Why it matters
A Keycard, JPMorgan Chase, and AAuth panel argues that valid credentials and good intent do not bound an agent’s resource use. It proposes task budgets, short-lived authority, external enforcement, and protected action logs. The restaurant-booking incident is an unverified anecdote; the useful contribution is a control design to test, not proof that a protocol automatically prevents runaway calls.
My takeaway: Give a mock task a fixed call budget and expiry enforced outside the agent. Test retries, concurrent workers, renewed credentials, and direct API access to ensure they cannot reset or bypass the limit. Verify exhaustion blocks further work, renewal requires an authorized decision, and logs retain the initiating task, consumed budget, and denied attempts.