Posted on Oct 5 ## Sidekick part 4: safety as honestly labeled ceilings ## Sidekick Part 4: safety as a stack of ceilings, each honestly labeled Most agent safety I've seen is a paragraph in the system prompt: "be careful with destructive commands." Small models ignore system prompts — we established that in Part 2. So Sidekick's safety model assumes the model will disobey and enforces the boundaries in code instead. This is Part 4: approvals, hard refusals, egress control, and the audit ledger — plus the ceilings, stated rather than hidden. ## Layer 1: approval sets, enforced in the…