for paragraphs,

for section headers,

• for list items. No CSS classes, no inline styles, no
  , no
  . Preserve all original content word-for-word, no addition, removal, summarizing, rephrasing. We must parse the given job description text, which includes HTML tags with styles etc. We need to extract the content and reformat as per rules. We must keep all original content word-for-word. That means we cannot drop any text, but we can re-tag it. We must not add or remove any characters (except tags). Must preserve spaces? Probably preserve textual content exactly. We need to identify sections: The raw text includes many

  tags with styles, some empty. Also includes

  Responsibilities

  ,

  , then bold headings like Administration, etc. Also there is a Qualifications and Experience required then a

  list. Then later Skills, then list of skills separated by commas. Then Competencies then list of competencies each followed by
  etc. Then Education, then Closing Date, then italic bold statement, then The Old Mutual Story!. We need to convert section headers to

  . Which headings? Likely: Responsibilities, Administration, Correspondence, Document Preparation, Data Collection and Analysis, Insights and Reporting, Personal Capability Building, Operational Compliance, Qualifications and Experience required, Skills, Competencies, Education, Closing Date, maybe also the introductory paragraphs (Let's Write Africa's Story Together!, Old Mutual is a firm believer...). Also the statement about appointment and The Old Mutual Story! maybe as paragraphs. We must not add or remove content. So we need to keep all text exactly as appears, but we can change tags. We must not add any extra text like "Responsibilities:" etc. The original headings are already present as text within tags. For example,

  Responsibilities

  we need to change to

  Responsibilities

  . Similarly for other headings. But there are also headings like Administration etc. Those are bold tags, not heading tags. According to rules, we should use

  for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role). So we need to treat those bold headings as section headers and wrap them in

  . However we must preserve the text exactly: "Administration". So we change Administration to

  Administration

  . Similarly for Correspondence, Document Preparation, Data Collection and Analysis, Insights and Reporting, Personal Capability Building, Operational Compliance, Qualifications and Experience required, Skills, Competencies, Education, Closing Date. Also the introductory lines:

  Let's Write Africa's Story Together!

  etc. Those are not section headers per list, but they are introductory paragraphs. So we keep them as

  tags (without styles). We must strip the style and class attributes, but keep the text inside. So we convert to

  Let's Write Africa's Story Together!

  . Note the HTML entity ' should be preserved as is? The original text includes ' which is an apostrophe. We must preserve it exactly. So we keep '. Similarly the next paragraph:

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

  becomes

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

  (note trailing space before closing span; we should preserve spaces? Probably we keep the text exactly, but we can trim? The rule says preserve ALL original content word-for-word. So we must keep the trailing space before the closing . However after stripping tags, we need to keep that space inside the

  . So we should keep the space before the period? Actually the text: "Old Mutual is a firm believer in the African opportunity and our diverse talent reflects this. " includes a space after the period before the closing . So we need to keep that space. So

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

  . Similarly there may be leading/trailing spaces. We also have many empty
  tags. Those should be removed? They contain no content. If we preserve all content word-for-word, empty tags have no content, but they are tags. The instruction: "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". Does that apply to tags? We are to output only HTML, we can remove empty tags because they have no content? But they are part of original content. However the goal is to produce clean semantic HTML; likely we should discard empty paragraphs as they add no meaningful content. The instruction about preserving content likely refers to textual content, not meaningless empty tags. We'll remove empty

  tags. Similarly there are

  etc. We also have
  empty; we should remove. We have

  Administration

  etc. We'll convert Administration to

  Administration

  and remove the surrounding

  tags? The original had

  Administration

  . We need to preserve the text "Administration". We can output

  Administration

  . The surrounding

  tags are not needed; we can drop them as they are just wrappers. That's removing tags but not textual content. Likely acceptable. Similarly for each bold heading. Now the list under Qualifications and Experience required: we have

  • Completed Matric

  etc. We need to convert to
  • Completed Matric
  preserving spaces inside. The and

  inside li should be stripped, but keep the text. So we will output

  • Completed Matric
  • Tertiary Qualification would be advantageous
  • Minimum of 3 years’ experience in a similar role
  . Note the apostrophe in years’ is a special unicode right single quotation mark? It appears as ’ (U+2019). We must preserve that. Now Skills: after Skills we have a paragraph of text: "Accounting, Action Planning, Budget Management, Calendar Coordination, Computer Literacy, Data Analysis, Database Reporting, Data Compilation, Data Interpretations, Executing Plans, Financial Acumen, Management Reporting, Numerical Aptitude, Oral Communications, Report Review". This is not a list; it's a sentence/comma-separated list. According to rules, we should use
  • for list items (duties, requirements, qualifications, skills). So we need to split into list items? The instruction: "Use
    • for list items (duties, requirements, qualifications, skills)". It implies if the original content is a list, we should wrap each item in
    • . The original skills are presented as a comma-separated list, not as
    • . Should we convert to
      • each skill? The rule says preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase. If we split the comma-separated string into separate
      • items, we are adding structure but not changing the textual content? We would be adding
      • tags and removing commas? Actually we would keep the text of each skill, but we would remove the commas and maybe the spaces. That would be removing characters (commas). That would violate "do not add, remove". So we should not alter the text. Instead we should keep the skills paragraph as a

        containing the exact same text. However the rule says use

        • for list items. But if the original is not marked as list items, we might keep as

          . The instruction: "Use

          • for list items (duties, requirements, qualifications, skills)". It suggests that if the content is a list, we should use
            • . But we must not change the wording. The original skills are a list but not marked up. We could treat each comma-separated item as a list item, but we would need to remove commas. That would be removing content (commas). Not allowed. So we must keep as

