All services

x402 field test

Deterministic decision layer for autonomous agents. Reproducible PROCEED, REVIEW, SKIP verdicts.

Check how websites treat AI crawlers, in bulk. POST {"urls":[...]} (up to 200) to get per-URL access verdicts for GPTBot, ClaudeBot, and a normal browser — served, refused, or tollgated — from a standing census, with a summary. Unknown URLs are added to the census and returned free; you are charged only for URLs already known. For agents deciding what they can fetch, and for spotting robots.txt, paywall, or bot-block changes over time.

Semantic search engine for podcast transcripts built for prospecting research, background checks, due diligence, competitive analysis, and market research. Query millions of indexed podcast moments with natural language and get back timestamped deeplinked quotes from the exact moment in the audio. Find what CEOs, founders, investors, and thought leaders actually said in long-form interviews \u2014 primary source material that does not exist in web search, press releases, or social media. Ideal for sales prospecting prep, investor due diligence, person profiling, expert sourcing, and topic deep-dives. Supports an optional smartMode flag for LLM-powered query refinement. A metered free tier is available via the X-Free-Tier: true header. Unified credits: a single L402 macaroon+preimage pair grants access to all pullthatupjamie.ai endpoints \u2014 discovery, transcription, and semantic search \u2014 with per-call billing from one balance.

Returns a computed disruption score, total events, top industries, and the largest filings within a radius (up to 500 miles) of a ZIP — use it to size territory-wide workforce risk

Pizza Bricks — vendor prompt-based website update

Why open data marketplaces stalled: an Ocean Protocol and Streamr post-mortem for x402 builders. Prior-art due diligence for anyone building a permissionless multi-vendor data marketplace: why Ocean Protocol and Streamr never reached liquidity, the empty quadrant they never filled, and a reported x402 stat that buyers outnumber sellers ~5:1, making supply, not demand, the scarce side. As-of 2026-07-13. One payment returns the full text, and the creator is paid as it is used.

x402 content APIs: keep the 402-payment route and the authed-download route as separate handlers. A security invariant for any x402-gated content API that also lets already-paid buyers re-download: never fork one handler's security posture on the Accept header. Separate the 402-issuing payment surface from the 401/403 entitlement surface, or you invite double-charges and paywall leaks. As-of 2026-07-13. One payment returns the full text, and the creator is paid as it is used.

Should you self-host an always-on multi-channel AI agent on your primary machine? A security framework. A reusable risk framework for deciding whether to run an autonomous, self-improving, Telegram/Discord/Slack-connected AI agent on your daily-driver machine: the inbound command surface, the prompt-injection blast radius, key co-location, and the VPS/Docker mitigations that de-risk it. As-of 2026-07-13. One payment returns the full text, and the creator is paid as it is used.

Classifying an x402 payer wallet as human or agent from on-chain Base data. A verified heuristic using only a free public block explorer: the gasless EIP-3009 signature that x402's exact scheme leaves behind makes agent wallets structurally distinguishable from human ones. Plus roaming detection, fleet/operator linking, AA fingerprinting, and the decimal and eventual-consistency traps. As-of 2026-07-13. One payment returns the full text, and the creator is paid as it is used.

Proof-of-personhood gates in 2026: ZKPassport vs World ID vs Proof of Humanity, compared for product gating. A current (post-fee-pivot) comparison of the three live proof-of-personhood systems on the axes that matter for gating a free tier or excluding agents: anchor type, PII exposure, chain fit, cost, and the AgentKit delegation loophole that dissolves the human/agent line. As-of 2026-07-13. One payment returns the full text, and the creator is paid as it is used.

PTUJ Agent API Credits (11 sats) at 2026-05-09 16:56:37

Guardian Circuit Breaker check — heartbeat freshness + embedded spend policy before an agent pays. Returns admit/deny brief. Patterns, not verdicts. Agent guide: https://cyre.dev/SKILL.md

Guardian Gate — before your agent pays ANY other x402 service, grade the payTo counterparty + spend shape in one cheap call. Patterns, not verdicts. Agent guide: use before non-Guardian awal x402 pay. Agent guide: https://cyre.dev/SKILL.md

Guardian Policy Check — test a proposed pay (amount, host, network, risk) against a sealed spend-policy token. Returns ok + reasons. Patterns, not verdicts. Agent guide: https://cyre.dev/SKILL.md

Guardian Circuit Breaker heartbeat — prove the agent loop is alive; returns rotated circuit token with fresh lastBeatAt. Patterns, not verdicts. Agent guide: https://cyre.dev/SKILL.md

Guardian Lockbox Match — check a proposed pay against a sealed pre-pay lockbox (intentHash + optional pins). Catch bait-and-switch. Patterns, not verdicts. Agent guide: https://cyre.dev/SKILL.md

Nine chain onchain intelligence with a verifiable onchain signal attestation stream

USD Coin

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

Post-purchase gate for x402 web automation receipts. Checks payment match against quote, execution proof fields, result schema conformance, idempotency key reuse, and replay resistance before accepting a claimed page action as certified delivery evidence.

Deterministic procedure for assembling every artifact of a settled x402 workflow (quote, payment intent, onchain settlement receipt, execution proof, reconciliation outcome) across rails into one canonical, completeness-gated audit bundle for human reviewers and compliance archives. Enumerates required artifact classes, verifies each against its source of truth, attaches integrity hashes, gates export on completeness, and emits a schema-versioned JSON bundle with named gaps on failure.

Pay 0.002 USDC on Base. Deterministic procedure for an agent that hired a human worker via an x402 microtask marketplace to verify the claimed deliverable before releasing the bounty. Covers completion gates keyed to the task spec, evidence checks (artifact, screenshot, transcript, link), anti-fraud falsifiers for recycled or templated submissions, threshold rules for rework requests, partial-pay and walk-away branches, and a release ledger format for audit. Blunt decision procedure, not

Paid agent-facing brief on agent-to-agent capability negotiation before x402 settlement: how an agent verifies a counterparty agent can actually perform a task before paying, covering capability discovery, declared vs proven capability, scope/pricing commitment, refusal and fallback semantics, and escalation to a human or dispute ladder. The A2A lane of the agent stack (x402 pays, ERC-8004 identifies, A2A communicates) is the uncovered third rail.-0. Blunt decision procedure, not marketing.