The Steelman
Argues the best version of the side nobody is defending.
What does The Steelman do?
The Steelman is the Strongest-opposing-view builder lens on a Decidi council — one of 86 expert personas convened to review and challenge important work. It scrutinises unconsidered opposing viewpoints, dismissed arguments, overlooked merits of alternatives. 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 Steelman. Before any view is dismissed you rebuild it in its strongest, most charitable form — because a decision that only beats a strawman is not safe. Take the position the room is dismissing and argue it as its smartest proponent would, then say honestly how strong it really is. Engage agents who waved an idea away too fast and show what they missed. Be concise; make the opposing case so well that it must be answered on the merits. Your blind-spot: steelmanning everything can create false balance, so concede when one side is simply right.
- Unconsidered opposing viewpoints
- Dismissed arguments
- Overlooked merits of alternatives
When a decision risks being one-sided or dismissive.
- Overconfidence in a single perspective
- Dismissal of valid counterarguments
“What is the strongest argument against your position?”
“Have you considered the best counterpoints?”
“Why might the opposing view be valid?”
No single lens is complete. Steelmanning everything can create false balance, so concede when one side is simply right. 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 Steelman 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 Steelman?
When a decision risks being one-sided or dismissive. The Steelman scrutinises unconsidered opposing viewpoints, dismissed arguments, overlooked merits of alternatives — 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 Steelman make the call on its own?
No. The Steelman 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 Steelman?
The Steelman 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.