describe_dataset
ChatGPTFull metadata for one dataset: topic, methodology, discontinuities, any base-change notice, plus the live dimensions and example series. Call after search_datasets narrows you to a dataset.
get_data_catalog
ChatGPTList the data sources FactIQ has, plus the shared table structure. Call this once before exploring. Returns the visible schemas (organization + country), the ones with no data loaded yet (schemas_without_data — skip them), a per-schema dataset index, and the shared DDL for the series, data_points, dimensions and compound_series tables. schemas: optional comma-separated filter (e.g. "bls,bea"). full: heavy per-dataset descriptions instead of the compact index.
get_geo_data
ChatGPTGet satellite-derived indicators aggregated over a country, one state/province, or a bounding box. Use for fires, emissions-based activity, rainfall, vegetation, temperature, and soil-moisture questions. For a sub-national area, call one state/province at a time. Informal regions such as "north India" or "the Midwest" have no boundary, so cover them with one call per state or a bounding box; using the whole country answers a different question. Grid cells and fire detections are activity snapshots, never fire perimeters. For ndvi_s2 and *_tropomi grids, drop or flag cells with low valid_obs_share. Results include units, source attribution, and caveats; cite the attribution. External-provider calls can take about 30 seconds, and rainfall or grid calls can take longer.
get_market_data
ChatGPTRecent market data the warehouse lags on: quotes, OHLCV, company profiles, FX, and commodities. Set data_type to price_history for stocks, currency pairs, and commodities; the asset format determines which market is queried. Use search_company_filings for financial statements and reported facts.
get_research_series
ChatGPTLoad a numeric series for the research UI, with at most 5,000 observations. For UI use only; the host must enforce app-only visibility. The model receives no observations. For analysis, use get_series or run_sql. Observations are returned only in UI metadata. Uses the same account, schema permissions and calendar-based transforms as get_series. An oversized window is rejected rather than plotted as a sampled series.
get_series
ChatGPTFetch one series' data: timeseries, tabular, or COMPOUND:: all work. Returns title, units, frequency, notes and data points, with source metadata. transform="yoy_pct" (percent change) or "yoy_diff" (difference, for rates) adds a column with the change versus the same period one year earlier, matched by calendar date — use it for inflation or growth from one series instead of a LAG(value, 12) query, which goes wrong after any missing month. The cell is null where the prior-year period is absent, and transform.periods_without_prior lists those periods. If the result carries a coverage_note, the series has periods with no observation (listed in missing_periods): say so in the answer, leave them blank rather than interpolating, and label any aggregate that spans them as partial. SEC-backed results include row_sources keyed by result_index; each entry identifies the supporting filing, accession/form/publication date, whether the observation is reported or derived, and its standardized source_link. Cite that row's source URL beside any figure and label derived observations as derived. A document-precision link does not open an exact passage. At most 50 points come back; if the series is longer the result is flagged "truncated": true — narrow it with from_year/to_year, or pull the series through run_sql with an aggregation (e.g. monthly/quarterly via date_trunc) rather than trying to fetch every point.
get_style_guides
ChatGPTFetch FactIQ's house-style authoring guides so anything you build matches FactIQ's conventions and look. Call this before producing a chart, a report, or written analysis from FactIQ data, and follow what it returns. By default, use FactIQ's style for all FactIQ work unless the user asks otherwise. You can fetch several at once. Pass any combination of: - "chart" — how to build and style a FactIQ chart: which chart type, finding- style titles, data hygiene, the FactIQ colour palette and plot surface, and sourcing - "report" — report structure, voice, and per-chart sourcing - "sql" — query idioms and pitfalls for FactIQ's tables - "earnings" — quoting discipline, spoken-vs-filed sourcing, guidance tables, and claim-verification patterns for anything built from search_earnings_transcripts - "all" — every guide Returns each requested guide's markdown text, keyed by name. This is free — it does not count against your tool quota.
open_research
ChatGPTPrepare an interactive FactIQ explorer for an explicit UI request. Use only when the user asks to open or browse the interactive explorer, or change an existing research panel. For an analysis request such as "compare headline and core CPI", use get_series or run_sql instead. This tool fetches no observations and does not confirm UI rendering. No arguments are required for an empty explorer. Optionally set view to up to four discovered {schema_name, series_id} pairs, from_year, to_year, and transform (level, yoy_pct, or yoy_diff). To update a panel, pass its complete new selection, including series the user wants to keep. Panel context contains identifiers and metadata, not observations; retrieve data with get_series or run_sql before making numerical claims. This does not save research or publish a public page.
