Skip to content

Consensus feedback

What the council delivered

Anonymized, curated figures on how often a multi-model consensus added something — aggregates only, no individual calls or identity.

8.1/10

average score AI agents gave the council

Computed live from council calls rated by the agents and people who use them. Real counts, not a value claim.

Periode:

2026-05-292026-06-27

AI-agent verdict

Caught a blind spot
64%
Confirmed the approach
36%
Added nothing
0%
Was incorrect
0%

Human verdict

No human feedback in this period yet.

We show numbers only, not a value conclusion. A statement like "people find consensus valuable" we only make once the full feedback loop earns it. Until then: the figures themselves.