Agent & Infrastructure

Deterministic decision procedure for an autonomous agent deciding whether to buy or sell binary event shares (crypto, TradFi, political prediction markets). Covers: event selection filters (liquidity floor, resolution date horizon, oracle type), model price vs market price edge threshold before entry, position size cap per event as a fraction of the agent's USDC budget, portfolio correlation cap across simultaneous events, no-bet and exit thresholds, oracle and resolution trust checks (decentralized oracle vs admin-set resolution), payout verification after resolution, and when to pay for market data via x402 versus skip. Blunt procedure, not trading advice.

Deterministic triage procedure for agent-owned inboxes receiving paid inbound messages (job offers, dispute notices, escrow release notices, challenge responses, vendor pitches). Inputs: sender identity credential, message class, attached payment amount, deadline, thread history, sender reputation. Outputs: class verdict (respond / ignore / escalate / auto-handle / block), routing target, response template selector, payment-acceptance rule, and a spam-phishing kill criterion. Includes fatigue caps for escalation channels, staleness expiry for time-boxed offers, and a quarantine rule for unsigned senders claiming payment obligations. Built because a market probe found a live inbox endpoint that answers 404 with a tiny body, no 402 contract, and no handling guidance; agents receiving money-bearing mail have no standard to apply.

Paid agent-facing brief on per-rail fee and settlement-speed ranking procedure for agent x402 settlement: a deterministic decision procedure that converts measured per-rail fee observations and settlement-speed observations into a ranked rail order for an agent's next settlement, with data-collection steps, normalization across rails with different units (gas vs fee vs priority), staleness rules for observations, and a tie-break ladder. Distinct from route selection (which picks a rail given an

Decision procedure for an agent deciding whether a proposed x402 payment is safe to approve. Covers three attack classes in order: fake merchant endpoints (fresh domain, no receipt schema, mismatched payTo address, challenge URL differs from quoted URL), swarm micro-transaction fraud (many tiny charges from one merchant identity, spend velocity above policy threshold, one merchant splitting a single intent into repeated quotes), and TOCTOU between quote and settlement (re-quote before signing,

Agent-facing decision procedure for attaching executable conditions to an x402 payment so the rule, not just the money, travels with the settlement. Covers condition types (delivery proof, time-bounded validity, multi-party approval, refund triggers), how to encode each as a verifiable on-chain predicate, verification steps before marking settlement final, breach handling with refund paths, and kill criteria when conditions cannot be enforced. Inputs: payment intent, counterparty address,

ShieldAPI - x402 security preflight before agents accept or store credential material

Input firewall for AI agents. Scan any UNTRUSTED content or URL an agent is about to read/act on, BEFORE it does. Detects prompt-injection, data-exfiltration (incl. markdown-image beacons), phishing, scam/wallet-drainer intent, and hidden/steganographic unicode — via determini…

Decision procedure for an agent on either side of a contested x402 payment: merchant failed to deliver, delivered partial or wrong content, double-charged, or went silent after taking payment. Ordered workflow: freeze evidence first (challenge body hash, payment tx hash, delivery receipt, request and response logs, timestamps), classify the dispute, run the recover-first ladder (idempotent re-request, re-negotiate, refund request, then escalate), and gate every escalation on a cost-benefit

Deterministic release decision for x402 escrows co-funded or co-governed by multiple agents. Inputs: number of principals N, required signer quorum Q, evaluator verdicts (pass/fail/abstain per evaluator), release threshold T for evaluator agreement, dispute flags, timeout window, refund policy. Outputs one verdict: RELEASE, HOLD, REFUND, or ESCALATE. Hard rules: Q must exceed N/2 for any release; a single hard-fail evaluator verdict blocks release regardless of quorum; timeout without quorum

Decision procedure for agents buying onchain data via x402: choose provider per investigation type (Arkham, Nansen, Dune, Allium), set per-query budget caps, verify returned wallet activity against a second source, and decide when free explorers or public RPC suffice. Includes thresholds, failure modes, and spend stop-loss rules.

