Is this simply a chatbot with a face?

Only if it is built badly. The value comes from the transactions behind it, checking eligibility, reading a document, issuing a ticket, booking a slot. Without those integrations an avatar is decoration.

Do you store visitors' faces?

By default, no. Where verification is legally required we process and discard, and any retention is an explicit, documented decision with a lawful basis behind it.

Government & Public Sector · Video agents & reception

Digital service counters for citizens

A face-to-face digital representative on a kiosk, branch screen or the web.

Book the Data Foundation Assessment

Walk-in wait timeSelf-service completionCounter load per staff memberVisitor satisfaction

The problem

What this fixes

Service centres still absorb visits that could be completed without a counter, and the people who most need help, those with a complex or exceptional case, wait behind routine transactions.

An avatar-led agent that greets, verifies, explains and routes, on branch kiosks, hospital and hotel receptions, government service counters and web sessions. It combines speech, an on-screen persona and document handling, and hands to a live human video call when the case needs one.

Government & Public Sector

Guided service completion

Eligibility explained and the transaction completed at the kiosk or online in Arabic or English.

Government & Public Sector

Document intake and checking

Uploads validated on the spot so a visitor is not sent home for a missing page.

Government & Public Sector

Accessibility as a requirement

Audio-first, large-type and sign-language modes for public services that must serve everyone.

Government & Public Sector

Escalation to a case officer

Exceptional cases go to a named officer on video with the full history attached.

In this sector

Where it earns its place

Delivery

How we build it

Foundation check

Before any build

We inspect the systems, the data behind them and the quality of the records this capability will depend on, then write down what has to be fixed before anything is built.

Narrow first release

First release

One workflow, one team, real traffic, measured against the baseline we captured before we started.

Controls and evaluation

Runs in parallel

Guardrails, approval gates, evaluation sets, logging and the evidence pack your auditor and your regulator will ask for.

Scale and hand over

After sign-off

Additional workflows, sites or languages, then runbooks and training so your team can operate it without us.

Data foundation

What has to be right first

Service catalogue and eligibility rules written down and owned.
Queue and appointment systems reachable by API.
A lawful basis and retention rule for any biometric or video capture.

Controls

Guardrails and KPIs

A human owns every consequential decision

Agents draft, route and execute reversible steps. Anything that moves money, changes a record of consequence or affects a person's rights stops at a named human approver with the reasoning attached.

Every action is logged and replayable

Inputs, retrieved context, model version, output and the human decision are written to an immutable log, so an auditor can reconstruct any single interaction months later.

Data stays where your regulator requires

In-country, in-region or on-premise deployment, with the model portfolio right-sized to the workload instead of routing everything to a frontier endpoint abroad.