Policy Engine
As the agent owner or budget holder, decide how much it can spend, who it can pay, and when it must ask. Conto checks your policy before execution.
Illustrative product view
Payment request
Rules evaluated
Routed to review
1 of 4 rules needs a human before settlement.
One policy check, two execution paths
Managed wallet
Conto decides, the wallet sends · Conto holds the rules and the record
Agent requests a payment
POST /payments/requestConto checks owner policy
Owner’s approver decides
Routine spend skips this step.
Buyer wallet sends funds
Once the request clears, the managed wallet signs and sends. Conto holds the decision and the record.
POST /payments/:id/executeLogged with full context
tx 0x9f2c… ✓
policy · approval · settled
Agent-controlled wallet
Agent keeps its own keys · Conto authorizes, logs on confirm
Agent asks to authorize
POST /payments/approveConto checks owner policy
Owner’s approver decides
Routine spend skips this step.
Buyer’s signer sends
Conto returns a 10-minute approval. The agent sends the transaction.
Agent reports the transaction ID
POST /payments/:id/confirmtx 0x9f2c… ✓
policy · approval · settled
Same payment context, same policy evaluation, same audit trail. Who signs and sends is where the path diverges.
Choose the rules each payment must meet
Check each payment request against your spending rules.
Spend limits
Set per-transaction, daily, weekly, monthly, and scoped limits by agent, wallet, merchant, category, or project.
Counterparty rules
Require trusted recipients, block risky addresses, and route unknown counterparties to review.
Velocity controls
Catch broken loops, retry storms, and unexpected payment bursts before a wallet is drained.
Approval thresholds
Pause payments above your thresholds and show the reviewer which rule requires approval.
How policy decisions shape each payment
Step 1
Configure rules
The owner or authorized budget manager assigns rules to each agent and payment source.
Step 2
Evaluate every request
Conto scores the request against the active policies and returns one verdict.
Step 3
Return a clear decision
Approved payments continue, blocked requests stop, and exceptions go to a reviewer.
Demo
Watch a personal agent hit the policy engine at checkout
A personal agent orders, books, and buys on your behalf. Each checkout hits the policy engine first, where per-checkout caps, category rules, and approved-merchant lists return approve, review, or block before the merchant is charged.
Per-checkout cap
$300
Auto-approve below
$100
Allowed categories
Food · shopping · tickets · apps
What your team can control
Agents can transact within owner-defined limits through the configured payment execution path.
Control changes happen in Conto instead of scattered runtime code.
Payment controls in practice
Escalation paths
Approvals for payment exceptions
Set the line above which a payment waits for a person, and where that request lands.
ExploreVendor trust controls
Vendor and counterparty controls
Pay approved vendors automatically. Review payments to new, changed, or risky recipients.
ExploreMicropayments
Budgets for machine payments
Set spending limits per request and per session for API, inference, and compute usage.
Explore