Mira - AI moderated interviews that read how people feel
by•
Unlike AI tools that stop at interview + transcript, Mira is a full AI researcher — plans studies, recruits globally (100M+ panel, 120 countries), runs dynamic interviews with intelligent probing, and uniquely captures what participants say AND feel via real-time facial coding, voice emotion AI, and webcam eye tracking.
Extracts themes, generates insights, and produces research reports automatically. 17 patents. 70+ languages. Trusted by Unilever, Nestlé and 150+ global brands. $25M Series B.
Replies
Mira
Hi Product Hunt 👋
I'm Lava, Founder of Decode by Entropik. We've been building AI that reads human behavior for 9 years and today, we're launching Mira, our AI Moderator.
Here's the problem every researcher knows but nobody talks about: people say one thing and feel another. It's called the Say-Do Gap. Self-reported data is filtered, rationalized, socially edited. Most research tools just accept this. We didn't.
Mira runs the entire research workflow, recruiting, moderating, analyzing, reporting, but uniquely captures what participants say AND feel in real time via facial coding, voice emotion AI, and eye tracking.
When someone says "I love it" but looks confused, Mira notices and probes deeper. Automatically.
Built on 17 patents. 70+ languages. Trusted by Unilever, Nestlé, and 150+ brands.
First study free with code PH20 → entropik.io/platform/ai-moderator
One question for the community: what's the most unreliable part of your current qual research process, and what would it take for you to actually trust AI to run it?
Drop it in the comments. I'll be here all day.
@productrambler What’s one concrete sign that your current qualitative insights are misleading, and what exact safeguards or transparency features would you need to see in an AI moderator before you'd let it probe participants or deliver final insights automatically?
Mira
@swati_paliwal Great question Swati, one we wrestled with a lot when designing the output layer.
A few concrete signs qual insights are misleading:
(1) unanimous positivity — if everyone loves it, your screener may be too narrow or the interview is not challenging enough; (2) verbal/non-verbal mismatch, someone says "I'd buy this" but their face shows confusion or disengagement; (3) vague themes without emotional backing, "ease of use" as a finding with no moments to support it.
On safeguards: Mira shows confidence levels on emotional signals (not just a single call), surfaces the raw emotional timeline so you can verify the signal behind any AI claim, and flags moments of mismatch rather than averaging them out. The AI summary is always a starting point, the original recording, transcript, and emotional data are there for the researcher to check and override.
We are firm that AI should make researcher judgment faster and better supported, not replace it. The final interpretation is always yours.
Intelli
@productrambler Congratulations Lavakumar on this launch. Mira I believe is the result of all the underground work you have been doing for the past 9 years.
How much cultural and local context have you created/designed it with i.e does it understand and differentiate accents + nuances of research candidates from Africa, Asia, Oceania etc or is it primarily designed for candidates from the Americas and Europe?
I believe the answer to the question above will be a determinant for many companies to actually trust AI to run their qual research processes.
"Captures what participants say AND feel" is the hard part most tools skip. I work with voice AI daily, and the transcript is the easy 20% — the signal that actually matters (hesitation, tone, the pause before someone says "yeah, it's fine") lives in how they said it, not the words. If Mira genuinely reads that layer at a 100+ panel scale, that's a real moat over "interview + transcript" tools. Question: how do you keep the emotional read from becoming false precision — do you surface confidence levels, or a single sentiment call? Congrats on the launch 🚀
Mira
@david_marko Thank you so much. Since our emotion AI is multi-modal, we use fusion techniques to make sure that false positive are taken care of and yes at raw level we do provide confidence level 😎
Mira
@david_marko Adding to what Sumit said - from a product perspective, the confidence level alongside the emotional call is exactly why we built the output the way we did.
The goal is to give researchers a richer signal to interrogate, not a verdict to accept. The transcript, emotional timeline, and raw clips are always there to verify or challenge what the AI surfaced. It is a tool to improve researchers' judgment, not a replacement for it.
How does the facial coding and eye tracking actually work in a remote setting without making participants uncomfortable or needing specialized hardware?
Mira
@layda138459 Everything runs in the browser — no app download, no plugin, no special hardware. Participants just allow webcam and microphone access when they join, same as any video call. Before the session starts there is a quick calibration check for lighting and camera positioning, which also helps participants get comfortable with the setup before the interview begins. The calibration doubles as a way to normalise the experience — by the time the actual interview starts, most participants have forgotten the camera is doing anything beyond a normal call.
Mira
@layda138459 Everything runs in the browser on a standard laptop or phone, no external hardware and nothing to install. Participants grant camera access upfront, run a short calibration, and the session feels like a normal video call from there.
If someone isn't comfortable on camera, they decline and still complete the study, with emotion read from voice and text instead.
Mira
Head of Data Science at Decode here.
The question we kept asking ourselves: how do you build an AI that understands the difference between what someone says and what they mean?