              . However the rule may be interpreted as: if there are list items (like the qualifications already in

              • ), we should use that format. For skills, it's not a list in original, so we keep as

                . That seems safe. Similarly Competencies: after Competencies we have a series of lines: "Directs Work

                Drives Results
                Ensures Accountability
                Manages Complexity
                Optimizes Work Processes
                Plans and Aligns
                Tech Savvy
                maybe due to formatting. The text appears as: Directs Work
                Drives Results
                Ensures Accountability
                Manages Complexity
                Optimizes Work Processes
                Plans and Aligns
                Tech Savvy
                tags. We need to preserve the text exactly, but we can strip the empty tags. So we will output a paragraph containing the competencies text exactly as appears, but without the empty

                tags. However we must preserve the spacing and line breaks? The original had line breaks? It seems each competency on new line? In the raw text, after Competencies there is

                then the line "Directs Work

                Drives Results
                Ensures Accountability
                Manages Complexity
                Optimizes Work Processes
                Plans and Aligns
                Tech Savvy

                with that exact string but without the

                tags. However removing those tags is removing content (tags). But they are empty tags; removing them likely acceptable as they have no textual content. We'll keep the text between them. Thus the competencies paragraph will be: "Directs WorkDrives ResultsEnsures AccountabilityManages ComplexityOptimizes Work ProcessesPlans and AlignsTech Savvy". Wait we removed the
                but there is no space between them. The original had no spaces either: "Directs Work
                Drives Results". So after removing tags we get "Directs WorkDrives Results". That would concatenate without space. That might be undesirable but we must preserve original text exactly; the original text between "Work" and "Drives" is "
                " which is zero-length text. So removing them yields "Directs WorkDrives Results". That is exactly the original text if you consider the tags as not part of the textual content. The rule says preserve ALL original content word-for-word. The tags are not content? ambiguous. I'd argue we should keep the text as is, but we can drop empty tags because they contribute no visible content. The resulting string will have no space between Work and Drives, which may be wrong but matches the original if you ignore the tags. However the original likely intended a space or newline. But we cannot add a space. So we keep as is. Similarly after each competency there are two empty h3 tags. So final string: "Directs WorkDrives ResultsEnsures AccountabilityManages ComplexityOptimizes Work ProcessesPlans and AlignsTech Savvy". No spaces between items. That seems odd but we follow rule. Alternatively we could keep the empty h3 tags as they are, but we are not allowed to use

                per rules (only h4 for section headers). So we must not output

                . So we must remove them. We'll output the text as is. Now Education: after Education we have text: "NQF Level 4 - Grade 12, School leaving Certificate, National or Occupational Certificate or equivalent". Note there are double spaces after comma? We'll preserve. Closing Date: after Closing Date we have "19 August 2026 , 23:59". Note space before comma. Then italic bold statement:

                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.

                . We need to convert to

                ...

                ? But we cannot use or per rules? The rules only specify using

                ,

                ,

                • . It doesn't forbid other tags, but says "Use

                  for introductory paragraphs and general text. Use

                  for section headers ... Use

                  • for list items". It doesn't say we cannot use other tags like or . However to keep clean semantic HTML, we might want to avoid inline styling tags. But the rule didn't forbid them. It only said no CSS classes, no inline styles, no
                    s, no
                    tags. It didn't forbid or . However we might want to preserve the emphasis. The original had ... . We could keep them as is, but they are not

                    ,

                    ,

                    • . The rule says "Use

                      for introductory paragraphs and general text". This statement is general text, so we could wrap it in

                      and drop the tags, but that would remove emphasis (tags). However the rule says preserve ALL original content word-for-word. Removing would be removing tags, which is altering content. So we should keep them. However the rule also says "Use

                      for introductory paragraphs and general text". That could be interpreted as we should use

                      for those paragraphs, but we can also have other tags inside? It doesn't say we cannot. So we can keep inside

                      . That satisfies using

                      for the paragraph, and we keep the emphasis tags. Similarly the final line:

                      The Old Mutual Story!

                      . We need to convert to

                      The Old Mutual Story!

                      but we cannot have class or style. So we must strip class and style attributes, but keep the text and the tags. The span with class emphasis-2 must be removed (no classes). So we will have

                      The Old Mutual Story!

                      . However we must preserve the text exactly: "The Old Mutual Story!". The original had The Old Mutual Story!. Removing the span removes the class attribute but keeps the . That's altering content (removing a tag). But the span had only a class attribute, no textual content. Removing it is removing a tag with no textual content, similar to empty tags. Likely acceptable. Thus final HTML will consist of a series of

                      and

                      and

                      • etc. We need to ensure we output only HTML, no markdown fences. Let's construct step by step. Introductory paragraphs: 1.

                        Let's Write Africa's Story Together!

                        2.

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

                        (note trailing space) Then we have empty paragraphs; we skip. Then the line: "This role is responsible for capturing, checking, loading and verifying of Fund prices and MM yields that feed various Product Administration Systems including BaNCS. Shift work is required in the role." This appears after some empty p tags. It is not wrapped in any tag in the raw? Actually it's plain text after the empty p tags. So we need to wrap it in

                        . So:

                        This role is responsible for capturing, checking, loading and verifying of Fund prices and MM yields that feed various Product Administration Systems including BaNCS. Shift work is required in the role.

                        Then we have

                        Responsibilities

                        followed by
                        . We'll convert h1 to

  Translated by AI — may not be perfect

  Show original