AI Governance API

OpenAPI 3.1 spec

Canonical spec at /api/openapi. Import into Postman, Insomnia, Swagger UI, or your preferred OpenAPI client. CORS-open; no auth required to read the spec itself.

Try it now (no auth, no signup)

Hit the public catalog from your terminal:

curl -s https://policywindow.org/wiki/catalog/json | jq '.instruments[0]'

Returns the first instrument record — about ~30 lines of JSON. Truncated example:

{
  "shortCode": "EU-AIA-2024",
  "name": "EU AI Act",
  "jurisdiction": "EU",
  "kind": "binding_regulation",
  "level": "binding",
  "adoptedDate": "2024-07-12",
  "effectiveDate": "2024-08-01",
  "status": "in_force",
  "sourceUrl": "https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:32024R1689",
  "sourceCitation": "Regulation (EU) 2024/1689 of the European Parliament...",
  "externalIdentifiers": {
    "wikidata_q_id": "Q117205559",
    "eli_uri": "http://data.europa.eu/eli/reg/2024/1689/oj",
    "celex_number": "32024R1689"
  },
  ...
}

For agent / MCP integration, see /llms.txt (curated AI-assistant ingestion guide) and /llms-full.txt (full-context companion with methodology + charter inline).

Free public endpoints

All free endpoints are CORS-open, no auth required. Cached at the edge for 5 minutes.

• GET /wiki/catalog/json — full structured catalog (instruments, topics, concepts, benchmarks, coverage cells, citations, confidence tiers, CC0 citation graph per I4OC).
• GET /wiki/query.json — deterministic structured query (filter by instrument, topic, jurisdiction, coverage type, confidence, has-excerpt) returning citation-bearing cells without downloading the full dump; human form at /wiki/query.
• GET /wiki/graph.json — the catalog as a citation / evidence network (nodes: instrument / topic / source; edges: coverage / evidence / lineage) for scientometrics and knowledge-graph tools.
• GET /wiki/prose-citations.json— the inline citations inside every article's analytical body sections (DOI / arXiv / statute-provision / author-year), with DOI & arXiv anchors resolved against the literature corpus. CC0 citation data so agents can ingest the analysis and its citation network, not just the matrix.
• GET /wiki/synthesis.json — per-theme cross-article research dossiers: cross-jurisdiction instrument stances + evidence convergence (sources cited across multiple articles). Human pages at /wiki/synthesis.
• GET /wiki/currency.json— living-review currency certificates: which topic articles' last review predates a governing instrument's latest review (review-recommended) + the review-due cadence. Dashboard at /wiki/currency.
• GET /wiki/comparative-quality.json — an adversarial head-to-head: Policy Window vs the live Wikipedia article + a published review per subject, scored on six dimensions (reports where PW loses). Scorecard at /wiki/comparative-quality.
• GET /wiki/openapi.json — OpenAPI 3.1 descriptor of these read endpoints (import to Postman, generate a typed client, or let an agent auto-discover the surface).
• GET /wiki/<slug>/snapshot.json?asOf=DATE — tamper-evident snapshot record (serializedRow + contentHash) so a cited ?asOf= snapshot can be proven unaltered.
• GET /wiki/<slug>/diff.json?from=DATE&to=DATE — verifiable field-level changes between two dated snapshots, anchored by both content hashes.
• GET /wiki/catalog/csv — one-row-per-cell expansion of the coverage matrix (RFC 4180 CSV; CSVW metadata at /wiki/catalog/csv-schema).
• GET /wiki/catalog/jsonld-context — JSON-LD @context for the pw: vocabulary (RDF-compatible).
• GET /wiki/[slug]/datacite.xml — per-article DataCite 4.4 metadata for Zenodo / DataCite Commons / institutional-repository ingestion.
• GET /wiki/[slug]?asOf=YYYY-MM-DD — historical-snapshot pinning. See /wiki/persistent-id.
• GET /wiki/changelog/feed — RSS 2.0 feed of catalog changes, ETag-cached.
• GET /sitemap.xml + /robots.txt — crawler discovery.

Authenticated + commercial scopes

Premium endpoints are bearer-token-gated via scoped tokens issued from /api/auth/issue-bearer. The following scopes are documented (Batch B+ availability):

• api.premium — premium exports with provision-level fields + historical snapshots
• change-feed.subscribe — paginated SemanticDiff endpoint /api/change-feed
• research-module.read — research-module records (ResearchModule, CaseStudy, InterviewEvidence)

Commercial licence + scope provisioning is available on inquiry — email hello@policywindow.org with your use case. See /wiki/services for the full offering description.

Stable identifiers

Instrument short-codes (e.g. EU-AIA-2024, US-EO-14110), topic codes (e.g. foundation_models), concept codes (e.g. frontier-tier), and slugs are stable under PW's naming convention. URL renames issue a 308 redirect from the old slug; the old short-code is preserved as an alias in the JSON dump. Use the short-code as your foreign key, not the URL slug.

Citation in your output

When you cite a Policy Window catalog cell in downstream output, use the ?asOf=YYYY-MM-DD URL form so the citation is permanent. The recommended form:

Eight reference-manager export formats per article (APA, Chicago, Harvard, BibTeX, RIS, CSL-JSON, OSCOLA, Bluebook); DataCite XML at /wiki/[slug]/datacite.xml pre-stages Q4 2026 Zenodo DOI registration.

MCP / agent endpoint roadmap

An MCP (Model Context Protocol) endpoint exposing the catalog as an agent-readable substrate is on the roadmap. Until that ships, the OpenAPI 3.1 spec + the catalog JSON dump are the canonical agent-integration path — both designed to be parsable by LLM tool-use without schema-inference workarounds.

Licensing

Catalog content (article prose, coverage cells, notes, citations): CC BY 4.0. Source code (this Next.js application): MIT. Citation graph specifically (structured citation triples): CC0 1.0 per the I4OC norm. See charter §5.