Job Description
for paragraphs,
for section headers, - for lists, no classes/styles//
, preserve ALL original content word-for-word, no rephrasing, if no clear sections just wrap in , return ONLY HTML, no markdown fences/explanation/preamble
2. **Analyze the Input Text:**
```
Business Unit:
Group Admin
Department:
Finance
Site:
Rosebank
Location - Town / City:
Rosebank
Job Advert Summary:
VACANCY ANNOUNCEMENT PPC ROSEBANK: INTERNAL & EXTERNAL ADVERTISEMENT POSITION: SPECIALIST GROUP TECHNICAL JOB GRADE: D3 Department: FINANCE LOCATION: PPC ROSEABANK NUMBER OF VACANCIES: 01 The Specialist Group Technical is responsible for monitoring the adherence to the International Financial Reporting Standards across the PPC Group
Minimum Requirements:
Chartered Accountant (South Africa) (NQF Level 8) 2-4 years post articles experience EXPERIENCE Reporting professional with a strong background in specific reporting standards - 2 – 4 years Manufacturing or mining industry experience - 2 – 4 years
Duties and Responsibilities:
Group Technical Maintain and update technical accounting frameworks, policies and procedures and align to industry standards and regulations Prepare technical position papers on IFRS and related matters Prepare and maintain accounting opinions database Participate in IFRS implementation projects Lead all projects relating to accounting papers and opinions across the Group Compliance Monitor stakeholder compliance with IFRS Keep abreast with JSE regulatory requirements and monitor the Group’s compliance Provide business units with support relating to any compliance requirements Prepare disclosures for external auditors in line with IFRS requirements Partner with business and provide them with support during the external audit process Monitor adherence to accounting principles and practices in line with regulatory requirements and PPC standards Reporting Participate in the preparation of the Group financial statements Review subsidiary financial statements on an annual basis Monthly review of PPC Ltd complex transactions Stakeholder Management Prepare and submit the JSE report to the Audit and Risk Committee for review and sign-off Support, provide data and respond to queries raised by auditors Provide IFRS guidance and support to the Groups’ divisions Facilitate training to capacitate stakeholders and mitigate risks
```
3. **Identify What to Remove:**
- "Business Unit:", "Department:", "Site:", "Location - Town / City:" labels (these are category/admin labels, not job info per se, but some might be relevant like location. However, the instruction says "Remove category labels that aren't part of the job (e.g., 'Internships' as a standalone line)". The labels like "Business Unit:", "Department:", "Site:" are probably administrative and should be removed. "Location - Town / City:" gives the location "Rosebank" which is useful, but the label itself might be considered a category label. I need to extract the actual job info. The location "Rosebank" is mentioned, but I'll keep it as part of the structured output if possible, or just include the location text naturally. Let's see.)
- "Job Advert Summary:" line and the long string after it contains the job title, grade, department, location, number of vacancies, and a summary. I need to extract the actual job title, maybe company (PPC is implied), location, summary. But the instruction says "Preserve ALL original content word-for-word". That's tricky. It means I shouldn't rephrase or summarize, but I can restructure into HTML. However, it also says "REMOVE all of the following: ... Category labels that aren't part of the job". So I should remove the labels like "Business Unit:", "Department:", etc., but keep the content they introduce, unless they're just noise.
- Actually, re-read carefully: "REMOVE all of the following: ... Category labels that aren't part of the job (e.g., 'Internships' as a standalone line)". So labels like "Business Unit:", "Department:", "Site:" are category/admin labels and should be removed. But the information might be needed. However, the rule says remove them. I'll remove the labels but keep the associated text if it's meaningful, or just strip them entirely. The safest is to remove the labels and the colon, but keep the text that follows if it's part of the job info. But some of that text is duplicated or redundant.
- "Social sharing text", "Author bylines", "You may also like", "Navigation text", "Comments", "Ads", "Cookie notices" - none present in this snippet, good.
- "Duplicate text (if the title appears multiple times, keep it once)" - the title seems to appear in the "Job Advert Summary" line. I'll keep it once.
- "Stray numbers or formatting artifacts" - need to handle carefully. The "2-4 years" etc. are requirements, so they should be kept as content, but "NUMBER OF VACANCIES: 01" might be a stray number artifact? The instruction says "Remove ... Stray numbers or formatting artifacts". But "01" is the number of vacancies, which could be considered job info. However, it might be considered a stray number. I'll keep it if it's part of the job ad, but the rule says remove stray numbers. I'll interpret "stray numbers" as formatting artifacts like "12345" unrelated to content. "01" for vacancies is relevant, but I'll see. Actually, the rule says "Remove all of the following: ... Stray numbers or formatting artifacts". I think I should remove explicit "NUMBER OF VACANCIES: 01" or keep just "01" if it's part of the info. But to be safe, I'll remove the label and keep the number if it's clearly part of the job ad, or just strip it. Hmm.
