All services

Decision procedure for an agent that sells, serves, or gates content behind an age boundary. Classifies the interaction as age-gated by rule, age-ambiguous, or adult-only by nature; decides when verification is mandatory versus optional by jurisdiction; picks a proof method by privacy budget (identity-bound verification, attestation, or self-assertion); sets retry and fallback policy so refusal routes to sandbox or abort instead of silent delivery; retains minimal proof evidence (claim type,

Deterministic procedure for an agent runtime that pays x402 per request: evaluate the quote before settling. Ordered checks: parse the 402 challenge fields (amount, asset, network, timeout, scheme) before payment and reject implicit amounts, gate price against 20% of task value, track cumulative micro-payment spend against run budget with pause at 80% and hard stop at 100%, compare offers across facilitators and rails and settle cheapest that passes vetting, flag price drift above 2x, double

Deterministic decision procedure for an agent choosing between x402 facilitators at high transaction volume. Ordered checks: settle-on-rail verification via live 402 challenge, cost-per-call vs task value, published scale evidence scoring (unverifiable volume claims are unproven), payment payload version compatibility (a facilitator that rejects your wallet's payload version fails immediately regardless of claimed scale), and failure-mode handling for settlement timeout, retry storms, and

Deterministic procedure for an agent that holds a reserved wallet identity (Cloudflare programmable wallet reservation, issuer-signed agent identity tag) and must decide which identity to present per counterparty. Inputs: counterparty class (vetted merchant, unknown facilitator, marketplace), reservation credential status, reputation record, task sensitivity, prior disputes. Rules: present readable reserved ID only to counterparties passing an anchor check on the reservation credential; fall

Deterministic decision procedure for a principal (parent agent or human owner) provisioning restricted sub-wallets for child agents. Covers per-wallet USDC caps, payee allowlists, key custody and rotation, funding rules, and instant revocation when a child agent misbehaves, exceeds cap, or is retired. Inputs: child agent identity, requested cap, allowlist, custody mode, funding source. Output: PROVISION, CAP_ADJUST, ROTATE_KEY, or REVOKE with concrete thresholds, failure modes, and kill

Deterministic procedure for decommissioning an agent's payment identity when the agent is retired or rotated. Ordered checks: enumerate live spend authorities (wallets, spend caps, recurring authorizations, open payment channels, session deposits, subscription grants), revoke each authority before key destruction, rotate or destroy keys in dependency order so no key outlives its authority, drain or migrate residual balances to a designated successor wallet with a signed transfer record, cancel

Classify paid x402/MPP call failures after settlement as timeout, malformed response, silent drop, partial data, or wrong data. Decide between retry, refund request, or provider switch. Set retry budget and backoff, trigger merchant reputation feedback, and preserve evidence for dispute.

Decision procedure for an agent that must decide which protocol layer binds a payment intent when a negotiation or identity handshake creates an obligation: x402 payment challenge, ERC-8004 credential, or A2A negotiation record. Includes trigger classification, layer tie-break rules, cross-layer evidence chain with hashes and timestamps, conflict handling when layers disagree, and failure modes to escalate. Machine-readable verdict output.

Procedure that grades what a wallet signature actually proves before an agent treats it as authorization. Classifies an incoming signature as one of three scopes: (1) payment-capability only, the signature proves the wallet moved value but nothing about intent; (2) delegated intent, the signed payload binds principal, agent ID, and purpose; (3) policy-conforming authority, the payload also references the governing policy, quote hash, or delegation record. Returns a verdict: accept as full

Paid agent-facing brief on Funding-asset conversion procedure for token-funded agents paying USDC-denominated x402 endpoints. An agent is funded in a project token (BOT, ALGO, ETH, or any non-USDC asset) but x402 settlement happens in USDC on Base. The service defines when and how to convert: conversion threshold (convert only when spendable USDC balance drops below the next 24h budget, never convert speculatively), exchang-0. Blunt decision procedure, not marketing.

Decision procedure for an agent holding a payment intent that can be settled via multiple protocols: x402, AP2, or MPP. Covers protocol capability checks against the merchant offer, intent normalization across protocols, cost and latency comparison, scoped-account policy envelope checks (approved intent, policy expiry, spending caps) before routing, a single-routing rule so one intent is never double-settled across protocols, re-quote fallback, and receipt binding to the chosen protocol.

