Sealevel's parallel execution scheduler, slot by slot. Toggle hot-account contention to see how a single popular writable account collapses eight parallel waves into eight serial queues. Each row is one execution wave — transactions in the same row settle simultaneously.
Solana agents get 400 ms — but only if they declare every account they'll touch before execution starts. The Sealevel write-lock model, hot-account contention, Jito tip economics, and what the declarative execution contract means for AI agent design.