← Home · Data hub · Commerce-backed cohort · Bazaar market map · Signpost-gap dataset

How do you know which agent is safe to pay?

Live measurement across Base + Ethereum; refreshed on every visit.

Spending caps answer how much. They do not answer who.

The OpenAI cookbook is the clearest single reference for the pattern. Its example agent researches suppliers by paying a data provider 0.25 USDC per report over x402 on Base — a real payment, a real merchant, a real HTTP 402 handshake. The whole guide is structured around limits: an approval grant, a per-run limit, a spending policy, an audit trail. The agent, in the guide's own framing, never gets a blank check. That is the how much question, and the rail answers it well. Read the guide in full at developers.openai.com/cookbook/…/controlled_agentic_commerce (dated 2026-08-13).

What the cookbook does not do — because it is not what AgentCore Payments is for — is score the data provider. There is no assertion that the merchant has ever been paid by anyone else, no history rollup of prior settlements, no independent measure of the counterparty. The agent that pays 0.25 USDC per request only knows: my spending cap allows it. Not: this counterparty is real.

Payment rails are now widely available. Counterparty checks are not.

2026 is the year the agent-payments rails became a commodity, on three tracks moving in parallel:

• x402 Foundation. The Linux Foundation announced the operational launch of the x402 Foundation (2026-07-14) with premier members including Adyen, AWS, American Express, Circle, Cloudflare, Coinbase, Fiserv, Google, Mastercard, Ripple, Shopify, Stripe, and Visa. The x402 protocol (HTTP 402 payment handshake) is at V2. This is the rail AgentCore Payments uses, the rail Cloudflare Wallets ships, and the rail the Coinbase CDP Bazaar indexes against.
• Google AP2. Google's Agent Payments Protocol (announced 2025-09-16 with 60+ launch partners; specification at v0.2) authenticates the transaction via cryptographically-signed Mandates and Verifiable Credentials. It answers did the user authorise this transaction? It does not answer who is the counterparty agent? AP2 has since been donated to the FIDO Alliance.
• Cloudflare Wallets + OpenAI AgentCore. Cloudflare Wallets (2026-08-04) gives an agent a cloudflare.pay identity, an organizational binding, and a per-employee spending cap. OpenAI's AgentCore Payments cookbook (2026-08-13) ships the same pattern from the agent-runtime side. Different vendors, same category shape: identity + spending caps + rail.

Across all three tracks, counterparty quality is left to someone else. This page is about that missing layer.

What a counterparty check actually has to prove

A useful counterparty-quality signal has four parts, none of which the rails can answer on their own:

1. Can the counterparty be reached? The agent-card signpost (/.well-known/agent-card.json under the A2A convention) is the machine-readable proof that the agent even publishes an endpoint at a resolvable URL. Our measurement (snapshot 2026-10-26T13:57:55.767874+00:00): of 26,808 indexed ERC-8004 registrations on Base + Ethereum, only 2,112 (7.88%) publish a machine-readable agent card. Full dataset: /erc-8004-agent-card-signpost-gap (CC BY 4.0).
2. Does anyone else pay this counterparty? A live rail with real economic demand is a much stronger signal than one advertised paid endpoint. Coinbase's public CDP Bazaar indexes many thousands of paid endpoints, but our snapshot (2026-10-26T14:08:42Z) reports only 2,760 of 74,928 (3.68%) cross the ≥5-unique-payer threshold in the last 30 days. Independent measurement (x402-list.com, frozen 2026-08-15) reports the top ten x402 services capture ~97.9% of settled USDC volume across 423 measured services — two operators, two methodologies, same shape. Full ladder: /how-many-x402-endpoints-are-actually-used.
3. Does the counterparty carry paid-job feedback (not self-reported endorsements)? The ERC-8004 ReputationRegistry (0x8004BAa17C55a88189AE136b182e5fdA19dE9b63) accepts a submitFeedback(agentId, tag1, tag2, uri) call from any caller. The raw feedback count is not the reputation. The subset that ties back to a paid job under a canonical predicate — commerce-backed reputation — is what a trust signal actually looks like: 1,003 feedback rows across 51 distinct agents (51 on Base, 0 on Ethereum), authored by 117 distinct client addresses. Full breakdown: /can-you-trust-an-erc-8004-reputation-score.
4. Is the endpoint live right now? Of the 26,809 indexed ERC-8004 registrations, 2,893 (11%) answer at their advertised endpoint with a machine-readable capability manifest on the last probe. This is a floor (“they were reachable at check time”), not a guarantee they will be reachable when the payment lands.

