Fusion

Fusion turns one prompt into a panel. The question goes to several models at the same time, each answering independently — with web search and bash, and with no knowledge of the others. Then Opus 4.8 (this very session — the orchestrator) reads every answer, extracts the structure of the panel's reasoning (what they agree on, where they conflict, what only one saw, what they all missed), and writes a final answer grounded in that analysis.

The whole mechanism is independence, then synthesis. The diversity that makes a panel beat a single model is harvested, not manufactured: running the same prompt independently yields different reasoning paths, tool calls, and sources. So there are no assigned "lenses" or personas — every panelist gets the user's task verbatim and answers it straight. (See references/panel.md.)

One hard rule: Opus 4.8 always judges and writes the final answer — the pipeline can't be reversed. The panelist models can't call back out to spawn Opus, so Opus is always the driver. The slug reads driver-first for that reason.