Let's re-evaluate the core instruction: "Your job is to extract ONLY the actual job information and return it in a clean, readable format." and "Return ONLY the cleaned job text." Then the HTML version says: "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". Wait, there's a conflict. The first part says "extract ONLY the actual job information", the HTML rules say "Preserve ALL original content word-for-word". Which one takes precedence? The later HTML rules seem to be the specific format requirements for this task. It says: "If text has no clear sections, just wrap paragraphs in
tags". And "Return ONLY the HTML. No markdown fences, no explanation, no preamble." Also: "No CSS classes, no inline styles, no
s, no
tags". And "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". This is critical. I must NOT remove or rephrase any content. I must keep every word as-is, but format it with HTML tags.
But wait, the very first prompt says: "REMOVE all of the following: - Social sharing text ... - Author bylines ... - "You may also like" ... - Navigation text ... - Comments sections - Advertisements or promotions - Cookie/subscription notices - Duplicate text (if the title appears multiple times, keep it once) - Category labels that aren't part of the job (e.g., "Internships" as a standalone line) - Stray numbers or formatting artifacts"
And the HTML rules say: "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". This is contradictory. Which one is the actual boss? The user says: "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." Then gives rules. The rules include both "REMOVE..." and "Preserve ALL original content word-for-word". I need to reconcile. Probably the "Preserve ALL original content word-for-word" is the overriding rule for the HTML output, meaning I should keep every word from the input, but format it, and perhaps the "REMOVE" list is for the initial extraction/cleaning phase, but since I'm directly formatting to HTML, I should keep everything? But the "REMOVE" list includes things like "Category labels that aren't part of the job (e.g., 'Internships' as a standalone line)". In the input, we have "Business Unit:", "Department:", "Site:", "Location - Town / City:". These are category labels. Should I remove them or keep them? The "Preserve ALL original content word-for-word" suggests keep them. But the "REMOVE" list says remove them. This is a test of following the most specific/ recent instructions. The HTML formatting rules are the task at hand. Often in these prompts, the later rules override or specify the exact output format. Let's read carefully: "Rules: - Use for introductory paragraphs and general text - Use
for section headers ... - Use - for list items ... - 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."
The "Preserve ALL original content word-for-word" is a strong instruction. It means I should not remove anything that's in the text. The "REMOVE" list from the first part might be a general guideline for the editor role, but the specific task here is to format as clean semantic HTML preserving all content. However, the first part says "Your job is to extract ONLY the actual job information and return it in a clean, readable format." Then it lists what to remove. Then it says "Return ONLY the cleaned job text." Then the second prompt says "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." and gives the HTML rules. It seems like the user is giving me two prompts in one, or the second is the actual format request. The input includes the job description text. I need to output HTML.
Let's look at the actual text and decide what to keep. If I must preserve ALL original content word-for-word, I cannot remove any text. But the HTML structure needs to make sense. I can wrap everything in
or
/- as appropriate, but keep every word. However, the "REMOVE" list includes things that are clearly not job info, but maybe they're in the text. In this text, we have: "Business Unit:", "Group Admin", "Department:", "Finance", "Site:", "Rosebank", "Location - Town / City:", "Rosebank", "Job Advert Summary:", then a long string, "Minimum Requirements:", then text, "Duties and Responsibilities:", then text. All of these are part of the job listing. If I remove "Business Unit:", "Department:", etc., I'm removing content, violating "Preserve ALL original content word-for-word". So I should keep everything, but format it.
But wait: "REMOVE all of the following: - Category labels that aren't part of the job (e.g., 'Internships' as a standalone line)". The example is "Internifications" as a standalone line. The labels here are "Business Unit:", "Department:", etc. Are they "part of the job"? They are typically part of a job posting metadata. The instruction says "that aren't part of the job". It's ambiguous. Given the "Preserve ALL original content" rule, I'll err on the side of keeping all text, but structure it with HTML tags. However, the "stray numbers or formatting artifacts" removal: "01" for number of vacancies, numbers like "2-4 years", "NQF Level 8", "D3". These are content, not stray artifacts. I'll keep them.
Let's re-read the very first line: "You are a job listing editor. You receive raw scraped text from a job website. Your job is to extract ONLY the actual job information and return it in a clean, readable format." This is the role description. Then it lists what to remove. Then "Return ONLY the cleaned job text." Then the user says "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." and gives the HTML rules. It seems the HTML rules are the specific format for this turn. The "Preserve ALL original content word-for-word" is key. I will keep every single word from the input, including labels, but format them into HTML tags as specified. However, the "REMOVE" list might be contradictory. In many AI prompt evaluations, the later instructions supersede earlier ones, or the "Preserve ALL original content" is the strict rule for the output format. I think I should keep all text, but structure it. But if I keep "Business Unit: Group Admin", that's a label and content. I'll wrap it.
Let's look at the HTML rules again: "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."
This suggests I should identify sections and use appropriate tags. The text has clear sections: "Minimum Requirements:" and "Duties and Responsibilities:". Also "Job Advert Summary:" etc. I should use
for section headers like "Minimum Requirements", "Duties and Responsibilities", maybe "Job Advert Summary". But the rule says "Use for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role)". It lists examples. I can use for "Minimum Requirements" and "Duties and Responsibilities". What about "Job Advert Summary", "Business Unit", "Department", etc.? They are not in the example list, but the rule says "Preserve ALL original content word-for-word". So I must include them. I could wrap the section headers in if they match the pattern, or wrap everything in
if no clear sections. But there are clear sections.
