Agent Engineering
Permissions & Safety
What can an Agent do — and what should it not? Switch between three permission modes and observe how the same set of actions is handled differently.
Choose Permission Mode
Confirm Mode Default
Every dangerous action requires user confirmation
Auto Mode Dangerous
All actions are executed automatically with no confirmation
Smart Mode Alice
An LLM classifier assesses risk level and handles each action accordingly
Scenario Simulation
| # | Action | Tool Metadata | Risk Assessment | Result |
|---|
Select a permission mode → click Run → observe the difference
Three Design Decisions
📌 Design Decision 1: The core tension in permission design is safety vs. efficiency. Every confirmation dialog interrupts the user flow, but skipping confirmations risks irreversible damage. Which does your product choose?
📌 Design Decision 2: Alice's "Smart Mode" uses an LLM to assess risk, but LLM judgments can be wrong. A single misclassification could delete user data. Is this a risk you can accept?
📌 Design Decision 3: "Read-only" and "destructive" are tool-level flags. It's the PM's job to decide which risk tier each tool belongs to — this is a product decision, not something you can hand off to engineering.
Takeaway
Takeaway The essence of Agent permission design is finding the right balance between safety and efficiency: confirming everything is safest but slowest; allowing everything is fastest but most dangerous. Alice's approach is to use AI to assess risk level — low-risk actions are auto-approved; high-risk actions are intercepted for confirmation.