Typed intention stores let an on-device model beat the best published prospective-memory scaffold.

Prospective memory, carrying out a deferred intention at the right future cue, is schema-constrained state tracking, so the Prospective Intention Store puts lifecycle logic in code and leaves scoped language work to the model. On PM-Bench, where the best published scaffold reached 65.1% Set-F1, DeepSeek-Chat with PIS reaches 82.9% (arXiv 2609.01272). The number for local deployment is Gemma-E2B: 4.2% with no store, at most 6.6% with seven retrospective memories, 66.2% with PIS. Training-free, no fine-tuning, no distillation.