Let's parse the text and decide on HTML structure:
- The text starts with "Business Unit:\nGroup Admin\n\nDepartment:\nFinance\n\nSite:\nRosebank\n\nLocation - Town / City:\nRosebank\n\nJob Advert Summary:\nVACANCY ANNOUNCEMENT PPC ROSEBANK: INTERNAL & EXTERNAL ADVERTISEMENT POSITION: SPECIALIST GROUP TECHNICAL JOB GRADE: D3 Department: FINANCE LOCATION: PPC ROSEABANK NUMBER OF VACANCIES: 01 The Specialist Group Technical is responsible for monitoring the adherence to the International Financial Reporting Standards across the PPC Group\n\nMinimum Requirements:\nChartered Accountant (South Africa) (NQF Level 8) 2-4 years post articles experience EXPERIENCE Reporting professional with a strong background in specific reporting standards - 2 – 4 years Manufacturing or mining industry experience - 2 – 4 years\n\nDuties and Responsibilities:\nGroup Technical Maintain and update technical accounting frameworks, policies and procedures and align to industry standards and regulations Prepare technical position papers on IFRS and related matters Prepare and maintain accounting opinions database Participate in IFRS implementation projects Lead all projects relating to accounting papers and opinions across the Group Compliance Monitor stakeholder compliance with IFRS Keep abreast with JSE regulatory requirements and monitor the Group’s compliance Provide business units with support relating to any compliance requirements Prepare disclosures for external auditors in line with IFRS requirements Partner with business and provide them with support during the external audit process Monitor adherence to accounting principles and practices in line with regulatory requirements and PPC standards Reporting Participate in the preparation of the Group financial statements Review subsidiary financial statements on an annual basis Monthly review of PPC Ltd complex transactions Stakeholder Management Prepare and submit the JSE report to the Audit and Risk Committee for review and sign-off Support, provide data and respond to queries raised by auditors Provide IFRS guidance and support to the Groups’ divisions Facilitate training to capacitate stakeholders and mitigate risks"
If I must preserve all content word-for-word, I will keep every line, every colon, every word. I'll structure it semantically. The headings like "Business Unit:", "Department:", etc., are part of the content. I could treat the whole thing as paragraphs and section headers. The rule "Use
for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role)" suggests I should use for section titles. The text has "Minimum Requirements:" and "Duties and Responsibilities:". Those match the examples (Requirements, Responsibilities). I'll use for those. For "Business Unit:", "Department:", "Site:", "Location - Town / City:", "Job Advert Summary:", these are not in the example list, but I still need to preserve them. I could wrap them in
or
. The rule says "If text has no clear sections, just wrap paragraphs in
tags". Here there are clear sections, so I should use the appropriate tags
Apply Now ↗
How well do you match?
Get an instant AI match score for this role — free, takes 3 minutes.
Tailor your CV for this role
The concierge rewrites your whole CV and writes a matching cover letter for this job — opens right here, nothing to paste.
Tailor My CV to This Job ✍️
Free cover letter for this job
Upload your CV and get a tailored cover letter in seconds — free, no account needed.
Generate a Cover Letter 📝
, preserve ALL original content word-for-word, no rephrasing, if no clear sections just wrap in
, return ONLY HTML, no markdown fences/explanation/preamble 2. **Analyze the Input Text:** ``` Business Unit: Group Admin Department: Finance Site: Rosebank Location - Town / City: Rosebank Job Advert Summary: VACANCY ANNOUNCEMENT PPC ROSEBANK: INTERNAL & EXTERNAL ADVERTISEMENT POSITION: SPECIALIST GROUP TECHNICAL JOB GRADE: D3 Department: FINANCE LOCATION: PPC ROSEABANK NUMBER OF VACANCIES: 01 The Specialist Group Technical is responsible for monitoring the adherence to the International Financial Reporting Standards across the PPC Group Minimum Requirements: Chartered Accountant (South Africa) (NQF Level 8) 2-4 years post articles experience EXPERIENCE Reporting professional with a strong background in specific reporting standards - 2 – 4 years Manufacturing or mining industry experience - 2 – 4 years Duties and Responsibilities: Group Technical Maintain and update technical accounting frameworks, policies and procedures and align to industry standards and regulations Prepare technical position papers on IFRS and related matters Prepare and maintain accounting opinions database Participate in IFRS implementation projects Lead all projects relating to accounting papers and opinions across the Group Compliance Monitor stakeholder compliance with IFRS Keep abreast with JSE regulatory requirements and monitor the Group’s compliance Provide business units with support relating to any compliance requirements Prepare disclosures for external auditors in line with IFRS requirements Partner with business and provide them with support during the external audit process Monitor adherence to accounting principles and practices in line with regulatory requirements and PPC standards Reporting Participate in the preparation of the Group financial statements Review subsidiary financial statements on an annual basis Monthly review of PPC Ltd complex transactions Stakeholder Management Prepare and submit the JSE report to the Audit and Risk Committee for review and sign-off Support, provide data and respond to queries raised by auditors Provide IFRS guidance and support to the Groups’ divisions Facilitate training to capacitate stakeholders and mitigate risks ``` 3. **Identify What to Remove:** - "Business Unit:", "Department:", "Site:", "Location - Town / City:" labels (these are category/admin