A clean connector does not make a reliable agent
Connector correctness and agent behaviour are separate problems. Most teams only test the first one.
Jul 27, 20262 min read
Command Palette
Search for a command to run...
#ai-safety
Articles tagged with #ai-safety
Day 58: Why governance belongs in the architecture
Why governance belongs in the architecture, not in a document after launch.
Jul 19, 20263 min read
Day 57: Why retrieved content must stay untrusted
Why retrieved content must stay data, not become authority over the system.
Jul 18, 20263 min read1
Day 52: Why shared memory becomes a permission problem
Why shared memory becomes an access-control problem in multi-agent systems.
Jul 14, 20263 min read
Day 38: Why guardrails should enable safe action
Why guardrails should shape safe progress, not just block uncertain behavior.
Jun 28, 20263 min read
Day 37: Where human review actually belongs in AI workflows
Why human review needs timing, authority, and context to be useful.
Jun 27, 20263 min read