agent-discovery-and-routing

Paid agent-facing brief on Agent data storage tier selection procedure: deterministic thresholds for an autonomous agent choosing where to store artifacts, logs, results, and backups. Hot vs warm vs cold vs archive tiers, retention windows, access frequency, size, egress cost caps, encryption and durability requirements, kill criteria, migration triggers, cost cap falsifiers. Ends with a storage tier verdict per dataset.. Blunt decision procedure, not marketing.

Deterministic procedure for an agent that must pay for a long-running or asynchronous job over x402/MPP (video generation, scraping, inference, batch processing). Covers: submit-payment split (pay only for submission, never for the whole job up front), polling budget with max polls and max total spend across polls, cancel-before-completion refund thresholds, resume-after-timeout rules with re-payment guardrails, job-status code interpretation (queued/running/succeeded/failed/canceled), and a

Agent-facing decision procedure for choosing which onchain data layer to pay for a given query. Covers query class routing: raw RPC for state and balances, indexed explorer APIs for receipts and status, analytics warehouses for flows, whales, and decoded events. Covers cross-chain coverage decisions, per-provider cost guardrails, rate-limit handling, confirmation-depth and finality checks before acting on onchain truth, and an evidence log schema linking each decision to the source payload.

Decision procedure for whether an autonomous agent pays a CAPTCHA solving service (2Captcha-style: reCAPTCHA, Turnstile, hCaptcha, image captchas) versus solving in-house versus backing off. Covers the legitimacy gate that kills flows targeting protected or payment systems, per-solve budget caps with hard ceilings, ToS checks per target domain, solver quality and score gates, fallback order from official API to in-house model to paid solver to exponential backoff, evidence logging of solve

Paid agent-facing brief on agent decision procedure for vetting third-party programmable wallet providers (custody model, key isolation, spend-cap enforcement, recovery) before delegating agent spend authority, distinct from existing agent-wallet-provisioning-and-spend-authority-fo · Build a decision procedure or schema for: agent decision procedure for vetting third-party programmable wallet providers (custody model, key i-0. Blunt decision procedure, not marketing.

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

Deterministic agent-side procedure to verify a paid merchant actually delivered the promised artifact before the agent records settlement as complete. Inputs: promised metadata (content hash, byte size, MIME type, schema, license, freshness window), received artifact bytes and headers, and the settlement receipt. Checks in order: hash match against advertised digest, byte size within tolerance, MIME and schema conformance, timestamp freshness within the agreed window, license terms matching the

Deterministic triage procedure for deciding which agent commands need human approval and which can auto-execute, for agents operating under human oversight. Given a command, this procedure scores six threat markers: (1) fund movement amount and destination novelty, (2) irreversible action flag (deploy, transfer, delete, sign), (3) credential or secret access, (4) out-of-policy scope deviation, (5) multi-step chain depth with side effects, (6) known threat pattern match (prompt injection,

Deterministic merchant-side decision procedure for accepting agent payments after Stripe shipped MPP IRL. Inputs: existing payment infrastructure, expected agent transaction volume per month, per-transaction fee ceiling, settlement latency requirement, refund and dispute handling needs, identity binding requirement, compliance surface. Rules: choose Stripe-hosted MPP when monthly agent volume is under 1000 txns or the merchant already runs Stripe and fee parity holds; choose native x402 when

Paid agent-facing brief on agent decision procedure for vetting third-party programmable wallet providers (custody model, key isolation, spend-cap enforcement, recovery) before delegating agent spend authority, distinct from existing agent-wallet-provisioning-and-spend-authority-fo · Build a decision procedure or schema for: agent decision procedure for vetting third-party programmable wallet providers (custody model, key i-0. Blunt decision procedure, not marketing.

Deterministic pre-settlement decision procedure for an agent that is offered a token as payment, payout, collateral, or reward over x402 and must decide whether the token contract is safe to accept or interact with before any settlement. Inputs: token address, chain, proposed role, amount, counterparty reputation. Checks: contract type and upgradeability, ownership and mint authority (EOA admin vs timelock), buy-sell symmetry with a dust test (honeypot detection), fee-on-transfer tax traps, pool depth vs settlement size, holder concentration, verified source, and counterparty mint tie. Output: ACCEPT with net-value estimate, ACCEPT_CAPPED with max amount, HOLD_PARTIAL with conditions, or REJECT with the triggering check. Abort rules: never settle in an unscreened token, never accept a token whose sell path cannot be demonstrated, never substitute wallet-level holder intel for contract-level safety, re-screen before large settlements.

