Skip to content
Lootrunners
Small blast radius

Assume an agent can fail. Limit what failure can cost.

Two layers, always. Business policy is the rich semantic layer — purpose, vendors, projects, approval tiers. Hard wallet and provider controls are the last line of defense if the application or agent behaves unexpectedly.

S·01
Bounded authority

Every autonomous dollar belongs to a Mandate — job, budget, vendors, time window, and approval rules.

S·02
Hard limits

Critical ceilings mirror into wallet or provider controls where supported — enforced below the application.

S·03
No self-escalation

Agents cannot raise their own budgets, change policy, or approve exceptions. Credentials are scoped to requesting spend.

S·04
Real freeze

One action stops new spend, pauses agents, and revokes available hard permissions — then shows you exactly which revocations succeeded.

The signature moment

"You are giving Research Runner permission to spend up to $50 USDC every 24 hours until August 20. Lootrunners can apply stricter rules, but it cannot use this permission to exceed that limit."

No wallet signing prompt ever appears before this plain-English explanation.

Operational safeguards
Least-privilege database roles, deny-by-default row security
Step-up auth for freeze, revoke, and policy changes
No raw private keys in application config
Deterministic audit log — every decision links to its rule
Custody and signing shown explicitly per connected account

Start risk-free on testnet.

Test agent payments with fake funds before giving them access to real money.

Try the sandbox
© 2026 LootrunnersHomeDevelopersPricing