The answer is multimodal signal fusion — combining facial action units, vocal pitch, speech rate, micro-expressions, and gaze patterns into a single emotional signal per moment of the interview. Not post-hoc analysis. In real time, during the conversation.
The Voice Emotion AI specifically analyzes confidence, hesitation, excitement, and frustration from the audio layer independently of the transcript. Tone often carries a completely different story than words. That layer is invisible in every transcript-only tool.
17 patents cover the core methodologies. Happy to discuss the technical depth of any of these.
Mira
Senior Director of Consumer Insights at Decode here.
Speaking as a practitioner, the feature I find most useful day-to-day is AI highlight reels. Instead of asking a stakeholder to watch hours of recordings, Mira clips the moments that matter: where a participant's hesitation revealed unspoken doubt, where genuine excitement came through before they could temper it, where what they said and what their face showed did not match.
Those moments are what change decisions in a review meeting. And they surface in minutes, not days of manual review.
The AI Copilot is the other one worth knowing about: you can ask "which participants mentioned trust concerns?" or "show me everyone who reacted negatively to the pricing slide" across an entire study instantly.
For researchers here, what type of qualitative research do you run most? Happy to walk through how this fits your workflow.
How does the facial coding and eye tracking actually work in remote sessions without users installing heavy software, and does that introduce any bias from people who decline to turn on their webcam?
Mira
@memetsanayi As long as users are connected to internet, we don't require you to install any software. Everything happens right on the web browser. Without facial data, there in bias introduced as long as enough people allow us to use webcab. We have seen in our research that the data for emotion converges beyond a point, which means we will have reduced bias as more people take the test.
Mira
@memetsanayi Everything works right in your browser, so you don’t need to download anything or install plugins. Participants just allow camera access, do a quick calibration, and then the session begins. It uses the regular webcam on your laptop or phone. There is no facial recognition involved; we only measure expressions, not identity.
Camera access is always based on full consent. If someone chooses not to allow camera access, they can still take part in the study. In that case, we do not collect gaze or facial signals, but we still measure emotion using voice tone and text. Declining the camera just removes one type of signal, but it does not exclude the participant or reduce the sample size.
Mira
Hi all,
Marketing lead at Decode here.
I have spent the last few months working closely with this product to build the launch. The thing that struck me most: most AI interview tools stop at the transcript. Mira treats that as the starting point.
A few capabilities people miss: AI follow-up probing that automatically asks "why?" and "tell me more" mid-interview based on what the participant actually said. AI highlight reels that automatically pull emotional moments, so you do not have to share 40-minute recordings with stakeholders. Cross-study intelligence that finds recurring themes across multiple research projects over time.
The multimodal layer — emotion AI on top of the interview — makes findings more defensible. You are not just quoting a participant. You are showing what they felt when they said it.
Happy to answer questions about the product or how we built the launch.
How does the facial coding and eye tracking actually work in practice for remote participants, especially since webcam quality and lighting vary so much across users?
Mira
@ersinyzak1i75 We do not need a very high end webcam to run our models. In fact our model can run on almost all commodity webcams as long as there is good visibility of the face. We however guide the users to adjust face, lights before each session to make sure we capture good data.
Mira
@ersinyzak1i75 This is a great question and we hear this constantly from a lot of our customers during the initial stages. We have designed our system to work with all kinds of webcams, not just the best ones. Before joining, participants go through a quick calibration and environment check. Each video frame receives a confidence score, and we omit any weak frames rather than guessing. We never base our findings on a single video feed, since we combine signals from the entire group. Webcam gaze tracking is less precise than lab infrared, but for questions like whether someone saw a brand element or where their attention went first, it works well. Plus, it lets us study hundreds of real-world settings instead of just a few in a lab. We do not use facial recognition at all; we only measure expressions, not identity.
Mira
Product Manger at Decode here
One thing that always fascinated me about qualitative research: researchers don't just analyze what people say. They spend hours replaying interviews to understand how they said it.
A micro-expression of disgust at the pricing slide, a long pause before "I'd probably use it," hands that stopped moving the moment they said they were "comfortable."
That's the invisible layer of qual research. The part that turns a quote into an actual insight.
Mira is built around that gap, it conducts interviews in 75+ languages, probes emotionally in real time, and simultaneously captures vocal hesitation, facial emotion, and where attention went. So researchers stop losing those moments to memory and manual replay.
The goal isn't to replace researchers.
It's to give them superpowers, so they can spend more time discovering why people behave the way they do, instead of manually reviewing hours of recordings.
Happy to answer any questions about how any of this works.
How do i verify the accuracy of Facial coding and eye tracking?
Mira
@jitender_pankaj1 Our algorithms are trained and validated with millions of data points we collected over the years with our in house data collection and tagging platform. We ensure each tag has high inter rater reliability before accepting it in our dataset. Our eye tracking algorithms are frequently tested against the data from a physical eye trackers.