Category Rule Policy
A category policy defines what agents may buy — by spend type. Here's the template and the enforcement.
The policy
Allowed categories with limits: [CATEGORY — limit].
Blocked categories: [LIST].
Flagged categories above threshold: [LIST].
Default for unspecified categories: [allow / block / flag].
Enforcement
Each category maps to a category rule; transactions outside policy get BLOCKED or FLAGGED.
Policy → rule
{
"category_rule": {
"data": {"action": "allow", "daily_max": 200},
"compute": {"action": "block"},
"default": "flag"
}
}
The policy becomes decisions.
FAQ
What's a good default for unspecified categories?
FLAG — it catches drift without blocking everything.
How often to review?
Monthly, or when agents change roles.
Related
Stop the next $12,400 night.
One API call (or MCP tool) in front of every agent transaction — APPROVED, BLOCKED, or FLAGGED, deterministic, ~5 ms, fully logged.
See plans — from $99/mo Try a live check