is the actual input data to process. The user wants me to take the raw job description text and output clean semantic HTML following the rules given. Let me extract the relevant job info from the provided text, remove all the junk, and format it as clean HTML using

,

,

• as specified. Let's analyze the raw text: ```

  Let's Write Africa's Story Together!

  Old Mutual is a firm believer in the African opportunity and our diverse talent reflects this.

  Job Description

  Provides advice on a specific range of products to a specific allocated market and are individually accountable for achieving results through their own efforts.

  Responsibilities

  Customer Service

  Carry out standard customer service activities and handle simple customer inquiries.

  Solutions Analysis

  Assess compliance with established standards and protocols for routine inquiries.

  Receiving Visitors

  Receive visitors and assist with various requests for information, referring more complex matters to colleagues.

  Customer Relationship Management (CRM) Data

  Ensure that basic customer details held in the system are accurate, and make notes of follow-up actions that have been promised, together with notes of actions taken during each sales call.

  Customer Needs Clarification

  Interview the customer, following a multilevel sales script, to clarify the customer's requirements.

  Customer Relationship Development / Prospecting

  Make calls (by telephone or in person) to allocated potential customers to develop relationships. Provide a first point of contact for resolving customer queries and complaints.

  Operational Compliance

  Follow a range of mandatory procedures to ensure that work is carried out to the required quality standards and/or to ensure adherence to external regulatory codes and internal codes of conduct.

  Business Development

  Carry out routine business development support tasks and assist others by following established procedures.

  Sales Opportunities Creation

  Identify potential customers by obtaining information, referrals, and recommendations from existing customers.

  Data Exploration

  Select appropriate data from information provided by others and input that data into spreadsheets or standard formats.

  Network of Influence

  Demonstrate understanding of the value of networking by participating in and contributing to a network of people, technologies, and ideas both inside and outside the company.

   

  na

  Skills

  Ability to Sell (Inactive), Communication, Company Policies, Credit Policies, Customer Centric Selling, Digital Savvy (Inactive), Interpersonal Relationship Management, Numeracy, Sales

  Competencies

  Balances Stakeholders
  Builds Networks
  Communicates Effectively
  Customer Focus
  Ensures Accountability
  Instills Trust
  Interpersonal Savvy
  Manages Complexity

  Education

  National Certification (Nat Cert) (Required)

  Closing Date

  08 October 2026 , 23:59

  The appointment will be made from the designated group in line with the Employment Equity Plan of Old Mutual South Africa and the specific business unit in question.

