how it works

How jpcite Evidence Packets work for AI agents

Your AI receives a Japan-regulatory question. It hits the jpcite Evidence Packet bank, retrieves a structured JSON envelope (source URL, fetched-at, known gaps, content-hash traceability), then answers using verified evidence instead of long-context retrieval. Browser and CLI agents both route paid use to the current metered API-key checkout.

Browse the catalogue See pricing

Three-step funnel

  1. Discover — Browse the catalogue at /en/packets/ or call jpcite.list_packets() from your AI agent over MCP.
  2. Verify — Free anonymous evaluation gives 3 requests/day per IP (no signup, resets at JST next-day 00:00). The returned envelope contains source_url, source_fetched_at, known_gaps, exclusion/prerequisite rules, and content_hash traceability.
  3. Integrate and pay — Pay-as-you-go ¥3 per billable unit from metered API-key checkout. Qualified Japanese invoices are issued automatically. Cost caps and idempotency headers control broad batch or fan-out spend before execution.

Two integration paths

Browser AI (Claude.ai / ChatGPT / Perplexity)

Your agent calls the REST endpoint, uses the anonymous preview allowance, and routes paid use to the API-key checkout page when the user needs higher quota.

CLI AI (Cursor / Claude Code / Windsurf)

Install the MCP server: npx @bookyou/jpcite or uvx autonomath-mcp. The agent calls jpcite tools natively over MCP stdio. Paid use is metered by API key.

What's in an Evidence Packet

FieldMeaning
source_urlPrimary public-source URL (METI / MAFF / NTA / Courts / e-Stat / etc.)
source_fetched_atISO-8601 timestamp when jpcite last crawled the source. This is a traceability timestamp, not a freshness SLA.
known_gapsExplicit known limitations (12 small-municipality programs lack a dedicated CMS page)
exclusion_rules181 codified exclusion + prerequisite rules (125 exclude + 17 prerequisite + 15 absolute + 24 other)
citation_candidatesSuggested citation form for the LLM answer step
content_hashSHA-256 content trace used to compare the packet body and source-derived material

Why agents save tokens with jpcite

Thesis: jpcite gives the agent a compact Evidence Packet before it reads long Japanese government PDFs or multiple public pages directly. Any token / context / web-search / retry cost difference is benchmark pending and must be measured on the same query before publication.

Next steps