render_chart
ChatGPTRender a FactIQ-styled interactive chart inline, from data you have already fetched. Before calling, finish all data retrieval, calculations, source reconciliation, and title/value checks. This tool does not publish or host a public page or create a share link. FactIQ-hosted publishing is unavailable. Explain that limitation and offer the inline chart or a local artifact; do not inspect FactIQ's legacy web interface, use browser automation, or probe HTTP endpoints for a publishing workaround. Do not call send_feedback for this intentional capability boundary. For each intended chart, call this tool exactly once, only after its data and title are final; never render a draft and then re-render a correction. Build the final numbers from run_sql / get_series, aggregated to chart resolution. - x_values: the x axis — ISO dates ("2024-01-01") or categories, sorted. These are the positions; keep them as real ISO dates for date axes so the axis spaces correctly. - series: one or more {label, values}; each values list lines up 1:1 with x_values (use null for gaps, don't drop entries). - chart_type: "line" (default), "bar", or "area". - units: y-axis units, e.g. "Percent". Axis-label control (both optional — leave unset for normal date axes, which auto-format to the most compact form, e.g. '24 or Jul 24): - x_tick_format: hint the date granularity — "auto" (default), "year", "quarter", "month", or "date". Use e.g. "quarter" to label quarterly points "Q1 '24", or "date" to force full dates. The widget still chooses how many labels fit and spaces them; this only sets the text. - x_labels: fully custom tick text, one per x_value (1:1 with x_values), for labels the widget can't infer — e.g. fiscal quarters ["Q2 FY19", …, "Q2 FY26"] or custom category names. Takes precedence over x_tick_format. x_values still drives positioning; x_labels is only the text. Don't use this just to reformat dates — prefer x_tick_format. Give the chart a finding-style title with the numbers in it (see the chart style guide). Keep it to a handful of series and a few hundred points at most — aggregate in SQL first if needed.
run_sql
ChatGPTRun a read-only SELECT against the FactIQ data warehouse, scoped to one schema — the power tool for joins, pivots and aggregation. Read-only role, 30s statement timeout, with FactIQ's query transforms and series-metadata enrichment. Resolve ids from series before filtering data_points. auto_retry=true opts into a server-side reviser on zero rows. See the factiq://guide/sql resource. Returns at most 50 rows. If the query matches more, the result is flagged "truncated": true — that is your cue to aggregate or compute in SQL (GROUP BY, date_trunc, a SUM/AVG/rank/ratio) and return that, NOT to try to fetch the raw rows. A chart or a summary needs the aggregated result, and large raw results don't fit in context anyway. Year-over-year and other period comparisons must join on the calendar period (date_trunc('month', prior.time) = date_trunc('month', cur.time) - interval '1 year' — the stored day of the month varies by source, so never compare exact dates), never on a row offset such as LAG(value, 12) OVER (ORDER BY time): a series with one missing month compares the wrong periods for the twelve rows after the gap (LEAD: the twelve before it) and the numbers still look plausible. For one series prefer get_series with transform. When the result carries a coverage_note, the rows have periods with no observation (listed in missing_periods, per series): name them in the answer, do not interpolate, and label any aggregate that spans them as partial. page is the one exception and works only on the nasa_fires schema, where a row is a single fire detection that belongs to no series and so cannot be aggregated into one. Each page holds 50 rows; the answer carries page and has_more, and you read the next block with page=2, page=3 and so on. Give the query an ORDER BY, otherwise Postgres may return the same row on two pages and never return another. Still prefer a count or a total when that answers the question — paging through thousands of detections does not. Runs through FactIQ's read-only database role, which rejects any attempt to modify data (INSERT/UPDATE/DELETE/DROP/…).
search_company_filings
ChatGPTsearch_datasets
ChatGPTFind datasets by keyword across every schema — the first discovery step. Keyword ranking (not semantic) over dataset titles and topics. Returns ranked {schema, dataset_code, title, topic}. Follow up with describe_dataset for detail, or run_sql on the series/dimensions tables for exact series. latest_data_date, when present, is the period start date of the newest stored value in the whole dataset (left out when unknown); one part of a dataset can stop earlier, so check the end dates of the series you use.