labels, not job info per se, but some might be relevant like location. However, the instruction says "Remove category labels that aren't part of the job (e.g., 'Internships' as a standalone line)". The labels like "Business Unit:", "Department:", "Site:" are probably administrative and should be removed. "Location - Town / City:" gives the location "Rosebank" which is useful, but the label itself might be considered a category label. I need to extract the actual job info. The location "Rosebank" is mentioned, but I'll keep it as part of the structured output if possible, or just include the location text naturally. Let's see.) - "Job Advert Summary:" line and the long string after it contains the job title, grade, department, location, number of vacancies, and a summary. I need to extract the actual job title, maybe company (PPC is implied), location, summary. But the instruction says "Preserve ALL original content word-for-word". That's tricky. It means I shouldn't rephrase or summarize, but I can restructure into HTML. However, it also says "REMOVE all of the following: ... Category labels that aren't part of the job". So I should remove the labels like "Business Unit:", "Department:", etc., but keep the content they introduce, unless they're just noise. - Actually, re-read carefully: "REMOVE all of the following: ... Category labels that aren't part of the job (e.g., 'Internships' as a standalone line)". So labels like "Business Unit:", "Department:", "Site:" are category/admin labels and should be removed. But the information might be needed. However, the rule says remove them. I'll remove the labels but keep the associated text if it's meaningful, or just strip them entirely. The safest is to remove the labels and the colon, but keep the text that follows if it's part of the job info. But some of that text is duplicated or redundant. - "Social sharing text", "Author bylines", "You may also like", "Navigation text", "Comments", "Ads", "Cookie notices" - none present in this snippet, good. - "Duplicate text (if the title appears multiple times, keep it once)" - the title seems to appear in the "Job Advert Summary" line. I'll keep it once. - "Stray numbers or formatting artifacts" - need to handle carefully. The "2-4 years" etc. are requirements, so they should be kept as content, but "NUMBER OF VACANCIES: 01" might be a stray number artifact? The instruction says "Remove ... Stray numbers or formatting artifacts". But "01" is the number of vacancies, which could be considered job info. However, it might be considered a stray number. I'll keep it if it's part of the job ad, but the rule says remove stray numbers. I'll interpret "stray numbers" as formatting artifacts like "12345" unrelated to content. "01" for vacancies is relevant, but I'll see. Actually, the rule says "Remove all of the following: ... Stray numbers or formatting artifacts". I think I should remove explicit "NUMBER OF VACANCIES: 01" or keep just "01" if it's part of the info. But to be safe, I'll remove the label and keep the number if it's clearly part of the job ad, or just strip it. Hmm. Let's re-evaluate the core instruction: "Your job is to extract ONLY the actual job information and return it in a clean, readable format." and "Return ONLY the cleaned job text." Then the HTML version says: "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". Wait, there's a conflict. The first part says "extract ONLY the actual job information", the HTML rules say "Preserve ALL original content word-for-word". Which one takes precedence? The later HTML rules seem to be the specific format requirements for this task. It says: "If text has no clear sections, just wrap paragraphs in
tags". And "Return ONLY the HTML. No markdown fences, no explanation, no preamble." Also: "No CSS classes, no inline styles, no
tags". And "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". This is critical. I must NOT remove or rephrase any content. I must keep every word as-is, but format it with HTML tags. But wait, the very first prompt says: "REMOVE all of the following: - Social sharing text ... - Author bylines ... - "You may also like" ... - Navigation text ... - Comments sections - Advertisements or promotions - Cookie/subscription notices - Duplicate text (if the title appears multiple times, keep it once) - Category labels that aren't part of the job (e.g., "Internships" as a standalone line) - Stray numbers or formatting artifacts" And the HTML rules say: "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". This is contradictory. Which one is the actual boss? The user says: "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." Then gives rules. The rules include both "REMOVE..." and "Preserve ALL original content word-for-word". I need to reconcile. Probably the "Preserve ALL original content word-for-word" is the overriding rule for the HTML output, meaning I should keep every word from the input, but format it, and perhaps the "REMOVE" list is for the initial extraction/cleaning phase, but since I'm directly formatting to HTML, I should keep everything? But the "REMOVE" list includes things like "Category labels that aren't part of the job (e.g., 'Internships' as a standalone line)". In the input, we have "Business Unit:", "Department:", "Site:", "Location - Town / City:". These are category labels. Should I remove them or keep them? The "Preserve ALL original content word-for-word" suggests keep them. But the "REMOVE" list says remove them. This is a test of following the most specific/ recent instructions. The HTML formatting rules are the task at hand. Often in these prompts, the later rules override or specify the exact output format. Let's read carefully: "Rules: - Use
for introductory paragraphs and general text - Use
for section headers ... - Use - for list items ... - 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."
