Skip to main content
Scrutica
Tool reference

Query

Ask a question in plain language. The engine plans which of its tools to call, runs them against Scrutica’s records, and cites the records they return. How answers are produced

10 corrections · latest 22 Oct 2026
Conversation visibilityPrivate saving is unavailable. Saved conversations are public.
A saved conversation becomes a permalink anyone holding the URL can read; search engines do not index it.

How an answer is assembled

The engine writes a plan first: which tools it will call, in what order, and which calls wait on an earlier result. The page draws the plan as it arrives, and the calls then run, in parallel where they are independent. A question has at most 8 data-tool calls across every round; calls past that budget are not run, and the answer is written from what was gathered.

The answer cites the records the tools returned: each supported clause carries a numbered marker, and the source list beside the answer has one row per cited record, saying what the record is, the source the tool returned for it, its authority tier where the tool returned one, and its estimate flag and date, with the tool and record identifier in its details. After the answer has streamed, the server checks that each cited identifier was returned in that run by the tool the citation names, and marks any it cannot find unverified provenance. The check does not establish that the record supports the claim. The model failover chain, the tag grammar and the matching rule are at the query-engine methodology.

55 tools; at most 8 data-tool calls per question

Search: —

thinksearch_facilitiesget_facility_detailsget_nearby_facilitiessearch_organizationsget_org_profileget_league_tableget_org_supply_chainget_chokepoint_analysisget_country_interdependenceget_full_supply_chain_graphsearch_investmentsget_investment_timelineget_sovereign_programsget_bis_designationsget_bis_cross_referencesget_entity_list_changesget_country_analyticsget_compute_overviewget_facility_type_breakdowncompare_entitiessearch_hardwaresearch_deploymentsget_compute_pricingsearch_trade_flowssearch_pjm_queueget_capacity_snapshotsget_threshold_compliancelist_threshold_capable_facilitiesget_compute_visibility_indexget_compute_visibility_breakdownwalk_ownership_chainsearch_procurement_recordsget_executed_allocation_rollupget_regulatory_impact_prescoresimulate_cascade_scenarioget_scenario_modelcompute_flop_threshold_compliancederive_cost_index_per_providerget_page_methodologyget_methodology_sectionget_page_contentrecent_editorial_correctionssearch_corrections_logget_data_freshnessget_authority_tier_provenanceget_chokepoint_anatomyget_concentration_metricsget_country_profile_summaryget_emerging_chokepointssearch_bis_license_actionsget_hbm_market_shareget_eu_grid_statusget_recent_developmentsget_training_evidence
55 available tools.
55

tools available to the query engine.

181

distinct fixed-list values across 45 parameters, including logic_fab and eu-ai-act.

—

Search above or try an example:

Each mark is a tool. Search matches tool names, descriptions, parameter names and declared parameter values; it does not search Scrutica’s records.

Scope

The tool reference lists the available searches and analyses. When a requested figure is missing, the model is instructed to say so. Revenue projections, for example, require a source that supplies a forecast. The model can explain regulations and threshold calculations; case-specific legal advice is outside its remit.

The subject box on the figure above matches against the catalogue in the browser and runs no query.