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 pricingThree-step funnel
- Discover — Browse the catalogue at /en/packets/ or call
jpcite.list_packets()from your AI agent over MCP. - 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, andcontent_hashtraceability. - 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
| Field | Meaning |
|---|---|
source_url | Primary public-source URL (METI / MAFF / NTA / Courts / e-Stat / etc.) |
source_fetched_at | ISO-8601 timestamp when jpcite last crawled the source. This is a traceability timestamp, not a freshness SLA. |
known_gaps | Explicit known limitations (12 small-municipality programs lack a dedicated CMS page) |
exclusion_rules | 181 codified exclusion + prerequisite rules (125 exclude + 17 prerequisite + 15 absolute + 24 other) |
citation_candidates | Suggested citation form for the LLM answer step |
content_hash | SHA-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.