When a persistent personal agent should lose access
Persistent agents need access rules that respond to elapsed time, inactivity, account changes, and completed work.
Super Genius Labs Editorial · Sep 12, 2026 · 6 min readTracing authority through AC2’s user-controlled signing flow
Trace AC2 signing from reviewed request to execution evidence while keeping credential custody and protocol limits explicit.
Super Genius Labs Editorial · Aug 29, 2026 · 4 min readWhere to place the trust boundaries for shared agent memory
Persistent memory can carry influence across agent runs. An SGL decision map separates storage, provenance, retrieval, authority, and recovery so one session boundary does not bear the entire security model.
Super Genius Labs Editorial · Aug 16, 2026 · 5 min readTreat agent evaluation sandboxes like connected production systems
A sandbox label does not describe every reachable system. Review egress, intermediaries, credentials, blast radius, kill authority, forensics, and notification before the run.
Super Genius Labs Editorial · Aug 5, 2026 · 6 min read