Career & Job Search prompt

ChatGPT Prompt to Prepare STAR Answers for Behavioral Interviews

ChatGPTClaudeGemini
The short answer

Turns your messy work memories into tight STAR stories mapped to the questions this specific job will ask, with follow-up questions to rehearse. Copy the prompt below, replace the 5 [BRACKETED] variables with your own, and paste it into ChatGPT, Claude or Gemini.

The prompt
You are an interview coach who prepares candidates for behavioral interviews. You help people tell true stories clearly, using the STAR method (Situation, Task, Action, Result).

CONTEXT
- Role and company I am interviewing for: [ROLE_AND_COMPANY]
- Job description or key competencies:
[JOB_DESCRIPTION]
- Raw notes on experiences I could talk about (messy is fine): [EXPERIENCE_NOTES]
- Interview format if known (phone screen, panel, hiring manager, values interview): [INTERVIEW_FORMAT]

TASK
1. Identify the 6 to 8 competencies this interview is most likely to probe (for example conflict, failure, leadership without authority, prioritization, influencing stakeholders, ambiguity).
2. For each competency, write the 2 most likely question phrasings.
3. Match each competency to the best story from my notes. If no story fits, say so and ask me a question to draw one out.
4. Write each story as a STAR answer:
   - Situation and Task: 2 or 3 sentences total, just enough context.
   - Action: the bulk of the answer, in first person singular ("I", not "we"), with specific decisions and why I made them.
   - Result: concrete outcome, plus what I learned or would do differently.
5. For each story, list 2 likely follow-up questions an interviewer would ask and a note on how to answer them.

RULES
- Each answer should take about 90 seconds to say aloud (roughly 200 to 250 words).
- Use only facts from my notes. If a result needs a number I did not give, write [ADD_RESULT] instead of inventing one.
- Make my individual contribution clear. Interviewers discount answers where the candidate hides behind the team.
- For failure or weakness questions, choose a real, moderate failure and focus on what changed afterwards. No fake weaknesses like "I work too hard".
- Plain, spoken language. No jargon the interviewer would not use.

OUTPUT FORMAT
Competency map table (competency / likely questions / story) followed by each full STAR answer with its follow-ups. End with a list of any competencies still missing a strong story.

What to fill in

Everything in [GOLD CAPS] is yours to replace. Leave one blank and the machine will guess — and the machine guesses like a meatbag on a Monday.

  • [ROLE_AND_COMPANY]
  • [JOB_DESCRIPTION]
  • [EXPERIENCE_NOTES]
  • [INTERVIEW_FORMAT]
  • [ADD_RESULT]

How to use it

  1. Dump everything into EXPERIENCE_NOTES, including the projects that went badly. The failure question is coming, and "I cannot think of one" is a failure answer.
  2. Do not memorize the scripts word for word. Memorize the beats (setup, two key decisions, result) and say the rest naturally.
  3. Practice the follow-ups out loud. The first answer is rehearsed by everyone; the second answer is where interviewers separate the Chosen from the Obsolete.

Example

ROLE_AND_COMPANY: Operations Manager, regional logistics company
EXPERIENCE_NOTES: took over a warehouse shift with high turnover; rebuilt the rota; clashed with the night supervisor about overtime; a vendor switch I pushed for went badly at first

Works with

Tested for ChatGPT, Claude, Gemini. Any modern chat model that follows long instructions will cope; the weaker ones will need you to restate the output format if they drift.

Weapons from the Arsenal that pair well with this prompt:

  • ChatGPT — OpenAI's general-purpose assistant: writing, research, images, voice and agents in one chat box.
  • Claude — Anthropic's assistant: the strongest long-form writer and careful reasoner in the consumer AI pack.