Plan: Free and above · Credits: 1 per call · MCP tool:
retrieveWhat You Can Use Semantic Retrieval For
Answer open-ended qualitative questions — what did management say about AI, how did they explain the margin move, what risks did they highlight, what was said about pricing or tariffs. Ground an LLM answer in citable source text. Compare how several companies described the same issue in the same quarter. The transcripts are not only earnings calls. Retrieval also searches management’s non-earnings appearances — broker and investor conference fireside chats, analyst and investor days, keynotes, strategic-deal calls and shareholder meetings — so “what did the CEO say at the investor conference” or “what did they tell analysts at investor day” is a retrieval question too. Both kinds are searched together by default.Semantic Retrieval Complements the Structured Endpoints
Retrieval and the structured datasets answer different halves of a question and are not alternatives. When the discussion concerns forward guidance, also call Management Guidance and present the parsed values alongside the supporting passages. When it concerns reported figures or KPIs, also call Reported Earnings Figures. Searching prose for a number a structured endpoint serves wastes a call and returns commentary instead of a value.How Period Filters Change Retrieval Behaviour
Leaveyear and quarter unset unless the caller named a specific period.
With no period set, the search covers the whole corpus and ranks recent documents higher. This is the correct behaviour for “latest”, “most recent”, and for any unqualified question.
Setting year restricts candidates to that fiscal year. Setting both year and quarter additionally turns the recency preference off.
For an earnings call, year and quarter are the fiscal period the call reports on. For a conference transcript, they are the calendar quarter in which the event took place.
What a Retrieval Result Carries
Each returned passage carries the text itself plus the provenance needed to cite it: the company, the year and quarter, the document type, the source URL, and page numbers where the source has them.documentType is earnings_call or conference_transcript, and documentTitle is a dated title naming the call or event. Transcripts carry no source link: sourceUrl is null for both earnings calls and conference transcripts.
Because every passage is traceable to a specific document and period, an answer built from them can always be checked against the original.
Semantic Retrieval Sources
Retrieval runs over the FocusAlpha document corpus: earnings call transcripts, a separate store of non-earnings management speech (conference firesides, analyst and investor days, keynotes, deal calls and shareholder meetings), and SEC filings and company documents. Earnings calls and conference transcripts are searched together and merged unless you passfilters.source_types. The ranking is computed by FocusAlpha; the text is the source document’s own.
Query Semantic Retrieval
Use the retrieve endpoint with a natural-language query. It is aPOST, and it authenticates with a bearer token.
string
required
The natural-language search query, between 1 and 2000 characters.
string[]
Restrict the search to these companies.
integer
Restrict to this fiscal year. Omit unless the caller named a year.
string
Restrict to this fiscal quarter:
Q1, Q2, Q3 or Q4. With year, it also disables the recency preference.string[]
Document types to search:
earnings_call and/or conference_transcript. Omit it to search both, merged — the right default. ["conference_transcript"] searches only conference fireside chats, analyst and investor days, keynotes, deal calls and shareholder meetings; ["earnings_call"] searches only earnings calls. A list that names neither type is treated as no filter.integer
Number of passages to return, between 1 and 50. The ceiling is also capped by plan — see Plans and credits.
boolean
Re-rank the candidate passages for relevance.