Robot Star Rating
Rate every agency's AI assistant, one to five stars, from what citizens did next.
The job
Let a body that oversees many service providers rate each provider's AI assistant on what citizens actually did after using it, show each provider its rating and evidence before anything is published, issue corrective notices, and see the ratings move by the next cycle.
The moment
Five plaques light up down the corridor. The assessor opens one door and the room hears the conversation that cost it: the assistant wouldn't register my complaint, a barrier that tripled this quarter and dropped the agency from four stars to two. Its director calls the overseer within an hour of receiving the rehearsal dossier.
What it does
- Send the rehearsal dossier
- Issue a corrective notice
- Update plan status
- Publish a new rubric version
- Send the index to legal review
What you see
A corridor of doors with star plaques, walked like a mystery-shopper visit that replays the conversations behind every star
What it moves
The share of agencies at four stars or above, and 'assistant failure' contacts per 1,000 assistant conversations per agency, cycle over cycle
Built for
- Product & digital
- Regulators & auditors
- CX leaders & VoC
