# Your agent pays from its own wallet, up to a daily cap you set URL: https://orla.finance/en/ai-agents Markdown twin of that page. Append `.md` to any Orla page URL to get one. Connect the agent you already run, give it a stablecoin wallet with hard ceilings or a card that holds only what you loaded, and keep the signature on the human side. #### It proposes. You sign Not a setting anyone can turn off. A new agent starts observing, and every write waits in the queue until you let it work. ##### Waiting for you A payment to Modal for 2,840 USDC came here because it is over the agent's daily cap; a Datadog charge of 410 dollars to file under Software came here because the agent that spotted it is still observing. Accept or reject; nothing in this queue expires on its own, however long it waits. - Every dollar a machine moved has a receipt: which agent, whose money, how much, to whom, and who decided, with the daily cap and what was left of it at that moment. A cap raised later does not rewrite an old receipt. ##### Freeze it, narrow it, send it back to observing - The drawer of one agent: what it has done, the spaces it reaches, its card, its wallet and its keys. Freezing stops the card and the wallet in the same click, and the history stays where it is. - A spend guard in Automations puts a monthly ceiling in USD on one agent or one supplier. Over it the agent is frozen together with its card, and only a person unfreezes it. ##### A key shown once, revoked on its own - A key is shown once and never again; revoking it takes effect on the agent's next call, and the agent's history stays under its name. #### Its own money, with a fence around it A wallet whose balance is the budget, a card whose balance is the fence, a ceiling per call; each refusal is logged with its reason. ##### A budget that cannot overdraw An EVM address and a Tron address, and the balance on them is the agent's whole budget: nothing stands behind it, so no mistake in any rule can spend more than you put in. Two ceilings sit beside it, one per request and one per day, and until both are set the agent buys nothing. - Sends go only to addresses the space already trusts; anything over the daily cap waits in the queue; the balance can be withdrawn by you and only you. - The agent can read its own fence before it spends: the daily cap, what is spent and what is left, the per-request ceiling and the hosts it may pay. You hear early too: once a day at 80 percent of the cap, and when the wallet falls under the level you named. ##### A card that cannot spend more than you loaded - The balance is the fence: what you loaded is all it can spend. A new card has no merchant rules or ceilings, so load only what the agent may spend; over the balance is declined. - By default the agent never sees the card number. You can hand it the numbers once: it reads the number, expiry and CVV one time, and asks again only after you save the form anew. What it already took cannot be taken back, short of blocking the card. ##### It can buy from pages that charge by the call - The page answers 402 with a price, the agent pays in USDC from its own wallet, and the content arrives. Over the per-request ceiling is refused, not queued, because the other side is holding a connection open; every call leaves a receipt behind. - The list of services it may pay holds hostnames and nothing else, and an empty list is a closed door. The first payment to a host pins the address that host is paid at; a quote naming another address is refused until you confirm the change yourself, checked against the host's own documentation. #### Three ways in, one set of rules Connect it observing, widen it when it earns that. Every call is checked against the grant, so it never does more than you could. ##### Name it, say what it is for Read the books and propose, pay by card, or pay in crypto: the choice decides what the drawer shows, not what the agent may do. Every permission still comes from the access you give it afterwards, and no role can sign a payment. - An MCP client, the CLI, an n8n flow or your own code over the API: the same agent, the same fence. ##### Or a client you already have - A Claude connector, Cursor, VS Code, Zed, Windsurf or the terminal reach the same server; the first question sends you to Orla's own consent page to tick which spaces it may reach. #### Where an agent can spend it Services that take a machine's payment without an account or an API key, with the price, the network and the source on every row. See /ai-agents/catalog. #### Rules in the code, not defaults that someone can change ##### Never - Signing a payment: It proposes, and a person signs; no role and no setting changes that. - Releasing an approved payment: Not by the agent that proposed it, and not by any other. - Widening its own limits: A change to its grant is a proposal in the same queue as everything else. - Paying an address it read in a document: A send goes only to an address the space already trusts, and only a person ever writes to that book. - Exporting its key: Shown once at creation, to nobody afterwards. ##### Only you - Trusting a new address: Written into the space's own address book by a person. - Withdrawing the wallet: The balance comes back to you on your signature. - Setting the two ceilings: Per request and per day; unset means closed, not open. - Opening a host: The agent can search the catalogues and ask; only your Allow puts a host on its list. - Changing where a host is paid: The first payment pins the address; a new one counts only after you confirm it by hand. - Freezing it: The card and the wallet stop in the same click, and the history stays.