Trigger
An agent proposes a typed payment, purchase, refund, payout, or vendor action before provider execution.Agent spending caps
Enforce agent spending caps before payment.
Use one financial policy to permit routine spend, hold an exception for approval, and deny a payment that breaches the hard cap.
What breaks
Routine spend, reviewable exceptions, and true cap breaches collapse into the same path, leaving the agent or prompt to police its own authority.Control point
Evaluate the exact principal, operation, amount, currency, rail, approval threshold, and live budget before execution is allowed to start.Live flow
Follow the action through the decision.
The walkthrough below is native page UI: proposal, policy facts, decision, and the point where the customer-owned executor continues or stops.
Proposed action
The agent proposes a vendor payment
$75.00 USD- Operation
- pay_vendor
- Principal
- spend-agent
Policy check
Financial policy checks authority
- Per action
- $100 hard cap
- Review above
- $50
- Monthly
- $1,000
Decision
Return an explicit effect
Execution
The provider call waits
Only a currently authorized action can reserve live budget and reach the payment provider.
How it works
- 01Configure
Set the hard and human boundaries
Choose the agent, operation, rail, currency, per-action cap, rolling budget, and the amount above which a named reviewer must approve.
- 02Evaluate
Submit the payment without executing it
Create typed financial actions with execute set to false so policy, evidence, eligibility, and current budget are checked before any provider call.
- 03Hold
Separate exceptions from breaches
Routine spend can be authorized, an in-policy exception can wait in the approvals queue, and a hard-cap breach is blocked immediately.
- 04Execute
Recheck before money moves
Approved actions are re-evaluated against current policy and live budget before the financial service reserves funds and calls the configured provider.