Hiring is high-stakes writing. A weak job description repels great candidates. A lazy interview loop hires by gut feel. AI can level both — but only if the prompts treat hiring as a system, not a single task.
The recruitment process is a funnel: a job description attracts applicants, a screen narrows them, interviews assess them, and an offer closes them. Each stage is a writing problem disguised as an HR problem. The job description is marketing. The screen is filtering. The interview is research. The offer is sales.
AI is genuinely useful at every stage — provided you brief it with the seniority, the team, the must-have capabilities, and the bar you are hiring against. Generic prompts produce generic hires. Specific prompts produce a structured, repeatable loop.
The recruitment funnel has roughly four stages: attract, screen, interview, decide. AI helps at every stage if you treat each one as a distinct prompt. Job descriptions need a prompt focused on attraction and clarity. Interview questions need a prompt focused on fair, comparable signal. Evaluation rubrics need a prompt focused on consistent scoring.
A good JD does three things in this order: it explains the mission of the role, lists the outcomes the hire is responsible for, and finally names the skills required. Most weak JDs do the opposite — they open with a five-bullet list of "requirements" and never mention what the person is actually meant to achieve.
Weak prompt
write a job description for a senior product manager
The AI will write a templated JD with five generic responsibilities and ten generic requirements. It will not attract anyone you actually want to hire — because it sounds identical to 200 other openings.
Strong prompt — outcome-led job description
Act as an experienced talent partner who writes job
descriptions that genuinely attract senior candidates.
Company: Northwave, a Series B B2B SaaS company (180
employees, headquartered in Bengaluru, remote-first).
We sell supply-chain analytics to mid-market retailers.
Role: Senior Product Manager, Retail Analytics.
Reports to: Director of Product.
Team: pairs with a tech lead (8 engineers) and a data
scientist; works closely with Sales and CS.
Use this structure:
1. **The mission** (2 sentences — why this role exists
right now, not a generic mission statement).
2. **What you will own in the first 12 months**
(3–4 outcomes, each phrased as a measurable result,
e.g. "Cut onboarding time from 6 weeks to 2 weeks").
3. **A typical month** (one short paragraph of what
the work actually looks like).
4. **Who we think will thrive here** (5 bullet skills
or experiences — the must-haves only).
5. **What we will not require** (a short anti-list:
things people often expect but we do not, e.g. "an
MBA", "experience at FAANG").
6. **Compensation and logistics** (one paragraph —
leave numbers blank for me to fill in).
Tone: confident, plain English, no buzzwords like
"rockstar", "ninja", "passionate". Length: ~400 words.
This prompt forces an outcome-led JD with concrete first-year goals, anti-requirements that signal honesty, and a tone that reads like a real human wrote it. That is how you stand out in a candidate's inbox.
Tip: Ask the AI to draft a "rejection email that protects the relationship" alongside the offer email. Most hiring loops invest heavily in offers and almost nothing in rejections — yet rejected candidates remember the experience for years.
Pick an open role at your company (or imagine one). Write the company profile, reporting line, and the team in 80 words. Run the JD prompt. Highlight the parts you would actually keep without editing.
For the same role, ask the AI to generate three interview questions per first-year outcome, plus a 1–5 rubric for each. Notice how having a rubric forces you to define what "good" actually means before you meet anyone.
Ask the AI to rewrite a recent job description from a competitor in the outcome-led structure above. Compare side by side. Which JD would attract a stronger applicant pool?
Sign in to join the discussion and post comments.
Sign inAdvanced Prompt Engineering Techniques
Master the powerful techniques AI experts use every day. Chain-of-thought, RAG, agents, function calling, prompt evaluation, and much more — 20 deep-dive tutorials.
Prompt Engineering for Developers
Use AI as your coding co-pilot. 18 tutorials on writing prompts to generate clean code, debug faster, write tests, build APIs, and ship better software.
Foundations of Prompt Engineering
The must-know basics of prompt engineering. Learn what prompts are, how AI models read them, and how to write clear instructions that get great results.
Prompt Engineering for Content & Copywriting
Write blogs, ads, emails, and social media content ten times faster with AI. 13 practical tutorials on prompt engineering for content creators and copywriters.
Prompt Engineering for Image Generation
Turn words into stunning visuals. Master AI image generation tools like Midjourney, DALL·E 3, and Stable Diffusion with 18 focused tutorials — from first prompt to full brand identity.
Prompt Engineering Projects & Real-World Applications
Twelve hands-on projects that turn prompt engineering theory into a portfolio. Build chatbots, content generators, RAG systems, and more.