Ask several models the same question in one thread and compare their answers side by side.
For questions where you actually want a second opinion, Council sends one prompt to several models at the same time and streams every answer into the same thread.
It is most useful when models disagree. Two strong models reaching different conclusions tells you something a single confident answer never would — usually that the question is underspecified.
You can save a Council line-up you like and reuse it, so a comparison you find useful becomes a habit rather than something you reassemble each time.