The "Preserve ALL original content word-for-word" is a strong instruction. It means I should not remove anything that's in the text. The "REMOVE" list from the first part might be a general guideline for the editor role, but the specific task here is to format as clean semantic HTML preserving all content. However, the first part says "Your job is to extract ONLY the actual job information and return it in a clean, readable format." Then it lists what to remove. Then it says "Return ONLY the cleaned job text." Then the second prompt says "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." and gives the HTML rules. It seems like the user is giving me two prompts in one, or the second is the actual format request. The input includes the job description text. I need to output HTML.
Let's look at the actual text and decide what to keep. If I must preserve ALL original content word-for-word, I cannot remove any text. But the HTML structure needs to make sense. I can wrap everything in
or
/- as appropriate, but keep every word. However, the "REMOVE" list includes things that are clearly not job info, but maybe they're in the text. In this text, we have: "Business Unit:", "Group Admin", "Department:", "Finance", "Site:", "Rosebank", "Location - Town / City:", "Rosebank", "Job Advert Summary:", then a long string, "Minimum Requirements:", then text, "Duties and Responsibilities:", then text. All of these are part of the job listing. If I remove "Business Unit:", "Department:", etc., I'm removing content, violating "Preserve ALL original content word-for-word". So I should keep everything, but format it.
But wait: "REMOVE all of the following: - Category labels that aren't part of the job (e.g., 'Internships' as a standalone line)". The example is "Internifications" as a standalone line. The labels here are "Business Unit:", "Department:", etc. Are they "part of the job"? They are typically part of a job posting metadata. The instruction says "that aren't part of the job". It's ambiguous. Given the "Preserve ALL original content" rule, I'll err on the side of keeping all text, but structure it with HTML tags. However, the "stray numbers or formatting artifacts" removal: "01" for number of vacancies, numbers like "2-4 years", "NQF Level 8", "D3". These are content, not stray artifacts. I'll keep them.
Let's re-read the very first line: "You are a job listing editor. You receive raw scraped text from a job website. Your job is to extract ONLY the actual job information and return it in a clean, readable format." This is the role description. Then it lists what to remove. Then "Return ONLY the cleaned job text." Then the user says "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." and gives the HTML rules. It seems the HTML rules are the specific format for this turn. The "Preserve ALL original content word-for-word" is key. I will keep every single word from the input, including labels, but format them into HTML tags as specified. However, the "REMOVE" list might be contradictory. In many AI prompt evaluations, the later instructions supersede earlier ones, or the "Preserve ALL original content" is the strict rule for the output format. I think I should keep all text, but structure it. But if I keep "Business Unit: Group Admin", that's a label and content. I'll wrap it.
Let's look at the HTML rules again: "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."
This suggests I should identify sections and use appropriate tags. The text has clear sections: "Minimum Requirements:" and "Duties and Responsibilities:". Also "Job Advert Summary:" etc. I should use
for section headers like "Minimum Requirements", "Duties and Responsibilities", maybe "Job Advert Summary". But the rule says "Use for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role)". It lists examples. I can use for "Minimum Requirements" and "Duties and Responsibilities". What about "Job Advert Summary", "Business Unit", "Department", etc.? They are not in the example list, but the rule says "Preserve ALL original content word-for-word". So I must include them. I could wrap the section headers in if they match the pattern, or wrap everything in
if no clear sections. But there are clear sections.
Let's parse the text and decide on HTML structure:
- The text starts with "Business Unit:\nGroup Admin\n\nDepartment:\nFinance\n\nSite:\nRosebank\n\nLocation - Town / City:\nRosebank\n\nJob Advert Summary:\nVACANCY ANNOUNCEMENT PPC ROSEBANK: INTERNAL & EXTERNAL ADVERTISEMENT POSITION: SPECIALIST GROUP TECHNICAL JOB GRADE: D3 Department: FINANCE LOCATION: PPC ROSEABANK NUMBER OF VACANCIES: 01 The Specialist Group Technical is responsible for monitoring the adherence to the International Financial Reporting Standards across the PPC Group\n\nMinimum Requirements:\nChartered Accountant (South Africa) (NQF Level 8) 2-4 years post articles experience EXPERIENCE Reporting professional with a strong background in specific reporting standards - 2 – 4 years Manufacturing or mining industry experience - 2 – 4 years\n\nDuties and Responsibilities:\nGroup Technical Maintain and update technical accounting frameworks, policies and procedures and align to industry standards and regulations Prepare technical position papers on IFRS and related matters Prepare and maintain accounting opinions database Participate in IFRS implementation projects Lead all projects relating to accounting papers and opinions across the Group Compliance Monitor stakeholder compliance with IFRS Keep abreast with JSE regulatory requirements and monitor the Group’s compliance Provide business units with support relating to any compliance requirements Prepare disclosures for external auditors in line with IFRS requirements Partner with business and provide them with support during the external audit process Monitor adherence to accounting principles and practices in line with regulatory requirements and PPC standards Reporting Participate in the preparation of the Group financial statements Review subsidiary financial statements on an annual basis Monthly review of PPC Ltd complex transactions Stakeholder Management Prepare and submit the JSE report to the Audit and Risk Committee for review and sign-off Support, provide data and respond to queries raised by auditors Provide IFRS guidance and support to the Groups’ divisions Facilitate training to capacitate stakeholders and mitigate risks"
