Translate hiring language into likely work, evidence needs, ambiguity, and interview questions
6 min setupTested with:ChatGPTReviewed: 2026-08-28
1
Add your context
Your text stays in this browser. AILesson Prompts does not send it to a model or server.
2
Your prompt
Unfilled fields remain visible as placeholders, so you can still copy and edit the prompt
Explain the job description in plain language as likely tasks, skills, and hiring evidence.
Complete posting, company context, location, date, and source:
[description]
Career stage, unfamiliar terms, goals, authorization, and accessibility needs:
[context]
Must/preferred rules, inference limits, seniority, salary, and evidence standard:
[rules]
Use only the posting for employer-specific claims. Separate explicit responsibilities, required qualifications, preferred qualifications, working conditions, and your cautious inferences. Translate each responsibility into likely day-to-day tasks, collaborators, outputs, and observable skill evidence, but label anything not stated. Identify ambiguous jargon, bundled roles, unrealistic combinations, location/travel/time expectations, application requirements, and legally or practically important missing information. Do not infer culture, salary, flexibility, sponsorship, or hidden screening rules. Return a plain-language role summary, requirement matrix, likely-week examples, evidence candidates should prepare, questions for recruiter/interview, and a fit-neutral application checklist.
Private by defaultPrompt assembly happens locally in your browser. Avoid placing confidential information into any AI service unless your organization allows it.
From input to outcome
A worked example
See how concrete context turns this recipe into a usable result
Actual input
Complete job description
Posted 4 August 2026. Operations Analyst, Manchester, hybrid. Responsibilities: own weekly capacity reporting; investigate service variance; partner with depot managers; improve planning processes; present recommendations to the Operations Director. Required: advanced Excel, experience with operational data, clear written communication. Preferred: SQL, Power BI, logistics experience. Role may require occasional depot visits. Application: CV and answers to two questions. Salary, hybrid frequency, travel area, and sponsorship not listed.
Candidate context
Applicant has two years in retail operations and understands Excel but not phrases 'own reporting' and 'service variance.' Needs to decide whether to apply and what examples to prepare. Requires UK work sponsorship, status unknown.
Interpretation rules
Treat Required as explicit screening evidence and Preferred as advantageous, not mandatory. Infer likely tasks only when labeled. Do not guess salary, seniority beyond title, travel frequency, hybrid days, or sponsorship.
Example output
Plain-language summary: the role turns operational data into a reliable weekly view of staffing/capacity and service performance, investigates why results differ from plan, and helps managers change planning. “Own weekly capacity reporting” explicitly assigns accountability for producing and maintaining the report; it does not state that you manage people. “Service variance” likely means differences between planned and actual service measures, but the exact measures are not defined.
Required matrix: advanced Excel—prepare a real example involving structured data, formulas/lookups, checks, and a decision; operational data—show how you handled definitions, quality, and business context; writing—provide an example of a concise recommendation. Responsibilities also call for stakeholder collaboration and presentation evidence, although these are not listed under Required. Preferred SQL, Power BI, and logistics should remain advantages, not automatic rejection criteria.
Likely week, labeled inference: refresh/validate a capacity report; investigate a depot exception; discuss causes with a manager; document a process change; brief the director. Ask: what metrics define service variance, which report tools/source systems are used, how often/where are depot visits, expected hybrid pattern, salary range, and whether sponsorship is available. Sponsorship is a decision-critical unknown to clarify before investing heavily in the application.
Why this works
1
Separating explicit requirements from cautious inference prevents plausible role conventions from becoming employer facts.
2
Observable evidence translates abstract skills into preparation without claiming the candidate has them.
Check the result
Is every employer-specific statement traceable to the posting?
Are required, preferred, inferred, and missing items clearly distinct?
Do suggested evidence examples avoid inventing candidate experience?
ChatGPT