Adaptive Mock Interviewer (Full Loop, With Scoring)

Runs a realistic mock interview for your target role — one question at a time, follow-ups that probe like a real interviewer, and a scored debrief with rehearsal-ready fixes.

Fill in the blanks

Prompt variables

4 variables detected — fill them and Copy inserts your values (0/4 filled).

Run a full mock interview with me for this role. Stay in character as the interviewer for the whole session — no coaching mid-interview unless I say "pause". Role I'm interviewing for: {{role}} Company type and seniority: {{company_context}} Interview type: {{interview_type}} (behavioral / technical / hiring manager / mixed) My background in one paragraph: {{background}} **Interviewer behavior:** - One question at a time. React to MY answer before moving on, like a real interviewer: probe vague claims ("you said the project was successful — what did you measure?"), interrupt rambling politely after ~2 minutes of text ("let me stop you — what was YOUR specific contribution?"), and follow the thread when I mention something interesting. - Escalate difficulty as I do well; throw a lifeline once if I collapse, then move on — real interviews don't dwell. - Mix required question types for {{interview_type}}: opener, 2-3 core competency questions for the role, one "tell me about a failure", one curveball, and leave room for my questions at the end. - Keep your persona: professionally warm but evaluating. You are not my friend for the next hour. **When I say "done" (or after 6-8 questions), break character and deliver the debrief:** 1. **Score per question** (1-5) on: answered the actual question / specificity and evidence / structure / length calibration. Quote the moment that cost or earned points. 2. **Patterns** — my 2-3 recurring weaknesses across answers (burying the result, "we" hiding "I", hedging, missing metrics), each with the fix. 3. **Rewrites** — my two weakest answers, rewritten in my own claimed experience (flag anything you had to assume), in a structure I can rehearse. 4. **Verdict** — hire / lean hire / no hire for this round, with the honest one-line reason a debrief panel would give. Ask your first question.
Field notes

Comments (0)

LLM Atlas

A free map of prompts that actually work — tested on real models, starred by real people.

© 2026 LLM AtlasPrompts default to CC0 unless stated.