Talk to us

Technology

The technology under Seekprotocol

Three things make the platform. We know for certain that someone was at a place. We put digital objects on a real spot. And we use AI in the app, in the map and, next, in the data we deliver.

PresenceChecked by the server
A penguin character standing in a shopping street, seen through the app's camera
Spatial ARCapture from the app
AI visionObjects recognised

Proof of presence

In production

Knowing for certain someone was there

Every claim is checked by our server. The phone supplies data. The server decides.

  1. 01

    The device is real

    The phone proves with an attestation from its operating system that the unmodified app is running on a real device.

  2. 02

    The location is not faked

    Simulated locations and emulators are refused and logged.

  3. 03

    The distance is right

    The server measures the distance to the spot itself. Within 40 metres counts.

  4. 04

    The speed is human

    Someone who covers a kilometre in a few seconds is not walking.

  5. 05

    Once more at payout

    The same checks run again at the moment something of value is paid out.

The radius

40 metres, measured by the server

A reward can be claimed within 40 metres of its spot. The server adds 15 metres for GPS error and refuses everything beyond that.

40 m
Catch radius
15 m
Margin for GPS error
5 s
Between two attempts
2
Attempts per reward
  • 40 m catch radius
  • 15 m margin for GPS error
  • Accepted
  • Refused

What happens to a false claim

01

It is refused and logged

A faked location or an emulator gets no reward, and the attempt is recorded.

02

Attempts are limited

Each reward allows a small number of attempts, with a pause between them.

03

Repeat offenders are blocked

Accounts and addresses that keep trying are shut out.

Spatial computing

In production

Digital objects on a real spot

In the camera, a 3D object stands in the street, on the spot where our server placed it. It works on an ordinary phone or tablet, with no headset and no extra hardware.

A penguin character standing in a shopping street, seen through the app's camera
A cat in a cardboard box in the same street, seen through the app's camera
A Solana reward in the same street, seen through the app's camera
Captures from the app, on a street in Haarlem.

From server to street

  1. PlacedThe server picks a spot on a footpath.
  2. On the mapPlayers nearby see it appear.
  3. Walk thereThe app counts down the distance.
  4. Camera opensThe object stands in the street.
  5. ClaimedAfter the server's checks.
01

World tracking in the camera

The phone follows its surroundings frame by frame, so an object stays put while you walk around it.

02

Placed by the server

The server decides where something appears: on footpaths only, never on a motorway or in the water.

03

3D content per partner

Every coin has its own 3D character. Partners supply it through the portal and it goes live without an app update.

AI

AI in the app, the map and the data

We use AI in four places. Each one shows how far along it is.

Mobi, the assistant in the Seekprotocol app, as a coloured orb with two eyes

Mobi

An assistant you talk to

Mobi is the voice assistant in the app. It answers out loud and can operate the app for the player.

  • Find rewards nearby
  • Mark a reward on the map
  • Look up a wallet balance
  • Move and zoom the map
Example

Where is the nearest reward?

There is one 120 metres away, on the corner. I have marked it on your map.

In production

Mobi, the voice assistant

Players talk to Mobi. The assistant can find and mark rewards nearby, look up a balance and operate the map.

In development

Vision models for the 3D map

Vision-language models read street photos and work out where windows and details belong on a building front. Early work: the first building is on the map.

By invitation

Content checks

Texts and images in third-party quests pass an automatic content check before a person reviews them.

In development

Training data for vision models

Captures with a verified place and time, labelled and with faces removed. Meant for training models that need to recognise streets, shops and buildings.

Questions about the technology?

Ask the people who built it

We are happy to walk your team through the architecture.