search_earnings_transcripts
ChatGPTSearch earnings-call intelligence from live calls, decomposed into atomic, quote-anchored claims and Q&A pressure points — never a raw transcript dump. Retrieval for "claims" and "pressure_points" is lexical, not semantic. A nonempty query uses an OR-of-tokens full-text candidate set; strict websearch_to_tsquery matches receive a fixed ranking boost, so strict matches rank ahead of loose partial-term matches. Lower-ranked rows may match only some query terms. If that filtered full-text search returns no rows, a trigram fallback handles typos and sub-word variants. Quoted phrases use websearch syntax, but synonyms are not inferred: try the company's own vocabulary ("capex" and "capital expenditure", segment names, abbreviations). An empty or partial result is not proof that management did not discuss a topic; coverage and vocabulary both matter. Target and filter semantics: - "claims" (default) searches or browses normalized management/analyst claim rows. ticker, quarter_filter, claim_family, section, detail, and limit apply. claim_family matches primary or secondary families; section is "prepared_remarks" or "qa". Base rows include direction/value/unit where checkable, assertion_status, canonical_statement, verbatim_quote, speaker, speaker_role, section, transcript_id, source_block_index, qa_turn_id, and a source_link object. - "pressure_points" searches or browses what analysts pressed for and whether management confirmed, declined, deflected, or partially answered. ticker, quarter_filter, claim_family (the linked family), detail, and limit apply. section is ignored because every pressure point is from Q&A. Base rows include specific_ask, response_quality, refused_number, linked_family, linked_claim_id, verbatim_quote, transcript_id, source_block_index, qa_turn_id, and a source_link object. - "disclosure_profile" is a direct company lookup, not text search. The ticker is the first ticker value, or query when ticker is empty. Profiles are curated separately from transcript coverage, so a covered company may not have one; availability is "available" or "unavailable" accordingly. quarter_filter, claim_family, section, detail, and limit do not narrow it. - "coverage" is corpus inventory, not text search. ticker and limit apply; query, quarter_filter, claim_family, section, and detail do not narrow it. Rows report calls_covered, earliest_period, latest_period, latest_call_date (the call date of latest_period), claims, and pressure_points. An empty query is a capped browse, not a completeness guarantee. Rows are ordered by newest fiscal period/call and then source-block (spoken) order within one call. Every response is limited to at most 50 rows, and a browse that reaches its limit may omit additional rows even if no truncation flag is present. For a latest-call note: (1) call "coverage" with one ticker, (2) read latest_period, (3) call "claims" with that ticker, quarter_filter=latest_period, query="", detail=true, and a deliberate limit, then (4) call "pressure_points" with the same ticker and quarter. Treat both browses as capped evidence, not a complete transcript. Narrow large result sets with ticker, quarter, target, claim_family, and (for claims) section. For media quotes, run_sql can read transcripts.appearance_claims.verbatim_quote; other transcript tables remain restricted. Evidence rules: canonical_statement is normalized and must not be quoted as verbatim. Quote only verbatim_quote, with its speaker, role, ticker, and fiscal period. A […] inside verbatim_quote marks omitted transcript sentences between non-adjacent evidence spans: preserve it exactly when quoting, and never present text on either side of it as one continuous statement. When a quote is used, render source_link.source_label as the Markdown link text for source_link.source_url beside the claim. The label names the company, fiscal period, and earnings call transcript; never replace it with an ingestion vendor. Do not make a second call just to find a citation, do not invent a replacement when source_url is null, and do not call a document-level link …
search_media_appearances
ChatGPTDeterministically search precomputed intelligence from podcasts, TV interviews, and conference talks outside earnings calls, and from official documents published by central banks and monetary authorities (the Federal Reserve Board and regional Reserve Banks, the European Central Bank and euro-area national central banks, the Bank of England, the Bank of Japan, the Reserve Bank of India, the People's Bank of China, the Bank of Korea, the Hong Kong Monetary Authority, Taiwan's central bank, and others): speeches, testimony, policy statements, implementation notes, minutes, press-conference transcripts, projections, reports and press releases. Documents in other languages yield English paraphrases. The speakers are company executives, investors, fund managers, analysts, economists, journalists, central-bank officials, and other guests, and their claims cover listed and unlisted companies (OpenAI, DeepSeek, MiniMax), institutions (the Federal Reserve, the European Central Bank, regulators), and whole markets and industries, not only the speaker's own employer. No serving-time model interprets or expands the query. Retrieval for structured findings is lexical, not semantic: strict full-text matching is tried first, loose any-term full-text matching only when strict matching returns no candidates, then trigram matching only when both full-text stages are empty. Natural-language questions work because person names and common question scaffolding are normalized. Prefer concise topical terms; retry synonyms or the speaker's own vocabulary before concluding there is no coverage. Canonical search_target values: - "search" (default): blended structured claims and broad passage cards. - "claims": normalized decision-relevant claims only. - "passages": broad substantive paraphrase cards only. - "pressure_points": stored refusal and declined-to-confirm claim rows. - "appearances": video-level