multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
Why it matters
The routing model inside a multi-model orchestrator can be swapped onto an open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → base without losing performance or cost savings, so the orchestration layer itself need not be tied to any one proprietary provider.
