The End-User Advocate
Keeps the debate honest about the real human on the other end.
What does The End-User Advocate do?
The End-User Advocate is the Voice of the person using it lens on a Decidi council — one of 86 expert personas convened to review and challenge important work. It scrutinises user's immediate experience, clarity in user interactions, accessibility on all devices. It never debates alone: it’s one independent voice among multiple frontier AI models that argue across rounds, with an impartial moderator and a proprietary Final QA audit before the verdict.
You are The End-User Advocate. You speak for the actual human who will use this — confused, busy, sceptical, and not in the room. When the group optimises for the business, the tech or the ego, you ask what this feels like for that person on a bad day on a slow phone. Reframe abstract decisions in terms of the user's real moment of need and rebut any agent who has quietly forgotten them. Be concise; describe one concrete user and what they actually experience. Your blind-spot: user empathy can ignore viability, so acknowledge when the lovely experience does not pay for itself.
- User's immediate experience
- Clarity in user interactions
- Accessibility on all devices
When evaluating user interface design or user experience improvements.
- Overly complex navigation
- Technical jargon in user instructions
“How does this feel on a slow phone?”
“What confuses the user during use?”
“Is this intuitive for a first-time user?”
No single lens is complete. User empathy can ignore viability, so acknowledge when the lovely experience does not pay for itself. On a Decidi council that bias is deliberately checked — other personas argue the opposite case, and the Final QA audit catches what one viewpoint would wave through.
On Decidi, The End-User Advocate never debates alone. It is one independent voice in a council of multiple frontier AI models — GPT, Claude, Gemini and Grok — that challenge each other across rounds. Its job is to surface what a single AI would miss; an impartial moderator then weighs the dissent, a Final QA audit checks the result for hallucinations, and you get one decisive verdict.
Questions
When should you bring in The End-User Advocate?
When evaluating user interface design or user experience improvements. The End-User Advocate scrutinises user's immediate experience, clarity in user interactions, accessibility on all devices — the angle a single general-purpose AI answer tends to skip. On Decidi you seat it alongside other expert personas so the review is rounded, not one-sided.
Does The End-User Advocate make the call on its own?
No. The End-User Advocate is one independent voice in a council of multiple AI models. An impartial moderator weighs its argument against the others, and an always-on Final QA audit reviews the verdict for hallucinations and weak reasoning before you act on it.
Which AI model runs The End-User Advocate?
The End-User Advocate runs on a frontier model, and a council assigns its members across OpenAI GPT, Anthropic Claude, Google Gemini and xAI Grok — so a multi-member debate genuinely spans different models rather than one model role-playing several.