Search what people said outside earnings calls, in
two kinds of source:
- Interviews: podcasts, TV interviews and conference talks by company
executives, investors, fund managers, analysts, economists, journalists
and other guests.
- Central-bank documents: speeches, testimony, policy statements, minutes,
press-conference transcripts, projections and reports from 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.
Documents in other languages yield English paraphrases.
Use it for questions about what a named person or institution said: "what has
Waller said about rate cuts", "what did the ECB say about inflation at its last
meeting", "what did Jensen Huang say about export controls". 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.
How to search: put one to three key words in query, and put the speaker in
person, the publisher in institution and the kind of document in
appearance_type. A returned row must contain most of the query words, so a
long question returns fewer rows than its key words alone. Retry with the
speaker's own vocabulary or a synonym before concluding there is no coverage.
No serving-time model interprets or expands the query: retrieval is lexical,
not semantic. It tries strict full-text matching 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.
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.
"all" maps to "search", "videos" to "appearances", and "companies" to
"coverage" for older clients; "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 value found only there is listed under
company_references.
- person is a case-insensitive substring over the finding speaker and/or
appearance speaker metadata. appearance_type applies to every target:
podcast, tv_interview, conference and other for interviews; speech,
testimony, minutes, statement, press_conference and hearing for official
documents. country ("US") restricts every target to official documents of
that country; institution ("Federal Reserve") is described with show and
channel below.
- claim_family restricts structured claims. With blended search it suppresses
passage cards; pairing it with search_target="passages" is an error. For
appearances/coverage it requires videos with matching structured claims.
- date_from/date_to are inclusive YYYY-MM-DD bounds on the video's stored
publication/upload date, which can differ from the recording or event date.
- show, channel, and institution are case-insensitive substrings of a
podcast show name, a YouTube channel name, and a publishing institution;
each returns only rows of its own kind, and when more than one is given
rows matching any of them are returned.
- relevance orders lexical score first, then publication date; newest orders
publication date first, then lexical score. Coverage has fixed inventory
ordering by latest covered publication date.
- limit is one page of 1-50 rows and offset skips that many ranked rows
before the page, so limit=15 with offset=15 returns rows 16-30 of the same
ranking. Every result carries has_more, plus next_offset when more rows
follow; call again with that offset to read the next page.
With an empty query, each target browses its most recent rows (search and
claims show claims only).
Evidence safety: canonical_paraphrase is a normalized paraphrase, not a
transcript quotation. Cite source_url (timestamped for YouTube, page-anchored
for PDF transcripts) with the returned speaker, publication date, and video
or document metadata. FOMC minutes describe the meeting of event_date and are
published three weeks later; the Committee, not one person, is their speaker. Do not put canonical_paraphrase
in quotation marks unless you independently verify the wording at the source
link. The tool never returns raw transcript text.
Detail-field safety: internal audit flags are not published; judge a claim
from value, assertion_status, and the timestamped source link.
company_attribution_confidence and company_attribution_source concern only the
video-to-company/ticker assignment; inferred attribution is not independent
confirmation.