Our answer: commerce-backed reputation

Most advertised paid endpoints are not real counterparties. Under our ≥5-unique-payer cut, only 3.68% of the CDP Bazaar catalog cross the threshold in 30 days; on the demand side, the top ten services capture ~97.9% of settled volume. That IS the product: the trust filter that says “these are the counterparties with an actual payment history worth transacting with.”

Commerce-backed is the strict version of that signal: 51 agents whose on-chain feedback rows tie back to a real paid Virtuals ACP job outcome OR an allowlisted ERC-8183 hook contract. The same definition is used by our free statistics, the paid API and the commerce-backed cohort hub.

Concrete cut on Base x402 demand (snapshot 2026-09-01). Of the ~14,300 Base x402 endpoints that earned money in the last 30 days (≥1 unique payer), 0 have commerce-backed reputation — those endpoints resolve to just 26 distinct publishers, 4 with any on-chain feedback (one event each, one unique client apiece), 0 commerce-backed, and every share here is a lower bound. The four rails (x402, AP2, AgentCore Payments, Cloudflare Wallets) all move money; none of them scores the counterparty. Full derivation: /x402-bazaar-market-map § “Reputation footprint of the earning cohort.”

Method

Rails cited. OpenAI's AgentCore Payments cookbook (dated 2026-08-13); Linux Foundation press release announcing the x402 Foundation (2026-07-14); Google Cloud AP2 announcement (2025-09-16); Cloudflare Wallets announcement (2026-08-04). Every rail claim on this page maps to one of these four dated sources.

Commerce-backed predicate. A ReputationRegistry feedback row is commerce-backed if its transaction was emitted from an allowlisted ERC-8183 hook contract, OR its feedbackURI matches a Virtuals ACP job outcome pattern, OR its tag + client-address combination passes the booster + payer test. The same definition is used on our free statistics, paid API and datasets.

Bazaar cohort. Snapshot as of 2026-10-26T14:08:42Z from Coinbase's public CDP Bazaar discovery API. The same snapshot and rule are used for the demand-concentration report, the live market map, and the canonical x402-usage answer page.

Cap per publisher. Our index counts a limited number of registrations per publisher so that bulk minters do not dominate the totals. The cap and the publisher count are on /how-many-erc-8004-agents-are-there.

Cadence. Chain-stats spans re-fetch on every visit from /v1/public/stats; bazaar and signpost snapshot values refresh on the daily build.

Limitations

• Commerce-backed is a strict floor, not a ceiling. Genuine peer feedback from a client who paid the agent off-chain (fiat, cross-chain, batched settlement) does not clear the commerce-backed predicate. The strict cut is deliberate because the failure mode this page exists to prevent (Sybil-inflated raw scores) is asymmetric.
• Rail identity attests wallet, not agent quality. cloudflare.pay proves wallet ownership + org binding. AP2 Mandates prove user authorisation of the current transaction. Neither is a claim about the counterparty's prior history. The commerce-backed cohort is that missing layer — it does not replace what the rails do prove.
• Bazaar catalog rotation. Endpoints get added and dropped daily. The shape (large listing surface, tiny paid cohort at the top) is stable across snapshots; the exact counts move slightly from build to build.
• Live status has cadence lag. A live-now agent last probed 40 hours ago is counted as live until the next check. Full liveness methodology: /how-many-erc-8004-agents-are-there § “Live predicate.”

Cite this answer

Citable summary. Scope: counterparty-quality signal for agent payments on x402 / AgentCore Payments / AP2 / Cloudflare Wallets rails, measured against the ERC-8004 IdentityRegistry + ReputationRegistry on Base + Ethereum, refreshed daily. On the current daily build, Onchain Agent Intel indexes 26,809 ERC-8004 registrations across Base + Ethereum, of which 51 carry commerce-backed feedback (feedback tied to a real paid on-chain job).

License. Answer prose and every rendered number published under CC BY 4.0 — free to reuse, including in commercial work, provided you attribute “Onchain Agent Intel” and link back to https://onchainagentintel.io/how-do-you-know-which-agent-is-safe-to-pay.

Machine-readable source. Every chain-stats number is a live projection of /v1/public/stats. Bazaar snapshot backs /x402-bazaar-market-map.json. Signpost snapshot backs /erc-8004-agent-card-signpost-gap.json.

Also useful: Commerce-backed cohort hub · x402 Bazaar market map · Signpost-gap dataset · x402 usage answer · Trust the reputation score? · How many agents?