Agent-to-Agent USDC Payment Workflow
Coinbase AgentKit flow: a human allocates a USDC budget, the agent authenticates its Base wallet, pays an x402 invoice and processes the supplier data, with no fiat in the path.
Coinbase Trust Flow — On-Chain Settlement
The trust layer behind agent-to-agent payments on Coinbase: the agent initiates the spend, the transaction is broadcast, the block confirms and the payment finalizes on-chain.
Full FlowZap Code
Copy and paste the following FlowZap code into a project in your FlowZap account to see this template diagram.
agent_env { # Agent & Wallet
n1: circle label:"Agent Initiates Spend"
n2: rectangle label:"Wallet Enforces Policy"
n5: circle label:"Payment Finalized"
n1.handle(right) -> n2.handle(left)
n2.handle(bottom) -> base_ledger.n3.handle(top) [label="Broadcast Tx"]
}
base_ledger { # Base Blockchain
n3: rectangle label:"Process USDC Transfer"
n4: rectangle label:"Update Ledger State"
n3.handle(right) -> n4.handle(left)
n4.handle(top) -> agent_env.n5.handle(bottom) [label="Block Confirmed"]
}
Install the MCP packagenpm install -g flowzap-mcpMCP documentation
Related templates
Stripe Trust Flow — Fiat Authorization
The trust layer behind agent-mediated payments at Stripe: the agent submits a shared payment token, the risk engine approves it and fiat clears through the banking rails.
Agent-Mediated Fiat Payment Workflow
Stripe Agent Toolkit flow: the consumer approves an agent spend, the agent requests a scoped token, passes it to the merchant and the order completes in fiat.
Agentic Commerce Checkout Architecture
Five-lane architecture for agent-driven checkout: merchant edge, commerce services, payment stack, fulfillment and the approval gate before an order is authorized.
Multi-Platform eCommerce Integration Hub
n8n as the central integration layer: one workflow decides whether an event is a product sync or an order, routes it to the right channel and closes the loop.
AI Product Sync Pipeline Workflow
Product sync between platforms with an AI agent in the middle: field extraction, category mapping and schema normalization before the write-back returns 200 OK.