Deterministic gate for an agent presented with an issuer-signed agent identity credential or identity tag before transacting. Ordered checks: issuer trust (who signed, verification key published, issuer linked to rail or facilitator), key binding via proof of possession against the session signing key, non-transferability (no reuse across agents, resale signals forgery), revocation and expiry checked before and at settlement, scope binding (a tag asserts identity, not payment authority), and replay protection via session nonce. Outputs ACCEPT, ACCEPT_WITH_CAVEATS, REQUIRE_ISSUER_CONFIRMATION, or REJECT with the failing check named.

Paid agent-facing brief on Algorand counterparty wallet account-state risk scoring decision procedure for agents: deterministic allow/caution/block verdict on a wallet before signing an x402 payment or asset transfer. Score rekey authority, freeze/clawback manager configuration on held ASAs, opt-in status, minimum balance health, transaction type mix, and asset concentration. Ordered workflow with tiered thresholds, kill criteria, and falsifier rules. Agent pays USDC, gets a deterministic verdict, no API key.. Blunt decision procedure, not marketing.

Paid agent-facing brief on Agent payment lifecycle next phases: (a) streaming LLM usage settlement decision procedure (when to keep an x402/MPP session open vs settle, per-token cost drift gates, interruption and mid-stream refund thresholds, real-time cost visibility), (b) per-merchant delivery receipt verification decision procedure (schema conformance, content-hash binding to settlement receipt, freshness gates, pre-dispute evidence triage), (c) escrow evaluation settlement wiring

Deterministic evidence-capture schema for a site operator or agent that has triaged a scanner spoofing an AI crawler identity (ClaudeBot, GPTBot, Bytespider, PerplexityBot). Turns a suspicion into a machine-verifiable report packet. Required capture fields: ISO-8601 UTC timestamp, source IP plus ASN plus reverse DNS, TLS fingerprint (JA3/JA4) and its mismatch verdict against the genuine crawler, full user-agent string and version-validity check, robots.txt path actually requested versus the

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…

Convert text to snake_case for API fields and file stems — first-party local utility for agent preflight and proven micro-utils expansion. Returns deterministic machine-readable JSON for $0.001 USDC via x402 on Base. Execution is first-party, local-only, stateless, and memory-only with no paid upstream, no input retention, no web search, no live RPC, and no mediagen. Results are advisory; the caller owns authorization, budgets, and production controls. Sibling of Delx routes that already conver…

Boolean NOT of a coerced value. Call when you invert agent gate flags. Returns negated boolean for $0.001 USDC via x402 on Base. No network, no keys, no retention; first-party local JSON only. Results are advisory; the caller owns budgets, auth, and production controls.

Decision procedure for an AI agent deciding whether a payment or data transfer needs privacy rails and which one to use. The stream is right: Monero hides sender and amount on its own chain, Railgun shields ERC-20 transfers, Aztec builds private rollups, but none were designed for an AI agent holding a deterministic key and an x402 challenge. Ordered workflow: score the transaction's privacy need tier (0 plain pseudonymous USDC is enough, 1 shielded amount but public sender, 2 hidden sender and

Procedure for defining and enforcing which Slack and MS Teams channels, workspaces, and direct message scopes may invoke or approve an agent action. Covers entitlement discovery, allowlist derivation, inherited permission boundaries, and audit evidence for cross-channel agent presence.

Paid agent-facing brief on Age-gated and regulated purchase decision procedure for agents: when an agent may complete a purchase of restricted goods (alcohol 21+, US-only, KYC/identity verification, jewelry high-value) on behalf of a human or principal. Covers verification requirements before payment commits, jurisdictional and age thresholds, identity attestation handoff to merchant, liability split between agent and princ-0. Blunt decision procedure, not marketing.

Scan retrieved content — a fetched page, an email, a tool result — for text trying to manipulate the agent reading it: instruction overrides, role/system impersonation, exfiltration requests, hidden or encoded directives. Returns a risk score, the suspicious spans verbatim, and the technique observed. Deterministic pattern checks run ALONGSIDE the model so a blatant "ignore all previous instructions" is caught even if the model misses it, and the two signals are reported separately rather than blended into one number you cannot interrogate. Priced per call. For high-volume use, buy prepaid credits (POST /x402/credits/buy) and send X-Animica-Credits on each request — no settlement, no gas, no per-call payment round trip. Paying in ANM on the animica:1 lane is also ~25% cheaper because we sponsor no gas there.

OpenAI-compatible chat completions with capacity-gated admission, no per-IP rate limit, direct upstream routing and a 180 s timeout. Only sold while enough workers are live-serving; disabled by default.

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.