AI as event-aware character
AI Treasure Hunt: venue-wide discovery with AI clues
AI Treasure Hunt is a concept activation, built per occasion: teams scan objects, spaces or markers around the venue and a vision model validates what they found, while a language model writes the next clue and side missions. A QR fallback keeps the hunt running if vision is unreliable.
ConceptConcept, built for your event. We scope it, rehearse it with your team and agree a fallback.
The idea
The AI is a guide with a voice. Sociana already runs QR and image-scan hunts; this adds clues that adapt to the team. Points follow discoveries, difficulty and speed, and a venue-wide board shows progress.
How it runs on event day
- Attendee
- Reads a clue, walks to a marker or object, scans it and receives the next clue and any side mission.
- Operator
- Places the markers, writes the clue hints, sets difficulty and time, and can unlock a stuck team by hand.
- LED or venue screen
- A map of progress by team, a leaderboard and the current clue count.
Inputs and outputs
Inputs
- Markers or objects placed by the organiser
- Team camera scans
- Clue hints and difficulty settings
Outputs
- Validated discoveries
- Next clues and side missions
- Points by discovery, difficulty and speed
Moderation and fallback
Human approval. Clues are generated within the organiser's hints and the venue map, with an operator able to edit a clue before it ships. A stuck team can be advanced by an operator, and nothing sends people outside the marked zones.
If something fails
- A named operator can pause, skip or replay any round from the admin panel
- The hybrid QR fallback validates a marker by code when vision cannot confirm an object
- If the model is down, the pre-written clue chain runs from the organiser's list
Privacy and consent
Scans of venue markers and objects are matched on the device or by a vision model; no face is needed. Location is limited to the markers the organiser places, and team positions show on a board only if the organiser switches that on.
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: a vision model to validate scans and a language model for clues
- Scans per team and the number of markers
- 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
How is this different from the QR treasure hunt?
The QR and AR hunt is a standard feature and runs from fixed clues. The AI version validates objects with a vision model and writes adaptive clues. We keep the QR hunt as the fallback, so reliability does not depend on the model.
Can teams get lost or go somewhere unsafe?
Clues stay within the markers and the venue map the organiser sets, and the operator watches team positions on the board. Venue rules and safety briefing remain the organiser's responsibility.
Do we need markers?
Yes. Objects and markers are placed or chosen by the organiser beforehand and tested at the venue, because lighting and signal change what the vision model can confirm.
Want this on your screens?
Tell us the occasion and the audience. We will show you the activation running with your branding.