Generic interview prep wastes hours. A good prediction prompt narrows from “all behavioural questions” to “the 8 questions THIS panel at THIS company at THIS level is likely to ask”.
Who this is for
Candidates with limited prep time, career switchers entering unfamiliar interview cultures, anyone tired of practising 100 generic questions.
When not to use these prompts
Don’t use these to skip prep on unpredicted areas. Predictions narrow the high-probability set; safe coverage still needs depth.
Prompt anatomy / structure formula
Every prediction prompt should carry six elements:
- Role: candidate, hiring manager, recruiter — name the persona AI plays.
- Context: target role, company, level, your background.
- Goal: one deliverable — analysis, script, answer, plan.
- Constraints: word count, banned phrases, must-include facts.
- Tone: confident / curious / measured — 2-3 anchors.
- Examples: paste 1-2 of your past answers or sample tone.
Best for
- Behavioural question set prediction
- Technical / case style prediction
- Interviewer-specific prediction
- Final-round panel prediction
- Recruiter screen prediction
12 copy-ready prompt templates
1. JD-driven question set
JD: {jd}. My background: {me}. Predict the 10 most likely behavioural questions for this role. For each: why this question (which JD line triggered it), what story I'd tell, gap I should prepare for.Variables to swap: jd, me
2. Level-calibrated questions
Role level: `{level}` (IC4 / IC5 / Staff / EM / Director). Predict 8 questions that probe THIS level: scope, ambiguity, cross-team, mentorship, prioritisation under constraint. Skip IC-coding questions for an EM role.Variables to swap: level
3. Company-culture predictor
Company: `{company}`. From their hiring page / interview blog / glassdoor reviews, predict their distinctive style (e.g., Amazon LP, Stripe writing, Netflix culture deck). Output 6 likely culture-driven questions.Variables to swap: company
4. Interviewer-LinkedIn driven
Interviewer: `{name}`. Their LinkedIn: `{summary}`. Their past talks / posts: `{public}`. Predict their go-to questions and what stories would resonate. Don't stalk — use only public-facing signal.Variables to swap: name, summary, public
5. Final-round panel decomposition
Final round: 4 panels — Bar Raiser, Hiring Manager, Skip-level, Cross-functional. For each: 2 questions they're likely to ask + the story I should lead with. Don't prep one story; segment.6. Recruiter screen probable list
For a 30-minute recruiter screen, predict 8 likely topics: brief background, motivation, comp expectations, notice period, location, remote / on-site, deal-breakers, next steps. Draft a 30-second answer per topic.7. “Why are you leaving” prediction
I'm leaving `{currentCompany}`. Predict 3 variants of this question they'll ask + 3 ways to answer without trash-talking. One answer should be the "boring true" version.Variables to swap: currentCompany
8. Behavioural buckets
Standard behavioural buckets: leadership, conflict, failure, growth, influence, decision under uncertainty, ambiguity, prioritisation. For my background, rank these by likely interview frequency. Prep the 4 most likely first.9. Reverse-engineer from a rejection
I was rejected from a similar role last quarter. Feedback: {feedback}. Predict which question types likely surfaced the gap. Prep specifically for those next time.Variables to swap: feedback
10. Last-week refresh
Interview tomorrow. Give me a 30-minute refresh: (1) 5 most likely questions, (2) one phrase to anchor each opening, (3) the one thing NOT to do, (4) what to read about the company in the morning.11. Cross-functional ambush questions
Cross-functional panel (e.g., PM interviewing engineer, or vice versa). Predict 5 ambush questions: how do you collaborate with X, how would you handle Y trade-off, what do you wish Z roles understood?12. Question coverage audit
I've prepped {nStories} stories. Map each to interview question types. Identify gaps: what question would have no story to tell? Prep the gap before the rest.Variables to swap: nStories
Common mistakes
- No specific context (company / role / level) — output is generic.
- Asking AI to “be honest” without your actual record — it confabulates.
- Same answer for every company — interviewers compare notes.
- No tone anchor — answers land flat.
- Skipping fact-checks — AI invents dates / numbers / titles.
- Treating first draft as final — first drafts read AI-flavoured.
- No peer / mentor review — feedback loop missing.
How to push results further
- Paste real examples to anchor AI to YOUR voice.
- Ask AI to play interviewer first; weak answers reveal themselves.
- Write 3 drafts; ship the third.
- Always read aloud.
- Save successful phrasings in a personal bank.
- Have a peer in the role review.
- Time-box practice — fatigue makes you worse.
Practical depth notes
Use these prompts as starting points, not final answers. For Interview Question Prediction Prompts: 12 Templates to Prep Smarter, the useful extra work is to replace every generic placeholder with a real constraint: audience, channel, length, brand voice, examples to imitate, and examples to avoid. Run at least two versions with different constraints, then compare the outputs side by side instead of accepting the first polished response.
A good result should pass three checks: it is specific enough that another person could reuse it, it avoids vague praise or filler, and it gives you an editable artifact rather than a broad suggestion. If the output feels generic, add one concrete reference, one forbidden pattern, and one measurable success criterion before rerunning the prompt. Before saving a prompt as reusable, test it on one realistic input and one edge case. The realistic input proves the template can produce the normal deliverable; the edge case shows whether it handles messy constraints, missing context, or an unusual audience. Keep the better output, but also keep the failed version with a note on what was missing. That small failure log is what turns a prompt collection from a list of nice sentences into a practical working library.
FAQ
- Can recruiters tell AI-written answers?: Yes when generic. Specifics are the antidote.
- How much research is enough?: 60-90 minutes for an important interview. Beyond, returns diminish.
- When to start salary research?: Before applying. Negotiation that begins after the offer is weak.
- Should I use levels.fyi / Glassdoor numbers?: Yes as a baseline, with caveats. Validate against 2-3 sources.
- How to keep prep notes organised?: One doc per company: research, questions to ask, story bank fits.
- How often to refresh research before final?: Quick re-scan day of interview — news / launches in the past week.