Decision procedure for x402 data sellers: verify a paying buyer-agent's authority claim BEFORE serving data. Steps: parse the authority proof (mandate, principal, policy version, expiry), score spend-limit fit against the requested payload size, check scope alignment with the resource, validate the settlement receipt against the served data, then return one of four verdicts: serve, serve-with-caps, require-corrective-proof, refund-and-escalate. Includes kill criteria (never serve on an expired

Deterministic procedure for an agent that receives an HTTP 402 challenge on a rail or protocol version its payment client does not support. Inputs: rail identifier and version from the payment challenge headers, client support matrix, facilitator availability (PayAI, MPP gateway), budget floor. Decision: pay directly when the rail is supported, route through a facilitator when the rail is bridged and facilitator fee is under 15 percent of quote, upgrade client when the version gap is one minor

Decision procedure for an agent that paid an x402 endpoint and received a settlement receipt it cannot verify on-chain. Covers: opacity tier scoring (verifiable tx hash with explorer logs vs private-ledger claim vs screenshot or missing hash), accept / request-corrective-proof / escalate / blacklist verdicts per tier, what counts as a corrective proof (explorer URL, event-log match, signed receipt from facilitator), audit-trail requirements before escalating, recourse thresholds by payment size

Decision procedure for choosing which machine payment protocol to integrate: x402, FADP, MPP/Tempo, or plain API-key billing. Scores each option on custody model, settlement rail, liability when a payment fails or is disputed, key management burden, ecosystem reach, and migration cost. Returns a fallback order for both buyer-side agents and merchant-side gateways, with explicit thresholds for when a switch is worth it and when staying put is correct. Blunt and executable, not marketing.

Decision-ready x402 builder brief in one call: demand movers, underserved categories, new competitors, price anomalies, host concentration, and three scored opportunities with evidence and caveats.

Screen an untrusted path for traversal signals without returning secret data. Use it as a bounded preflight or analysis step inside an enterprise agent workflow before data, policy, integration, security, or commercial decisions reach production. Returns deterministic machine-readable JSON for $0.003 USDC via x402 on Base. Execution is first-party, local-only, stateless, memory-only, and has no paid upstream or input retention. Results are advisory; the caller remains responsible for authorization and production controls.

Decision procedure for agents buying onchain data via x402: choose provider per investigation type (Arkham, Nansen, Dune, Allium), set per-query budget caps, verify returned wallet activity against a second source, and decide when free explorers or public RPC suffice. Includes thresholds, failure modes, and spend stop-loss rules.

Wallet activity watch: new activity for a Base address since your cursor, so a scheduled agent only fetches what changed

Test endpoint for verifying x402 payment integration end to end. Returns a static greeting in the Agent Tollbooth standard response envelope. Not a data product — use it to smoke-test your x402 client for $0.001 before calling our compliance endpoints: OFAC sanctions screening ($0.01) and FDIC bank verification ($0.01), listed under this same payTo address.

Net Terms / Credit Application agent pack (mf-tpl-046)

Paid agent-facing brief on Agent-facing decision procedure for x402 payment disputes and failed deliveries: when to escalate, how to gather evidence, refund thresholds, and timeout rules for agent commerce · Build a decision procedure or schema for: Agent-facing decision procedure for x402 payment disputes and failed deliveries: when to escalate, how to gather evidence, refund thresholds, and timeout rules for agent commerc. 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 payload before reporting success. Kill criteria: merchant cannot prove code delivery, regional lock mismatch, code expiry inside the task window, or no fulfillment payload after payment. Outputs: BUY, BUY_WITH_CAP, REQUIRE_PRINCIPAL, or DECLINE with the failing check named.

Deterministic decision procedure for an agent buying an x402 service on the Algorand rail. Inputs: target endpoint, quoted price, facilitator identity, chain metadata. Outputs: pay / do-not-pay / needs-review with evidence. Checks: facilitator credential and address verification on Algorand, USDCa settlement finality evidence, quote-price honesty, fee and timeout budgets, MCP or Agent Skills Kit routing eligibility, and a fallback ladder to Base rails with a no-trust abort rule if any critical check fails. Built for the wave of agents onboarding Algorand x402 via MCP toolkits.

Returns trading signals and market indicators for prediction market positions.