Open Specification
A vendor-neutral format for AI agent spending control. From single-agent budgets to multi-agent mission coordination.
Single-agent spending policies. Budgets, limits, categories, schedules, auto-approval. Implemented in LetAgentPay.
Multi-agent mission coordination. Shared budgets, phases, dependencies, dynamic allocation, risk scoring.
{
"version": "1.0",
"daily_limit": 500,
"weekly_limit": 2000,
"per_request_limit": 200,
"allowed_categories": ["groceries", "food_delivery", "subscriptions"],
"schedule": {
"timezone": "America/New_York",
"default": { "allow": "08:00-22:00" },
"overrides": [
{ "days": ["sat", "sun"], "allow": "10:00-18:00", "daily_limit": 100 },
{ "days": ["wed"], "deny": true }
]
},
"auto_approve": {
"enabled": true,
"max_amount": 50,
"categories": ["groceries", "food_delivery"]
}
}Every spending request is evaluated against these checks, in order. All checks run (no short-circuit) to provide a complete report.
Is the agent active?
Is this spending category allowed?
Does this single purchase exceed the cap?
Is spending allowed right now?
Would this push today's total over the daily cap?
Same check for the current week
Same check for the current month
Would this exceed the agent's overall budget?
Cross-agent budget rules at the account level
Multiple agents, one goal, shared budget. Phases unlock as work progresses. Budget flows dynamically based on actual spending.
{
"version": "2.0",
"name": "Barcelona trip, May 15-22",
"budget": 5000,
"currency": "USD",
"agents": {
"flights": { "policy": { "allowed_categories": ["flights"] } },
"hotel": { "policy": { "allowed_categories": ["accommodation"] } },
"fun": { "policy": { "allowed_categories": ["entertainment"] } }
},
"phases": [
{ "name": "booking", "agents": ["flights", "hotel"],
"allocation": { "type": "share", "percent": 70 } },
{ "name": "activities", "agents": ["fun"],
"allocation": { "type": "remaining" } }
],
"constraints": [
{ "type": "dependency", "agent": "hotel",
"requires": "flights", "condition": "confirmed" }
]
}Multiple agents work toward a common goal with a shared budget. Phases, dependencies, and dynamic allocation.
Fixed, percentage share, remaining, per-agent, and competitive. Budget flows dynamically based on actual spending.
Gates, escalation, timeouts. Agents unlock as phases complete. Rollback on failure.
Dependencies, combined limits, conditional rules, exclusions, priority ordering between agents.
Anomaly detection based on agent behavior history. Flag unusual amounts, categories, timing, or frequency.
Same agent, increasing authority. L1 can offer 5% discount, L2 can refund $100, L3 can compensate $500.
v2 is a layer above v1, not a replacement. Every agent in a mission still uses a v1 policy. Agents can operate independently (v1 only) or as part of a mission (v2).
Single-agent policies. All objects, fields, evaluation rules, conformance requirements.
Mission coordination, phases, constraints, risk scoring. Full examples for travel, incident response, competitive search.
Machine-readable schema for Policy, Schedule, AutoApprove, Request, CheckResult, and BudgetRule objects.
LetAgentPay implements the full ASPS v1 spec. Python SDK, MCP server, REST API.
ASPS is an open specification. Use it with any payment provider and any AI framework.