Mira

AI moderated interviews that read how people feel

User Experience

Analytics

Artificial Intelligence

Visit WebsiteSee on Product Hunt

running facial coding and eye tracking across 120 countries means dealing with wildly different consent and biometric data laws (BIPA in Illinois, GDPR in the EU, etc). is that handled per-region automatically or does it fall on the researcher to configure what's legal where they're recruiting from?

I think the difficult part is whether those signals truly reflect what someone is feeling at that moment. Sometimes the face expression, eye movement can mean different things depending on the person and the context. How do you validate that the emotional signals are accurate ?

the disagreement-not-resolved answer above is good, but does the participant themselves know that level of emotional inference is happening? "we're recording this call" is a different consent than "we're scoring your face for confusion/disengagement in real time." biometric emotion inference specifically is called out under GDPR and the EU AI Act in a way plain video recording isn't. across 120 countries with different disclosure standards, is that spelled out to participants upfront, or folded into a generic research-consent form

"Said yes, looked confused" catching that in real time instead of

buried in hour 3 of a recording is the kind of detail that makes me

trust the rest of the data way more.

The Say-Do gap framing is sharp, and running recruit → moderate → analyze → report as one agent is the ambitious part. For a team that already has research infra, two setup questions: can I bring my own recruited participants into a Mira study, or is moderation locked to your 100M panel? And can I export the raw session data — transcripts plus the behavioral signals you capture — into our own repo, or does the analysis stay inside Mira's dashboards?

The idea of AI moderating interviews based on how people feel is interesting because tone can be pretty subjective. I’m curious how you balance consistency with making the conversation feel natural rather than scripted.

Two things... first, how does the "Real time facial encoding" work? Secondly, this seems like an interesting idea, but im curious regarding how you plan to deal with jobseekers, inevitably, despising software like this. Sure businesses trying to cut costs would love something like this, but on the consumer/job-seeker side how will you mitigate and ensure a candidate doesn't feel like a robot is screening them.

How do you prevent Emotion AI from overinterpreting facial expressions or cultural differences in user reactions?

The Say-Do Gap framing is the sharpest part of this — self-reported data being "socially edited" is exactly the failure mode most research tools quietly inherit. My honest question on the emotion layer: facial coding and voice-emotion signals vary a lot across cultures and neurotypes, so how do you keep the "feel" read from becoming its own bias, especially across 120 countries? Curious whether researchers can see and override the affect signals, or whether they're treated as ground truth in the final report.

Respect for not hand-waving that, most launch threads would have. One thing I'd add: per-frame confidence is the model scoring its own certainty, so it won't catch systematic bias. A model can be high-confidence and wrong the same way across a whole population and never flag it. The only check I trust is human-coded ground truth sampled per region, which is painful to collect. Which regions have you actually validated against local human coders versus carried over from the base model?

"Reads how people feel" is the interesting (and risky) part. When it detects hesitation mid-interview, does it adapt its questioning in the moment or just annotate for the researcher afterward? I'm running beta-user interviews right now and what I always miss is what people didn't say, I would love to know if you surface that.

Per-frame confidence scoring is the right instinct. The bit I'd push on at 120-country scale is cross-cultural validity of the facial and voice layer. Most action-unit and voice-emotion models train on largely Western data, and expression-to-affect doesn't transfer cleanly: gaze aversion, smile intensity, vocal pitch carry different meaning across cultures, so a 'how they feel' score can be confidently miscalibrated for a Jakarta panel while looking fine on a London one. Do you re-validate the emotion mapping per region, or is it one global model?

Congratulations on launch! A lot of the questions are about accuracy and privacy, so I'll ask a different one: how does the emotion reading hold up across cultures and languages? People show feelings differently depending on background, and my audience is fairly reserved by nature. Does the model account for that, or is it mostly calibrated to more expressive participants?

The mid-interview probe on the say/feel mismatch is the part that interests me. I run the cheap cousin of this for my own app, a panel of simulated user personas that scores LLM output before a change ships, and the one thing simulation can't give me is exactly that hesitation signal you're reading off real faces. When facial coding and the transcript disagree, which one do your reports trust? I'd want the raw disagreement surfaced, not resolved for me.

I have run plenty of user interviews by hand, so the moderation part I get. The reads-how-people-feel part is where I would love more detail: inferring emotion from voice or wording is powerful, but it is also the kind of signal that can mislead a decision (someone nervous is not someone negative). How do you present that layer to the researcher, as a hint to probe further or as scored data? The difference feels important.

What stands out is the integration of facial coding and voice emotion AI directly into the interview flow rather than bolting them on as an afterthought. That feels like a real research instrument, not just a chat wrapper dressed up with sentiment scores.

What happens when it works fine and every brand in a category runs creators against the same queries, does it become an arms race where the UGC cancels out, or is there a ceiling on how much citation share you can actually buy back?

When Mira spots a say/feel mismatch and digs deeper on its own, how do you keep that follow-up from leading the participant? A moderator reacting to visible confusion can easily plant the doubt rather than uncover it. Is the probe neutral by design, or tuned per study?

How does the facial coding and eye tracking actually work on participants who don't have webcams or who join from mobile devices?