kept using AI for actual decisions, not "write my email" but real ones like whether to take a contract or an idea worth building, and i realized the answer just depended on which model i happened to open. one says go, one says wait, one hedges. i wasn't getting an answer, i was getting one model's opinion in a confident voice and treating it like it settled things.
so i built the opposite. you give it one hard decision and five different models (claude, gpt-5, gemini, grok, qwen) each argue it from a locked role across three rounds, then you get one verdict with the disagreements kept visible instead of smoothed into a safe average. the disagreement turned out to be the actual signal, the one model that broke from the pack was usually pointing at the thing i'd skipped.
it went live on the App Store this morning, which still feels unreal. free to start: https://apps.apple.com/us/app/war-table-ai-council/id6780293764
genuinely curious what people here think though, do you trust the disagreement between models more than the consensus, or is that just reading signal into noise?
[link] [comments]