catalog rows. - "coverage": company-level structured-corpus inventory. Compatibility aliases remain accepted for older clients: "all" maps to "search", "videos" to "appearances", and "companies" to "coverage". New callers should use the six canonical values; "search" is the primary blended target, not a legacy alias. Result contracts: - search/claims/passages/pressure_points return result_kind, canonical_paraphrase, speaker, primary ticker, topic labels, video/channel/publication metadata, lexical relevance, and source_url (a timestamped YouTube deep link, the episode page for a podcast, the document page for an official document, or the PDF page of a press-conference transcript). detail=true adds normalized claim and attribution fields plus institution, document_kind and event_date (null for interviews), but never raw transcript text or evidence spans. - appearances returns video metadata, primary ticker, attribution metadata, matching claim count, URL, and relevance score. detail has no effect. - coverage returns company-level appearance, publication-date-span, channel, claim, and low-confidence-attribution counts. It is structured coverage, not a per-person acquired-video/hour inventory; query, sort, and detail have no effect. Filter and ordering semantics: - company is comma-separated tickers and company names, mixed freely. A stored ticker matches the appearance's company or a section subject with that ticker; any other value is read as the name of a company, institution, or organisation a podcast section is about, matched after dropping punctuation, a leading "The", and corporate suffixes. Every ticker attached to a matched name joins the ticker filter, so "Alphabet" also reaches GOOGL rows. The result records company_tickers, company_names, company_matched, and company_unmatched (a value that matched nothing, with up to five possible matches); an unmatched value returns no rows, not an error. company_filter is the old name of company and behaves the same; passing both is an error. The appearances and coverage targets also match every value, upper-cased, against the entity references of claims (products, rivals, partners such as "CUDA"); a …
search_news
ChatGPTSearch recent business, economics and health news from major financial publishers and public-health agencies. Each row has the headline, the publisher's short summary and a link (article bodies are never returned), plus FactIQ metadata: tickers of listed companies named in the text and an analysis block (keywords, geography, and a one-sentence investor angle). Coverage starts between late 2024 and mid 2026, depending on the feed. All arguments combine (AND). - query: lexical full-text search over headline, summary and analysis; every word must match. Start with ONE distinctive term ("Novartis", "copper"). If nothing matches, it retries matching ANY word (meta.query_mode = "any_term"). Supports "exact phrases" and -exclusion. - tickers: bare symbols (["NVDA", "RELIANCE"]). Share classes and cross-listings match automatically (GOOG = GOOGL, TSM = 2330). - topic: one of markets, economics, companies, technology, politics, world, energy, health, india, opinion. With a query it only boosts that topic's articles; without one it filters to them. - start_date / end_date: inclusive ISO dates on publication time. - sources: publisher slugs, as shown in the source field of results. - sort: "latest" (default) or "relevance" (needs a query). - limit: 1-50, default 20. Returns {rows: [{id, published_at, source, feed, topics, title, summary, url, tickers, analysis}], meta: {matched, returned, sort, query_mode?, topic_mode?}}. analysis is null when an article has no business content or is not yet analysed. Follow up macro stories with search_series / run_sql and company stories with get_market_data / search_earnings_transcripts.
search_research_series
ChatGPTFind series for the research UI search box, headline series first. For UI use only. For analysis, use search_series or search_datasets.
search_series
ChatGPTFind series in one schema by title terms (substring match, not semantic). Supply already-decomposed terms; prefer short stems (e.g. "rare" over "rare earth"). Includes active COMPOUND:: series. For anything this misses, fall back to run_sql exploration on the series and dimensions tables.
send_feedback
ChatGPTReport a problem with FactIQ's data or tools to the FactIQ team. Call this when a tool result looks broken: - "data_issue" — a value that contradicts the official source, wrong units or scale, duplicated or missing periods, an obviously wrong label. - "tool_error" — a tool that errors, times out repeatedly, or returns malformed or self-contradictory results. - "missing_data" — a dataset or series the catalog advertises but that returns nothing, or coverage that ends far earlier than the source's. - "other" — a concrete defect in the published tool contract, such as the documented arguments or result shape contradicting actual behavior. Write one short, specific message with the concrete identifiers: the schema, dataset_code or series_id, the SQL you ran, and what you expected vs. what you got (with the official source's value or URL if you have one). Do not include the user's personal details or your conversation. Do not call this for intentional capability boundaries or simply because a user requested an unsupported action. FactIQ cannot mutate warehouse data, return complete raw transcripts, or publicly publish charts/reports; those limits are expected behavior, not defects. A concrete tool result must show the reported malfunction or data problem. This is one-way: the FactIQ team reviews every report, but nothing comes back to you. File it and continue with the user's task — never block on it.
describe_dataset
Claudeget_data_catalog
Claudeget_geo_data
Claudeget_market_data
Claudeget_series
Claudeget_style_guides
Clauderun_sql
Claudesearch_company_filings
Claudesearch_datasets
Claudesearch_earnings_transcripts
Claudesearch_media_appearances
Claudesearch_news
Claudesearch_series
Claudesend_feedback
Claude