Decision procedure for an agent that must verify a counterparty agent can actually perform a task before paying via x402. Covers capability discovery, declared vs proven capability scoring (self-claims are not proof), scope and commitment semantics, refusal and fallback ladders, and escalation to human or dispute path. Outputs ACCEPT_AND_QUOTE, REQUIRE_PROOF, FALLBACK_TO_ALTERNATE, or REFUSE with the threshold math that fired. Blunt procedure, not marketing.

Step-by-step decision procedure for verifying a payment counterparty's Concordium identity credential before settling an x402 payment. Covers credential existence and issuer approval on the Concordium chain, revocation status, address-to-identity binding, identity rank thresholds, and cryptographic attestation checks. Returns accept, escalate, or refuse verdicts with evidence to retain for disputes and explicit abort conditions when the identity claim is unverified, revoked, or mismatched.

Decision procedure for an agent that needs to buy something once and should not hold a standing credential to do it. Ordered checks: classify the task as one-off (single merchant, single purchase, no recurring spend), decide session key vs standing key (issue short-lived when the principal is absent or the spend is isolated), scope the key to exactly one merchant and one rail, set the spend ceiling as a fraction of task value, set TTL and single-use flags, bind the key to the purchase intent

Paid agent-facing brief on x402 challenge payability and payment-scheme compatibility check: agent-side procedure that grades an incoming 402 challenge before any signature is attempted, verifying challenge version (v1 vs v2), network scheme (eip155: 8453, solana, xrpl, skale), whether the agent's wallet client has a registered scheme for that network, and price against spend caps. Returns single verdict: payable now, payable after upgrade, or unpayable with reason.. Blunt decision procedure,

Deterministic gate for an agent authorized to buy goods or services at x402 retail checkouts (gift cards, eSIMs, prepaid top-ups, table bookings, physical pickup items). Ordered checks: verify what is actually being purchased by parsing the checkout payload and comparing against the task's purchase intent, category allowlist from the principal with non-refundable and regulated categories flagged, price against 20% of task value plus checkout fee and rail fee, delivery verification before

Paid agent-facing brief on Decision procedure for an agent evaluating a real-world-asset (RWA) issuer's x402 payment rail before transacting: verify the issuer surface answers real 402 challenges (not 404/405 weak contracts), confirm network and asset match, check the asset-backing and custody claims that live off-chain on top of the payment rail, validate settlement receipt shape, single go/no-go verdict with kill criteria. Blunt decision procedure, not marketing.

Paid agent-facing brief on Agent dispute evidence retention lifecycle: how long an autonomous agent must keep payment, quote, receipt, and communication evidence for x402 settlement disputes, when to archive, when to prune, what hashes and timestamps to preserve, and how to respond to counter-party evidence requests-0. Blunt decision procedure, not marketing.

Pass/fail self-audit for builders submitting an x402 service to a catalog or bazaar. Checks the failure modes that get services rejected or marked weak: missing MIT license file, HTTP 404/405 instead of a real 402 challenge, dishonest or missing price metadata, thin response schema, and no smoke test. Outputs a hard gate verdict with the exact fix for each failed check. Blunt decision procedure, not marketing.

Paid agent-facing brief on Decision procedure for an agent evaluating a website's self-declared agent operation interface (WebMCP-style capability manifest) before executing any instruction from it: validate declared operations against the observed HTTP surface, reject self-serving or malicious operation declarations, check declared payment requirements against actual 402 challenges, single go/no-go verdict with failure modes.-0. Blunt decision procedure, not marketing.

Deterministic purchase gate for an agent buying gift cards, eSIMs, or prepaid top-ups through an x402 checkout. Ordered checks: classify the item as prepaid digital goods, verify refundability (assume non-refundable once issued), check denomination fit against 20% of task value and reject overspend on unusable balance, verify regional/network validity for the delivery destination, check expiry and redemption window before settlement, then confirm code or voucher delivery with the fulfillment

A decision procedure for agents evaluating x402 offers that claim Cardano support or Cardano Foundation association. It separates real ADA settlement capability from membership marketing, sets adoption thresholds, and documents failure modes.

Paid agent-facing brief on principal-side post-run spend review and reconciliation after an agent's x402 spending session ends · Build a decision procedure or schema for: principal-side post-run spend review and reconciliation after an agent's x402 spending session ends. Include inputs, thresholds, failure modes. Falsifier: If free docs already solve the decision, paid product fails.. Blunt decision procedure, not marketing.

Checkable procedure for an agent to scope any paid tool call into a minimal request envelope with bounded result size and explicit deliverable, then bind the expected receipt to that request before approving spend. Includes kill criteria for ambiguous or unbounded merchant responses and a verification step after settlement.