ask_authority
Query a published authority on the NOMOS Exchange marketplace — a different system from verify_decision's own governance artifacts. Every public authority (e.g. eu-ai-act.nomos) is queryable with no key. Returns the authority's own verdict (AUTHORIZED/DENIED/ESCALATED), the exact rule and reason, and a permanent, cryptographically-bound transcript (query_id + url) — replayable evidence, not just a reply. Nothing is invented or paraphrased: the verdict is the authority's sealed rules evaluated against your inputs. The default response is a short, curated summary (verdict, matched rule, source citation when the artifact has one, transparency/completeness disclosures, transcript link) — not the full rule-by-rule evaluation trace. Set include_evaluation_trace: true to get that complete diagnostic record when you or the user actually need it.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | No | Optional label for what this query represents, for the caller's own transcript record (e.g. "pre-deployment check"). Purely descriptive — does not affect the verdict. | |
| inputs | Yes | Key/value facts to evaluate against the authority's rules (e.g. {"ai_categorises_biometric_data_for_sensitive_attributes": true}). Fields must match the authority's vocabulary — see the atlas endpoint or the artifact's catalog page. | |
| authority | Yes | The Exchange artifact's standard name — its short slug, optionally ".nomos"-suffixed (e.g. "eu-ai-act" or "eu-ai-act.nomos"), or its raw artifact ID. Browse the catalog at https://www.nomosprotocol.com/exchange. | |
| exchange_api_key | No | Exchange API key (nxk_...). Optional for free/public queries. Required only for metered access to licensed (paid) authorities beyond their free allotment. | |
| include_evaluation_trace | No | Set true to receive the full rule-by-rule evaluation trace (every rule checked, every missing field) instead of the default curated summary. Most callers never need this. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | Path to the permanent, shareable transcript for this query | |
| verdict | No | The authority's own verdict | |
| query_id | No | Permanent transcript ID — reopen any time at the returned url | |
| expected_fields | No | Present only when ESCALATED for lack of data — the fields this authority still needs | |
| matched_rule_id | No | ID of the rule that determined the verdict — null when AUTHORIZED with no matching rule | |
| response_source | No | Provenance label — this is a sealed NOMOS verdict, not Claude's own reasoning. Preserve or restate this distinction when relaying the answer. | |
| rules_evaluated | No | Only present when include_evaluation_trace was true | |
| source_reference | No | Citation for the matched rule, when the source document's structure was captured at extraction time. Names where the rule TEXT was extracted from (e.g. "Article 5"), not a legal claim about what it covers. Null if unavailable. | |
| matched_rule_name | No | Human-readable name/description of the matched rule — use this for display, not matched_rule_id | |
| verdict_description | No | Human-readable reason — the exact rule and its consequence | |
| rules_evaluated_count | No | Total rules checked during evaluation — the size of the full trace, whether or not it was returned | |
| open_higher_priority_count | No | 0 means every relevant fact was known when this was sealed; >0 means facts were still missing above the matched rule | |
| open_higher_priority_rules | No | The actual rules behind open_higher_priority_count (capped to 20) — use this to answer "which ones?" instead of guessing. Each has the rule name, what it would do if it matched, and exactly which input fields are missing. |