AI as judge
AI Pitch Judge: sell the impossible in 30 seconds
AI Pitch Judge is a concept activation, built per occasion: a participant draws a random product, audience and constraint and pitches it in 30 seconds. A speech model transcribes the pitch and a language model scores clarity, originality, persuasion, structure and filler words, then gives a short, light verdict.
ConceptConcept, built for your event. We scope it, rehearse it with your team and agree a fallback.
The idea
The AI is the judge, and the humour comes from a verdict that is specific to what was said. Sales and leadership teams get a quick, low-stakes pitching drill, and the best pitches can play on the LED wall.
How it runs on event day
- Attendee
- Gets a card, speaks for 30 seconds into a phone or kiosk mic, then sees a scorecard and the verdict.
- Operator
- Writes the product list and constraints, picks which scoring lines show, reviews any pitch before it plays on the wall, and can override a score.
- LED or venue screen
- A countdown during the pitch, then the scorecard and verdict, with the day's best pitches in a leaderboard.
Inputs and outputs
Inputs
- Random product, audience and constraint from the organiser's list
- A 30-second voice recording
- Participant identity
Outputs
- Transcript and a scorecard on five lines
- A short verdict
- Points to the leaderboard
Moderation and fallback
Human approval. Scores are advice shown with the transcript, an operator can override them, and no pitch plays on the wall until it is approved. Verdict wording is limited to the organiser's approved tone, so it stays kind.
If something fails
- A named operator can pause, skip or replay any round from the admin panel
- If transcription fails, the participant can type the pitch and the language model scores the text
- If the model is down, a human panel scores from the same five lines on a tablet
Privacy and consent
The microphone opens only after a consent tap. Speech is transcribed for the round; the recording is not kept unless the organiser configures it and the notice says so. A typed-answer mode is the alternative for anyone who prefers not to speak.
Under India's Digital Personal Data Protection Act, 2023 the organiser decides the purpose and the retention period, and Sociana configures the consent notice, the withdrawal route and deletion on request. Collect only what a round needs. Details sit on the data protection and AI pages in the trust centre; nothing here is a legal opinion. See responsible AI, data protection and DPDP and Smart Lens and biometric consent.
What drives the cost
Price band: ₹35,000–₹75,000 per activation per occasion, ex-GST (add-on menu). Per-completion model costs are quoted on actuals at proposal; no per-completion rate is published.
- Rounds per day times players per round, since every completion triggers one or more model calls
- Model mix for the round: speech-to-text and a language model
- Minutes of audio transcribed, which scales with participants and rounds
- Peak concurrency, which sets queueing and the number of kiosks or tablets
- Retention of outputs: replays, galleries and downloads add storage and moderation time
- Rehearsal and operator time on site; kiosks, tablets, cameras and LED walls come from the venue or a hardware partner, not from Sociana
Questions people ask
Is the voice recording kept?
Not by default. The recording is used to produce the transcript for the round, and storage is set per occasion in the consent notice. A typed pitch is available for anyone who prefers not to speak.
Can the AI score be wrong or unfair?
Yes, and that is why the verdict is advice. An operator can override a score, a human panel can replace the model, and the scorecard lists what it measured so players can see why.
Is this a recruitment tool?
No. It is a light event game and the scoring is not for hiring or appraisal. The organiser should not store or reuse the scores for HR decisions.
Want this on your screens?
Tell us the occasion and the audience. We will show you the activation running with your branding.