If I must preserve all content word-for-word, I will keep every line, every colon, every word. I'll structure it semantically. The headings like "Business Unit:", "Department:", etc., are part of the content. I could treat the whole thing as paragraphs and section headers. The rule "Use
for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role)" suggests I should use for section titles. The text has "Minimum Requirements:" and "Duties and Responsibilities:". Those match the examples (Requirements, Responsibilities). I'll use for those. For "Business Unit:", "Department:", "Site:", "Location - Town / City:", "Job Advert Summary:", these are not in the example list, but I still need to preserve them. I could wrap them in
or
. The rule says "If text has no clear sections, just wrap paragraphs in
tags". Here there are clear sections, so I should use the appropriate tags
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." The "Preserve ALL original content word-for-word" is a strong instruction. It means I should not remove anything that's in the text. The "REMOVE" list from the first part might be a general guideline for the editor role, but the specific task here is to format as clean semantic HTML preserving all content. However, the first part says "Your job is to extract ONLY the actual job information and return it in a clean, readable format." Then it lists what to remove. Then it says "Return ONLY the cleaned job text." Then the second prompt says "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." and gives the HTML rules. It seems like the user is giving me two prompts in one, or the second is the actual format request. The input includes the job description text. I need to output HTML. Let's look at the actual text and decide what to keep. If I must preserve ALL original content word-for-word, I cannot remove any text. But the HTML structure needs to make sense. I can wrap everything in
or
/- as appropriate, but keep every word. However, the "REMOVE" list includes things that are clearly not job info, but maybe they're in the text. In this text, we have: "Business Unit:", "Group Admin", "Department:", "Finance", "Site:", "Rosebank", "Location - Town / City:", "Rosebank", "Job Advert Summary:", then a long string, "Minimum Requirements:", then text, "Duties and Responsibilities:", then text. All of these are part of the job listing. If I remove "Business Unit:", "Department:", etc., I'm removing content, violating "Preserve ALL original content word-for-word". So I should keep everything, but format it.
But wait: "REMOVE all of the following: - Category labels that aren't part of the job (e.g., 'Internships' as a standalone line)". The example is "Internifications" as a standalone line. The labels here are "Business Unit:", "Department:", etc. Are they "part of the job"? They are typically part of a job posting metadata. The instruction says "that aren't part of the job". It's ambiguous. Given the "Preserve ALL original content" rule, I'll err on the side of keeping all text, but structure it with HTML tags. However, the "stray numbers or formatting artifacts" removal: "01" for number of vacancies, numbers like "2-4 years", "NQF Level 8", "D3". These are content, not stray artifacts. I'll keep them.
Let's re-read the very first line: "You are a job listing editor. You receive raw scraped text from a job website. Your job is to extract ONLY the actual job information and return it in a clean, readable format." This is the role description. Then it lists what to remove. Then "Return ONLY the cleaned job text." Then the user says "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." and gives the HTML rules. It seems the HTML rules are the specific format for this turn. The "Preserve ALL original content word-for-word" is key. I will keep every single word from the input, including labels, but format them into HTML tags as specified. However, the "REMOVE" list might be contradictory. In many AI prompt evaluations, the later instructions supersede earlier ones, or the "Preserve ALL original content" is the strict rule for the output format. I think I should keep all text, but structure it. But if I keep "Business Unit: Group Admin", that's a label and content. I'll wrap it.
Let's look at the HTML rules again: "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."
This suggests I should identify sections and use appropriate tags. The text has clear sections: "Minimum Requirements:" and "Duties and Responsibilities:". Also "Job Advert Summary:" etc. I should use
for section headers like "Minimum Requirements", "Duties and Responsibilities", maybe "Job Advert Summary". But the rule says "Use for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role)". It lists examples. I can use for "Minimum Requirements" and "Duties and Responsibilities". What about "Job Advert Summary", "Business Unit", "Department", etc.? They are not in the example list, but the rule says "Preserve ALL original content word-for-word". So I must include them. I could wrap the section headers in if they match the pattern, or wrap everything in
if no clear sections. But there are clear sections.