  The Old Mutual Story!

  ``` Now, I need to parse this and extract only the job information, removing: - All the inline style tags, span classes, b tags with HTML artifacts - Empty paragraphs - "Let's Write Africa's Story Together!" - seems like a tagline, probably remove or keep as company motto? The instructions say remove category labels that aren't part of the job, social sharing, author bylines, etc. This might be part of the company branding. I'll consider keeping it if it's part of the job ad header, but the instructions say remove things that aren't actual job info. I'll be careful. - "Old Mutual is a firm believer..." - company intro, keep? The instructions say keep company/organisation name. So keep the company name "Old Mutual", but maybe strip the surrounding fluff. - "Job Description" heading - keep as title? - The first paragraph "Provides advice on a specific range of products..." - this seems like a job summary or description. Keep. - Then Responsibilities section with h1/h2 headings and list items. - Skills section - Competencies section (with h3 headings that are empty) - Education section - Closing Date - Equity statement - "The Old Mutual Story!" - probably remove. Rules for HTML formatting: - Use

  for introductory paragraphs and general text - Use

  for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role) - Use

  • for list items (duties, requirements, qualifications, skills) - No CSS classes, no inline styles, no
    s, no
    tags - Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase - If text has no clear sections, just wrap paragraphs in

    tags - Return ONLY the HTML. No markdown fences, no explanation, no preamble. Important: "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". This is tricky because I need to remove HTML tags and formatting artifacts, but keep the text content exactly as is. So I need to strip all HTML tags, but keep the plain text words in order. However, the output must be clean semantic HTML using

    ,

    ,

    • . So I need to restructure the text into that HTML format, but ensure the textual content is preserved exactly word-for-word. That means I cannot change any words, but I can wrap them in the specified tags. Let me re-read: "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". This likely means the text content should be exactly the same, just formatted into the new HTML structure. So I need to extract the text from the raw HTML, maintaining order, and then wrap it appropriately. Also: "If text has no clear sections, just wrap paragraphs in

      tags". The text does have clear sections: Responsibilities, Skills, Competencies, Education, Closing Date. But the headings in the original are h1, h2, h3, bold text. The rules say use

      for section headers. So I need to map the sections to

      tags. But which sections? The instructions list: Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role. The raw text has: Responsibilities, Skills, Competencies, Education, Closing Date. Also there's an equity statement and "The Old Mutual Story!". I need to decide how to structure it. The rule says use

      for section headers e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role. So I should use

      for each section header. The raw text has "Responsibilities" as h1, then h2 sub-headings for each responsibility category. But the rule says use

      for section headers. I think I should output the main sections as

      , and the list items as

      • . However, "Preserve ALL original content word-for-word" means I cannot rephrase the responsibility descriptions. The raw text has each responsibility as a heading (h2) followed by a paragraph. I need to keep those exact paragraphs. Let me outline the text flow as I see it, stripping HTML tags but keeping text: Starting from the top: - "Let's Write Africa's Story Together!" - probably remove as it's a tagline, but it's part of the ad. The instructions say remove social sharing, author bylines, "you may also like", navigation, comments, ads/promotions, cookie notices, duplicate text, category labels that aren't part of the job. This might be considered ad copy. I'll remove it to be safe, or maybe keep it as it's part of the job ad. But the user says "extract ONLY the actual job information". I'll exclude it. - "Old Mutual is a firm believer in the African opportunity and our diverse talent reflects this." - company intro. Keep? It's about the company, could be kept as part of the job listing, but maybe it's not essential. The instructions say keep company/organisation name. I'll keep a cleaned version, but word-for-word preservation means I keep the exact text. I'll include it if it's part of the job ad, but maybe strip the HTML tags. - Empty paragraphs - remove. - "Job Description" - this is a heading. Keep as title? Could wrap in

        or

        . The rules say use

        for section headers. I'll maybe use

        Job Description

        or just include the text. But the raw text has it in bold. I'll keep the text "Job Description" as a paragraph or heading. - "Provides advice on a specific range of products to a specific allocated market and are individually accountable for achieving results through their own efforts." - this seems like a job summary or the first paragraph of the description. Keep. - Then Responsibilities section: headings and paragraphs. - Skills section. - Competencies section. - Education section. - Closing Date. - Equity statement. - "The Old Mutual Story!" - remove. Now, the tricky part: "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". This means I must not change any text. So if a paragraph says "Carry out standard customer service activities and handle simple customer inquiries.", I must keep exactly that. I just need to wrap it in appropriate HTML tags. The output format: clean semantic HTML using

        ,

        ,

        • . No
          , no
          , no inline styles, no classes. How to handle the sections? The raw text has: -

          Responsibilities

          - Then multiple

          Customer Service

          ,

          Solutions Analysis

          , etc., each followed by a

          with text. - Skills followed by a list of competencies separated by commas. - Competencies followed by

          headings (empty) and then text lines like "Balances Stakeholders", "Builds Networks", etc. - Education followed by "National Certification (Nat Cert) (Required)" - Closing Date followed by "08 October 2026 , 23:59" - Then equity statement and "The Old Mutual Story!". I need to map these to

          sections and

          • lists where appropriate. But the rule says "Preserve ALL original content word-for-word". If I put things in
            • , the text of each li must be word-for-word the same as the original paragraphs/headings. However, the original has headings and paragraphs interleaved. I need to decide on a structure. Let's think about what the user likely expects. They gave rules for HTML formatting. They want me to take the raw text and output HTML that uses

              ,

              ,

              • . The content must be preserved exactly. So I should probably keep the textual content in the same order, but restructure the container tags. Possible approach: - Use

                for each main section header (Responsibilities, Skills, Competencies, Education, Closing Date). - For Responsibilities, the original has sub-headings (Customer Service, Solutions Analysis, etc.) each with a paragraph. I could keep them as

                under the

                Responsibilities, or as

                • with the heading and text combined. But the rule says use
                  • for list items (duties, requirements, qualifications, skills). The responsibilities are duties. So I could make them
                    • items, where each li contains the heading and the paragraph text, or just the paragraph text. But I must preserve word-for-word. If I combine heading and paragraph into one li, that's fine as long as the text is exact. However, the original has the heading as an h2 and the paragraph as a p. If I put them in an li, I need to decide the exact text. The instruction says "do not add, remove, summarise, or rephrase". So I cannot change the order or content. I could output the h2 text and the p text as separate elements, but within the li? That might be overcomplicating. Maybe the simplest is to keep the responsibilities as

                      paragraphs under an

                      Responsibilities, since the rule says "Use

                      for introductory paragraphs and general text" and "Use

                      for section headers". It doesn't strictly force

                      • for everything, but says "Use
                        • for list items (duties, requirements, qualifications, skills)". So for duties/requirements that are listed as bullet points originally, I should use
                          • . But in the raw text, responsibilities are not bullet points; they are headings with paragraphs. I could convert them to
                            • by making each duty an li, but I need to include the duty name and description. The original duty name is the h2, and the description is the p. I could combine them into one li text, e.g., "Customer Service Carry out standard customer service activities and handle simple customer inquiries." But that changes the structure. Alternatively, I could keep the headings as

                              or

                              and the descriptions as

                              . The rule says "If text has no clear sections, just wrap paragraphs in

                              tags". The text does

    Translated by AI — may not be perfect

    Show original