PromptWork
Write interview questions for a role and level
Turn a role and seniority level into behavioural and technical interview questions, each paired with a note on what a good answer looks like.
Last updated
Fill in the blanks
Assembled in your browser — nothing you type is stored or sent anywhere.
Your prompt
Write interview questions for a senior (5-8 years experience) Backend Engineer candidate, focused on: distributed systems experience, ability to debug production incidents under pressure, and experience mentoring junior engineers. team works primarily in Go with a Postgres-backed service handling ~2000 requests/sec..
Write 4-5 behavioural questions and 4-5 technical or role-specific questions. For each question, add a short note on what a good answer looks like at this level — specific enough that an interviewer with less experience in this area could still evaluate the response, and calibrated to the level given (a good answer from a senior candidate should look different from a good answer from a junior one). Base the technical questions only on the focus areas given; if a focus area is too broad to write a fair, specific question about, say so and suggest what would need to be narrowed down first.
Focus areas and any additional context:
distributed systems experience, ability to debug production incidents under pressure, and experience mentoring junior engineers. team works primarily in Go with a Postgres-backed service handling ~2000 requests/sec.
Model-agnostic — works in Claude, ChatGPT, Gemini or any AI chat.
Why this prompt works
- →Requiring a "what a good answer looks like" note per question is what makes the output usable by an interviewer who isn't already an expert in the area being probed, not just a list of things to ask.
- →Calibrating the good-answer note to the stated level, rather than a single generic standard, prevents the common mistake of using the same rubric to evaluate a junior and a senior candidate.
- →Limiting technical questions to the given focus areas, with a prompt to flag ones that are too broad to question fairly, stops the model from inventing a plausible-sounding but ungrounded deep-dive question about a topic nobody asked for.