Let's parse the text and decide on HTML structure:
- The text starts with "Business Unit:\nGroup Admin\n\nDepartment:\nFinance\n\nSite:\nRosebank\n\nLocation - Town / City:\nRosebank\n\nJob Advert Summary:\nVACANCY ANNOUNCEMENT PPC ROSEBANK: INTERNAL & EXTERNAL ADVERTISEMENT POSITION: SPECIALIST GROUP TECHNICAL JOB GRADE: D3 Department: FINANCE LOCATION: PPC ROSEABANK NUMBER OF VACANCIES: 01 The Specialist Group Technical is responsible for monitoring the adherence to the International Financial Reporting Standards across the PPC Group\n\nMinimum Requirements:\nChartered Accountant (South Africa) (NQF Level 8) 2-4 years post articles experience EXPERIENCE Reporting professional with a strong background in specific reporting standards - 2 – 4 years Manufacturing or mining industry experience - 2 – 4 years\n\nDuties and Responsibilities:\nGroup Technical Maintain and update technical accounting frameworks, policies and procedures and align to industry standards and regulations Prepare technical position papers on IFRS and related matters Prepare and maintain accounting opinions database Participate in IFRS implementation projects Lead all projects relating to accounting papers and opinions across the Group Compliance Monitor stakeholder compliance with IFRS Keep abreast with JSE regulatory requirements and monitor the Group’s compliance Provide business units with support relating to any compliance requirements Prepare disclosures for external auditors in line with IFRS requirements Partner with business and provide them with support during the external audit process Monitor adherence to accounting principles and practices in line with regulatory requirements and PPC standards Reporting Participate in the preparation of the Group financial statements Review subsidiary financial statements on an annual basis Monthly review of PPC Ltd complex transactions Stakeholder Management Prepare and submit the JSE report to the Audit and Risk Committee for review and sign-off Support, provide data and respond to queries raised by auditors Provide IFRS guidance and support to the Groups’ divisions Facilitate training to capacitate stakeholders and mitigate risks"
If I must preserve all content word-for-word, I will keep every line, every colon, every word. I'll structure it semantically. The headings like "Business Unit:", "Department:", etc., are part of the content. I could treat the whole thing as paragraphs and section headers. The rule "Use
for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role)" suggests I should use for section titles. The text has "Minimum Requirements:" and "Duties and Responsibilities:". Those match the examples (Requirements, Responsibilities). I'll use for those. For "Business Unit:", "Department:", "Site:", "Location - Town / City:", "Job Advert Summary:", these are not in the example list, but I still need to preserve them. I could wrap them in
or
. The rule says "If text has no clear sections, just wrap paragraphs in
tags". Here there are clear sections, so I should use the appropriate tags
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."
This suggests I should identify sections and use appropriate tags. The text has clear sections: "Minimum Requirements:" and "Duties and Responsibilities:". Also "Job Advert Summary:" etc. I should use
for section headers like "Minimum Requirements", "Duties and Responsibilities", maybe "Job Advert Summary". But the rule says "Use for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role)". It lists examples. I can use for "Minimum Requirements" and "Duties and Responsibilities". What about "Job Advert Summary", "Business Unit", "Department", etc.? They are not in the example list, but the rule says "Preserve ALL original content word-for-word". So I must include them. I could wrap the section headers in if they match the pattern, or wrap everything in
if no clear sections. But there are clear sections.
Let's parse the text and decide on HTML structure:
- The text starts with "Business Unit:\nGroup Admin\n\nDepartment:\nFinance\n\nSite:\nRosebank\n\nLocation - Town / City:\nRosebank\n\nJob Advert Summary:\nVACANCY ANNOUNCEMENT PPC ROSEBANK: INTERNAL & EXTERNAL ADVERTISEMENT POSITION: SPECIALIST GROUP TECHNICAL JOB GRADE: D3 Department: FINANCE LOCATION: PPC ROSEABANK NUMBER OF VACANCIES: 01 The Specialist Group Technical is responsible for monitoring the adherence to the International Financial Reporting Standards across the PPC Group\n\nMinimum Requirements:\nChartered Accountant (South Africa) (NQF Level 8) 2-4 years post articles experience EXPERIENCE Reporting professional with a strong background in specific reporting standards - 2 – 4 years Manufacturing or mining industry experience - 2 – 4 years\n\nDuties and Responsibilities:\nGroup Technical Maintain and update technical accounting frameworks, policies and procedures and align to industry standards and regulations Prepare technical position papers on IFRS and related matters Prepare and maintain accounting opinions database Participate in IFRS implementation projects Lead all projects relating to accounting papers and opinions across the Group Compliance Monitor stakeholder compliance with IFRS Keep abreast with JSE regulatory requirements and monitor the Group’s compliance Provide business units with support relating to any compliance requirements Prepare disclosures for external auditors in line with IFRS requirements Partner with business and provide them with support during the external audit process Monitor adherence to accounting principles and practices in line with regulatory requirements and PPC standards Reporting Participate in the preparation of the Group financial statements Review subsidiary financial statements on an annual basis Monthly review of PPC Ltd complex transactions Stakeholder Management Prepare and submit the JSE report to the Audit and Risk Committee for review and sign-off Support, provide data and respond to queries raised by auditors Provide IFRS guidance and support to the Groups’ divisions Facilitate training to capacitate stakeholders and mitigate risks"
