How Conto works
When an agent goes to pay, Conto checks the request against your rules first, pauses anything that needs a second look, and keeps a record either way. Conto decides what clears, not what your agents buy. Choose a managed wallet, let the agent keep its own key, or connect an existing card.
One control plane, from request to record
Every connected payment takes the same path. It comes in through your SDK or API, clears the same checks before it is sent, and ends up in one record you can reconcile. Managed wallets enforce the decision, and external signers must require it.
Conto
Every connected request is checked and scored before it is sent, then logged with full context.
Apply the owner’s limits, recipient rules, categories, and payment frequency.
Trust and risk scores on every counterparty.
Ask the owner’s authorized reviewers before execution.
A governed wallet identity for each agent.
From wallets Conto manages or wallets controlled by the agent.
Every payment reconciled with full context for finance, operations, and security.
Inside the control plane
See the full productPolicy Engine
Limits, categories, velocity, and counterparty rules, checked on every request before it settles.
ExploreNetwork Intelligence
Identity, past dealings, and a trust and risk score for every recipient.
ExploreApprovals
Anything unusual goes to a person with full context, by email, Slack, Telegram, or WhatsApp.
ExploreAgent Wallets
A wallet for each agent, held by Conto or by the agent itself.
ExploreAudit & Reconciliation
One record of every decision and payment, ready for finance and security to reconcile.
ExploreDeveloper Platform
SDK, REST, MCP server, and CLI to add these controls to any agent.
ExploreOne policy check, two execution paths
You pick who holds the keys. With a managed wallet, the wallet sends once the request clears. With self-custody, the agent keeps its own key and sends the payment itself, while Conto signs off first and records the result after. The policy check and the audit trail are the same either way.
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 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.
What teams build with it
Browse all solutionsInstant payouts
Pay people or move funds the moment work is done, with every payout checked before it goes out.
ExploreAutonomous procurement
Agents find suppliers and buy, while Conto controls who they can pay, how much, and when to ask.
ExploreRefunds & credits
Small refunds and credits clear on their own. Larger ones go for review.
ExploreVendor & counterparty controls
Known vendors clear. New, changed, or risky ones pause for a look.
ExploreMicropayments and x402
Per-call and per-session budgets for APIs, inference, and compute.
ExploreApproval routing
Routine spend keeps moving. High-value or unclear requests pause for a person.
ExploreMake your first policy-checked payment
Spin up an agent, wallet, and policy in the sandbox. It takes about ten minutes.