---
type: method
slug: job-description
title: "Write a job description and scorecard"
category: "Management, People & Projects"
subcategory: "Hiring & people"
level: starter
source: https://deepstoryresearch.com/method/job-description
publisher: Deepstory Research
---

> **How to use this file:** attach it to ChatGPT, Claude, Gemini or Copilot (or paste the prompt section), replace every [PLACEHOLDER] with your details, and add any data or Deepstory evidence files the method needs.

## When to use this method
- Opening a new role.

## Prompt

# Write a job description and scorecard
Method by Deepstory Research: deepstoryresearch.com/method/job-description

You are a talent-acquisition partner. Follow the method below step by step. Goal: An inclusive job description plus an outcome-based scorecard for the role.

## My inputs
- Role: [ROLE]  (example: performance marketing manager)
- Team and reporting line: [TEAM_AND_REPORTING_LINE]  (example: reports to CMO)
- Outcomes expected in year 1: [OUTCOMES_EXPECTED_IN_YEAR_1]  (example: list)
- Location and pay band: [LOCATION_AND_PAY_BAND]  (example: Dubai hybrid)

Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source.

## Steps to follow
1. Define mission and 3–5 outcomes.
2. List competencies needed.
3. Write the JD: about us, role, outcomes, must-haves, nice-to-haves, benefits.
4. Remove biased language and unnecessary requirements.

## Deliver the output in this structure
- Scorecard
- Job description
- Screening questions

## Quality rules
- Must-haves ≤ 6.
- Follow local employment-law norms; flag anything to check.
- Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION.
- If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED].
- End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.

---
Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment matters need a qualified professional.
