Problem
Agents cannot tell a harmless action from a consequential one. Deleting an account and renaming a list look the same in an API reference.
Context
Use this pattern when:
- Your product mixes routine and high-stakes actions.
- Agents and their operators want to apply policies (approval, logging, limits) based on risk.
Recommended solution
Assign every action a risk level and machine-readable attributes: reversible or not, involves payment, shares personal data, affects other people. Publish these in the manifest so agents can plan, and enforce corresponding policies server-side.
- 01Define a small risk vocabulary (read, low, medium, high).
- 02Tag actions with attributes: reversible, financial, personalData.
- 03Publish attributes in the manifest.
- 04Enforce policies server-side regardless of agent behavior.
Interaction diagram
Example implementation
Illustrative exampleExamples use a fictional store and illustrative field names. Adapt the shape to your stack; the qualities matter more than the exact format.
{
"name": "delete_account",
"description": "Permanently delete the account and all associated data.",
"risk": "high",
"attributes": {
"reversible": false,
"financial": false,
"personalData": "deletes",
"affectsOthers": false
},
"requiresApproval": true,
"agentAllowed": false
}Accessibility and security
Accessibility
- Use the same risk language in UI confirmation dialogs so the mental model is consistent for everyone.
Security
- Some actions should not be available to agents at all; say so explicitly with agentAllowed: false.
- Risk labels inform agents, but enforcement must not depend on agents honoring them.
Related patterns
TrustHuman ApprovalPause consequential actions until a person confirms, with a self-contained summary of what will happen.DiscoveryCapability ManifestPublish a single machine-readable document that lists what agents can do with your product.RecoveryRollbackProvide compensating actions so completed steps can be undone when a later step fails.
Applies the principles Clear Permissions and Progressive Autonomy.