Research
How Emoti works, written down in full: the methods, the choices behind them, their limits and what has not been measured yet.
- Designing first-round voice screens candidates can trustEmoti's first-round voice screens tell candidates that an AI interviewer asks the questions, ask everyone the same questions, rate each answer against the team's rubric, and leave every advance or reject decision to a recruiter. The design still has gaps, including rubrics anchored only at the ends, scorecards that show summaries rather than the answers themselves, and no setting for how long recordings are kept.For talent leaders, 8 min, ai voice screens, structured interviews, fairness
- Evidence-first candidate matchingEmoti ranks candidates by checking each criterion in a recruiter's brief against what a profile actually says, and it never shows a score without that evidence. Each criterion is marked met, partly met, missing or not enough information; must-haves count double, and a missing must-have caps the score at 54 out of 100.For recruiters, 9 min, sourcing, candidate matching, explainable ranking
- Grounded interview notesEmoti's interview notes follow a template the team chooses, and every section, highlight and answer points back to the moment in the transcript it came from. A language model writes the note when one is configured; otherwise a rules engine assembles it from transcript quotes, and the app labels which one answered.For hiring managers, 8 min, interview notes, transcripts, explainable ai
- Personal outreach with a person in the loopEmoti drafts one personal first line for each candidate from facts in their own professional profile, and nothing is sent until a recruiter approves the line and the sequence is active. Emails go out on weekdays inside a sending window and under a daily limit, and any reply stops the sequence for that person.For recruiters, 8 min, outreach, personalization, human oversight