Mock interviews with follow-up questions and a written report.
Set the role, level and kind of interview, then answer by typing or speaking. The interviewer follows up when an answer is thin, and the report covers structure, specifics and filler words. Keep a bank of STAR stories to reuse.
The app itself, running inside this page. Anything you do here is saved in your browser.
Ask it to do things
Press Ctrl+K in the app (Cmd+K on a Mac) and describe what you want. The model chooses from the app's own functions, runs them in order and tells you what changed. Some examples:
| Mock interview for a junior data analyst, behavioral, tough | Sets up the interview and asks the first question. |
| Save my story about fixing the deploy pipeline | Adds a STAR story to your bank. |
| Drill me on conflict questions | Starts a timed drill for that competency. |
Instructions you save in the same box, such as "keep it short" or "I'm a beginner", are added to every AI request the app makes.
Features
- Configurable role
- Level, interview type, persona, question count.
- Adaptive follow-up probes decided by the AI
- From your actual answer.
- Voice answers
- Via SpeechRecognition with live transcription; questions via speech synthesis.
- Live analytics
- Words, wpm, fillers, hedges, numbers, I/we ownership, STAR detector.
- Scored report
- Per-answer 1-5, strengths, fixes, stronger-answer outlines, overall signal.
- Markdown report export
- Prep page
- Paste a job description to extract the skills it mentions (ranked by frequency, without false matches like "go" inside words), requirement sentences, years of experience and behavioral themes, then generate likely questions or start an interview tailored to it.
- Stories page
- A STAR story bank tagged by competency, with coverage gaps, AI tightening that never invents numbers, and search that ranks your stories against any question.
- During behavioral interviews the best-matching
- Saved stories appear beside the question.
- Drills page
- One timed question at a time per competency, scored on STAR structure, length and fillers with a specific tip.
Runs in your browser
Speech-to-text plumbing, timing, linguistic metrics, STAR detection, report rendering. None of this needs a network connection or a model.
Uses a language model for
Conversational question generation with persona + competency coverage. Follow-up decision. Rubric-based evaluation informed by local metrics.
Notes
- Cost
- Free. Each account has a daily allowance of AI requests.
- Your data
- What you make stays in this browser on this device. Your account is only used for signing in and for the built-in AI. You can export a backup or clear everything from Settings.
- AI access
- Signed-in users get the built-in AI with nothing to set up. You can also use your own Groq or OpenRouter key under Settings.
- Source
- The code and tests are on GitHub under the MIT license. The tests also run in your browser.