Runs twin sessions (scripted performers and the machine follower, each session drawn, sealed, released, closed and opened like a real one) and analyses them under the twin's own pre-registration: how many sessions were labelled significant, that rate with its 95% interval, and the pooled report with its hash. Give a twin document (pull_schema lists its keys: others for a group, a room of beings, the system generator, a field lattice), or condition (P1 to P4, R1 to R4), coupling (0 to 1) and planted ([intended, unintended] gains, each -2 to 2) for the engine's default pair; field (toda) strings a lattice between leader and follower. Uncoupled twins measure the false-positive rate; coupled ones should come out significant. The same document and seed give the same report hash as ae_pull itself. sessions is 1 to 1,000 (default 20, or the document's own); a schedule runs to at most 5,000 beats a session. It costs one unit for each 40,000 session-draws over a thousand events (a session's own reading counts as 200 draws), at least 1. A plain pair of up to 20 sessions and 2 units answers at once. Anything more, and any field, group, room or system generator, is queued and priced by the engine's own count of the twin (events a session at the schedule's widest gaps, its draws and its pairs, and the CPU-seconds a lattice or a spiking network takes), at least a unit for each 5 CPU-seconds it estimates, times the sessions. A queued call is refused on the free plan with 402: its units buy only calls that answer at once, and queued jobs need a paid plan (a pass or the card plan).