If I must preserve all content word-for-word, I will keep every line, every colon, every word. I'll structure it semantically. The headings like "Business Unit:", "Department:", etc., are part of the content. I could treat the whole thing as paragraphs and section headers. The rule "Use
for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role)" suggests I should use for section titles. The text has "Minimum Requirements:" and "Duties and Responsibilities:". Those match the examples (Requirements, Responsibilities). I'll use for those. For "Business Unit:", "Department:", "Site:", "Location - Town / City:", "Job Advert Summary:", these are not in the example list, but I still need to preserve them. I could wrap them in
or
. The rule says "If text has no clear sections, just wrap paragraphs in
tags". Here there are clear sections, so I should use the appropriate tags
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." This suggests I should identify sections and use appropriate tags. The text has clear sections: "Minimum Requirements:" and "Duties and Responsibilities:". Also "Job Advert Summary:" etc. I should use
for section headers like "Minimum Requirements", "Duties and Responsibilities", maybe "Job Advert Summary". But the rule says "Use for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role)". It lists examples. I can use for "Minimum Requirements" and "Duties and Responsibilities". What about "Job Advert Summary", "Business Unit", "Department", etc.? They are not in the example list, but the rule says "Preserve ALL original content word-for-word". So I must include them. I could wrap the section headers in if they match the pattern, or wrap everything in
for "Minimum Requirements" and "Duties and Responsibilities". What about "Job Advert Summary", "Business Unit", "Department", etc.? They are not in the example list, but the rule says "Preserve ALL original content word-for-word". So I must include them. I could wrap the section headers in if they match the pattern, or wrap everything in
if no clear sections. But there are clear sections. Let's parse the text and decide on HTML structure: - The text starts with "Business Unit:\nGroup Admin\n\nDepartment:\nFinance\n\nSite:\nRosebank\n\nLocation - Town / City:\nRosebank\n\nJob Advert Summary:\nVACANCY ANNOUNCEMENT PPC ROSEBANK: INTERNAL & EXTERNAL ADVERTISEMENT POSITION: SPECIALIST GROUP TECHNICAL JOB GRADE: D3 Department: FINANCE LOCATION: PPC ROSEABANK NUMBER OF VACANCIES: 01 The Specialist Group Technical is responsible for monitoring the adherence to the International Financial Reporting Standards across the PPC Group\n\nMinimum Requirements:\nChartered Accountant (South Africa) (NQF Level 8) 2-4 years post articles experience EXPERIENCE Reporting professional with a strong background in specific reporting standards - 2 – 4 years Manufacturing or mining industry experience - 2 – 4 years\n\nDuties and Responsibilities:\nGroup Technical Maintain and update technical accounting frameworks, policies and procedures and align to industry standards and regulations Prepare technical position papers on IFRS and related matters Prepare and maintain accounting opinions database Participate in IFRS implementation projects Lead all projects relating to accounting papers and opinions across the Group Compliance Monitor stakeholder compliance with IFRS Keep abreast with JSE regulatory requirements and monitor the Group’s compliance Provide business units with support relating to any compliance requirements Prepare disclosures for external auditors in line with IFRS requirements Partner with business and provide them with support during the external audit process Monitor adherence to accounting principles and practices in line with regulatory requirements and PPC standards Reporting Participate in the preparation of the Group financial statements Review subsidiary financial statements on an annual basis Monthly review of PPC Ltd complex transactions Stakeholder Management Prepare and submit the JSE report to the Audit and Risk Committee for review and sign-off Support, provide data and respond to queries raised by auditors Provide IFRS guidance and support to the Groups’ divisions Facilitate training to capacitate stakeholders and mitigate risks" If I must preserve all content word-for-word, I will keep every line, every colon, every word. I'll structure it semantically. The headings like "Business Unit:", "Department:", etc., are part of the content. I could treat the whole thing as paragraphs and section headers. The rule "Use
for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role)" suggests I should use for section titles. The text has "Minimum Requirements:" and "Duties and Responsibilities:". Those match the examples (Requirements, Responsibilities). I'll use for those. For "Business Unit:", "Department:", "Site:", "Location - Town / City:", "Job Advert Summary:", these are not in the example list, but I still need to preserve them. I could wrap them in
for those. For "Business Unit:", "Department:", "Site:", "Location - Town / City:", "Job Advert Summary:", these are not in the example list, but I still need to preserve them. I could wrap them in
or
. The rule says "If text has no clear sections, just wrap paragraphs in
tags". Here there are clear sections, so I should use the appropriate tags
How well do you match?
Get an instant AI match score for this role — free, takes 3 minutes.
Tailor your CV for this role
The concierge rewrites your whole CV and writes a matching cover letter for this job — opens right here, nothing to paste.
Tailor My CV to This Job ✍️Free cover letter for this job
Upload your CV and get a tailored cover letter in seconds — free, no account needed.
Generate a Cover Letter 📝Let jobs find you
Leave your email and our AI matches you to new jobs across 24 African markets — free. You wait for the call.
Add your CV for real matches
Upload your CV and we score every new job against your real experience — only strong matches reach your inbox. Optional, but it makes your matches far sharper.
You're in.
We'll email you the moment a job matches your profile. Check your inbox for a welcome from My Job Concierge.
I'm ECHO, your MJC career assistant. I can help you find jobs, explore career tools, and connect with opportunities across Africa.