Permission Models

Permission models apply the principle of least privilege to agents: each agent receives only the access it needs to complete its assigned task, nothing more. This topic appears after the autonomy spectrum in the learning sequence because you cannot design meaningful permissions until you know what level of autonomy you are granting. An agent that only reads files needs a very different permission boundary than one that writes to a database or calls external APIs, and the cost of getting it wrong scales with the autonomy level: a highly autonomous agent with overly broad permissions converts any prompt injection into a system-wide breach.