HRSandbox · bring your own key
Test “JD Interview Questions” with your own key
Paste an Anthropic, OpenAI, or OpenRouter key. It's stored only in your browser's localStorage and sent directly from your browser to the provider — never to KLI Prompts. We have no backend that can see it.
How this works (honestly)
- Your key lives in
localStorageon this device only. - The HTTP request to the LLM goes from your browser straight to
api.anthropic.com/api.openai.com/openrouter.ai. - KLI Prompts has no server endpoint that receives, logs, or proxies your key.
- Clear it any time — there's a button below.
Step 1 · Provider
Recommended for this prompt: any · temperature 0.4
Step 2 · Your API key
Saved to
localStorage on this device. Never sent to KLI servers.Step 3 · Fill the variables
Final prompt (sent to anthropic)
You are an expert career coach and interview preparation specialist.
A candidate is preparing for an interview. Below is the job description they are applying for.
{{role_context}}
Job Description:
---
{{job_description}}
---
Generate exactly 25 tailored interview questions this candidate is likely to be asked. Distribute them across these categories:
- behavioral: 5–6 questions (past experience, "tell me about a time...")
- technical: 7–8 questions (role-specific skills, tools, methodologies mentioned in the JD)
- situational: 4–5 questions (hypothetical scenarios, "how would you handle...")
- culture: 3–4 questions (values alignment, work style, motivation)
- leadership: 3–4 questions (influence, ownership, mentoring, career growth)
For each question, provide a brief 1–2 sentence "why" explanation of what the interviewer is assessing.
Respond ONLY with a JSON object in this exact shape (no markdown fences, no explanation):
{
"roleTitle": "<extracted role title from JD>",
"company": "<extracted company name from JD, or 'the company' if not found>",
"questions": [
{
"id": 1,
"question": "<the interview question>",
"category": "<one of: behavioral | technical | situational | culture | leadership>",
"why": "<1–2 sentence explanation of what the interviewer is assessing>"
}
]
}
Rules:
- Exactly 25 questions total
- Questions must be directly tailored to the specific role, skills, and responsibilities in the JD
- Each question must be distinct — no duplicates or near-duplicates
- Do not number questions in the question text itself
- Output valid JSON onlyOutput — will stream here
Nothing yet. Fill in variables and click Run.
Prompt slug: jd-interview-questions
Prefer copy-paste? Back to the prompt page →