How to run your first AI moderated study with Mira — a quick walkthrough
A few people have asked how Mira actually works in practice, so wanted to write this up.
The full flow from start to finish:
1. Set up your study (5 minutes)
Choose a template — Customer Discovery, Concept Testing, UX, Brand Perception, NPS follow-up, and more. Or build your own discussion guide. Mira generates contextual follow-up questions automatically, so you do not need to script every question.
2. Recruit participants (built in)
Access 100M+ participants across 120 countries directly from the platform. Set demographic filters, screener questions, and Mira handles recruitment. No third-party panel needed.
3. Run the AI moderated interview
Participants join via link — no app download. Mira moderates the conversation, asks follow-up questions intelligently, and reads facial expressions, voice emotion, and eye gaze in real time during the session. Works on a standard webcam.
4. Get your report (minutes, not days)
Automatic transcript with speaker separation. AI themes, tags, summaries, and key quotes extracted automatically. Emotional signal overlaid on each moment. Full research report generated — executive summary, findings, evidence, recommendations.
5. Share and store
AI highlight reels for stakeholders — no one watches 40-minute recordings. Everything stored in a searchable research repository. Cross-study intelligence lets you compare findings across multiple projects over time.
The part most people ask about:
The emotional layer runs during the interview — not after. So when a participant says "I like it" but their face shows hesitation, Mira catches it and probes deeper in the same conversation. That is the core difference from transcript-only tools.
First study is free this month — happy to help anyone set one up. Drop a comment below or book here: https://www.entropik.io/book-demo?utm_source=producthunt&utm_medium=forum&utm_campaign=mira-jul2026
See Mira on Product Hunt: https://www.producthunt.com/posts/mira-the-ai-moderator
What type of research are you running? Happy to walk through how Mira would work for your specific use case.
Replies
Good work guys
Mira
@sunnymakar Thanks a lot!
Congrats on shipping this!! The emotional layer running live instead of after the fact is what stopped me, because so much of what people actually mean lives in the hesitation, not the words. I spend my days deep in the hiring world and the same thing holds there: the strongest signals are usually messy and easy to miss, not absent. How do you handle the moments where the face and the words disagree and Mira has to decide which one to trust?
Mira
@ceciliatran Thank you, and the hiring parallel is exactly right. The hesitation before "yes" carries more signal than the yes itself.
To your question: Mira doesn't decide which one to trust, that's the researcher's job. When face and words disagree, the report surfaces the disagreement: the clip, the transcript line, the emotional trace, and a marker flagging that the two signals split at that moment. Both are shown side by side with timestamps. No verdict, no winner picked.
What Mira does take a position on is duration. A one-second facial flicker during a considered verbal answer is weighted differently from a 6-second emotional hold that contradicts a polished close. The weighting metadata is visible, not hidden.
The philosophy is the same one you're describing in hiring, the messy signal is the evidence. The interpretation is still the human's call.