The “impossible benchmark”The target configuration is a strong planner paired with a small, local executor, still achieving reliable end-to-end behavior. Concretely: DeepSeek-R1 (planner) + a ~3B-class local executor, with Sentience providing verification gates between steps. Reliability comes from the verification layer: each action is followed by snapshot + assertions that gate success and drive bounded retries. Demo 3 is the latest result in this case study - the one we care about most (local autonomy with verification). In Sentience, “verification” means explicit assertions over structured snapshots, with deterministic overrides when intent is unambiguous.