Jid: the trust API for AI agents

Checks whether an e-mail is from who it claims. Input: the raw headers of a message (as shown by Show original or View source). Returns checks and a read (headline, recommendation engage | verify_first | do_not_engage, failed checks, lookup links): DMARC/SPF/DKIM as the receiving server recorded them, DKIM alignment with From, Reply-To going to another domain, and a From domain or display name that imitates a known business. The headers are processed in memory and never stored. Deterministic, no AI. Counts as 1 check with a key; free tier without one.

The Jid file for one business. Default (compact): status with its flags, identifiers, verified websites, the top facts with source and verification date, counts and the latest changes. With detail "full": every current fact with its source, verification date, next check and confidence, owner statements (labelled self-reported), possible matches and the change history.

Returns a stored, Ed25519-signed verification receipt by receipt_id: the inputs, decision, reasons, fact ids and value hashes, rules version and time of the check. Free; does not count as a check.

Qualifies a business that made contact (a form submission, an inquiry, an outreach reply). Input: the sender's e-mail (or the company domain), the company name if given, and the context (form type, message, stated value, stated role). Jid checks the domain (MX, SPF, DMARC, registration date over RDAP, the website), matches it to a Jid business file, reads that file's registrations, licences, filings, capital raises, loans and adverse records, and returns signals (each with source, source_url, verified_at), three scores (legitimacy, capacity, consistency, 0 to 100 with reasons), checks (each pass, fail or unknown with one line of evidence) and a read: a one-line headline ("Passed all 7 checks Jid could run. Recommendation: engage."), the recommendation (engage, verify_first, do_not_engage), the failed checks and up to 4 links to verify by hand, plus a signed receipt reference. detail "full" adds each signal's raw value, each check's lookup link and the full signed receipt. Businesses only: personal webmail or no matched business returns individual_or_unverified with no scores. A possible list match is returned as 'review', not as a finding. Counts as 2 checks with a key; free tier without one. Not intended for credit, employment, insurance or housing decisions about any person.

Screens a lead, sender, vendor or website and returns an engage-or-not answer. Input: any of domain, url, email, phone or company_name, the context (lead, inbound_email, partnership, vendor, purchase, marketplace_seller, agent_action), an optional amount (USD) and a policy (strict, balanced, permissive; default balanced). Returns engage (true or false), risk (low, medium, high, unknown), confidence 0 to 1, subject_type, reasons (each with source and evidence), mitigations, checks, a read (headline, recommendation engage | verify_first | do_not_engage, failed checks, lookup links) and a signed receipt_id. Deterministic, no AI in the decision, usually under a second. A possible sanctions name match returns engage=false with 'manual review', not a finding. For individuals only technical checks of the address, phone or domain run. engage is advisory. Rules: https://jid.com/screen-rules. Counts as 1 check with a key; free tier without one.

Finds Jid business files by name or by any registry number (FEI, LEI, SEC CIK, DUNS, NDC labeler code, state licence or entity number, French SIREN or SIRET). Returns candidate files with status and match evidence. For a French company pass country "FR": the SIRENE register is searched live and files are created on demand.

Verifies a business against the registry facts Jid holds. Input: a Jid id (or a name or registry number) and, optionally, an activity, jurisdiction and amount. With an activity it returns a decision (proceed, review, stop or insufficient_data) with reasons: each names the requirement, met (true, false or unknown), the fact ids, source, verified_at and fresh_until, plus a signed receipt_id. Without an activity it returns the status and the top cited facts. Default output is compact (verdict, reasons, status, identifiers, top facts, receipt reference); detail "full" adds every cited fact and the full signed receipt. Activities: general_commerce (General commerce (default)); sell_prescription_drugs (Sell prescription drugs); manufacture_drugs (Manufacture drugs); sell_medical_devices (Sell medical devices); haul_freight (Haul freight (for-hire motor carrier)); broker_freight (Broker freight); sell_alcohol (Sell alcohol (wholesale or import)); produce_spirits (Produce distilled spirits); provide_investment_advice (Provide investment advice); accept_deposits (Accept deposits); lend (Lend); bill_medicare_medicaid (Bill Medicare or Medicaid); healthcare_supplier (Health care supplier); federal_contracting (Federal contracting); charitable_solicitation (Charitable solicitation); construction (Construction or home improvement (contractor)); operate_psilocybin_healing_center (Operate a psilocybin healing or service centre (CO, OR)).