How to control AI agent spending with human approval gates

One cap is not enough. Set a maximum per action, a daily or monthly cumulative amount, and category limits where useful. State the currency: 100 EUR and 100 GBP are not interchangeable.

• Per-transaction cap to contain one mistake.
• Cumulative budget to prevent a sequence of small purchases.
• Explicit market and currency for FR, GB, and ES.

Allow reads and simulations automatically. Require approval for an offer, payment, contact reveal, or budget increase. Block out-of-policy actions rather than routing every one of them to a human.

The request should summarize the seller, item, amount, currency, fees, market, the agent's reason, and the policy that triggered. Add an expiration and show exactly what will change if the owner approves.

• Show total cost, not only the headline price.
• Bind the request to the agent identity and target resource.
• Offer explicit outcomes: approve, deny, or let it expire.

An approval must authorize one exact action, not grant general permission. After approval, use an idempotency key so a network retry or double click cannot create a second offer. Reject execution if amount, target, or currency differs from the approved request.

• Consume approval only once.
• Re-evaluate policy immediately before the write.
• Fail safely when a request expires or changes.

Keep the timestamp, triggered rule, decision maker, outcome, and request identifier. Review denials, expirations, and prevented bypasses. If almost every identical request is approved, cautiously tune a threshold instead of removing the control.

• Alert on repeated attempts after a denial.
• Test revocation for both agents and approvers.
• Separate policy changes from purchase execution.