Company Identification
What defines a company in Captide?
What defines a company in Captide?
We define a company as a publicly listed entity that files its financial results independently. In cases where a company files with multiple market regulators or is traded on multiple exchanges, we consider all such filings and listings to belong to the same entity in Captide—provided they refer to the same underlying corporation.
Which company identifiers does Captide use?
Which company identifiers does Captide use?
Captide assigns proprietary company identifiers (
companyId) to uniquely identify each entity. We also capture organizations’ LEIs and Refinitiv PermIDs. Additionally, ticker symbols, when paired with their respective exchanges, serve as reliable identifiers. Users can retrieve the complete list of available companies, including each entity’s companyId, permId, lei, and associated tickers, through the /api/v1/companies/list endpoint.Document Access
When are new documents available?
When are new documents available?
New documents from US-listed companies are typically available within 1 minute of release. For non-US-listed companies, documents are available within 12 hours. Earnings call transcripts are generally published 6 to 12 hours after the call concludes.
Are all document types available for every company?
Are all document types available for every company?
Annual, interim, and current reports are available for all companies in Captide. Additional document types are provided for companies that have filed them at any point. Note that reporting practices vary by geography (for example, companies in the United States typically file quarterly interim reports, while those in Australia often file semi-annual reports). As a result, the availability and frequency of document types may vary by region, company, and regulatory requirements.
How do available document dates differ? Is point-in-time data available?
How do available document dates differ? Is point-in-time data available?
When retrieving documents, the following date-related parameters provide key information:
date: Indicates the date the document refers to (e.g., the press release date for a current report, or the fiscal period end date for annual and interim reports).filingDate: The date and time the document was made publicly available (useful for point-in-time analysis).fiscalYearandfiscalQuarter: Indicate the fiscal period covered by the document.createdAt: The date and time the document became available in Captide.updatedAt: The most recent date and time the document was updated in Captide.
What is the use case of Markdown versions of documents?
What is the use case of Markdown versions of documents?
Captide transforms original corporate disclosures into LLM-optimized Markdown files that preserve all information and data points from the source documents in a machine-readable format. This enables efficient and interpretable downstream analysis or AI applications, where documents must be chunked and ingested by large language models.
Agentic RAG
What is different between the agent-response and agent-response-stream endpoints?
What is different between the agent-response and agent-response-stream endpoints?
The only difference between the two endpoints is how they deliver AI-generated responses. The
agent-response endpoint is optimized for use cases where the full response is only needed after generation is complete (e.g., data extraction or alert systems). In contrast, the agent-response-stream endpoint streams the response in real time via server-sent events, making it more suitable for chat interfaces and interactive applications.What is the use case of the chunk-retrieval endpoint?
What is the use case of the chunk-retrieval endpoint?
The
chunk-retrieval endpoint is designed for firms that want to retrieve relevant content from corporate disclosures in response to natural language prompts—without involving an LLM, or where greater control over AI-generated responses is required. This is particularly useful for applications that aggregate context from multiple sources, allowing Captide’s retrieved content to be combined with data from other providers or internal systems.How can I verify the source of AI generated answers?
How can I verify the source of AI generated answers?
Every API response from the agentic RAG endpoints includes metadata about the sources and document excerpts used to generate the answer. The
agent-response and agent-response-stream endpoints provide sentence-level attribution to excerpts from corporate disclosures. Clients can programmatically access these excerpts and metadata, or use the Captide SDK to easily display sources within a document viewer.Refer to the Captide Frontend Integration guide for details on integrating our document viewer for seamless source auditing.
If your question isn’t addressed here, please contact our support team for assistance.