SEC filings for AI agents need a retrieval contract
An agent can retrieve public filings without an EDGAR API key, but “public” does not mean unconstrained. The SEC asks automated clients to identify themselves with a declared User-Agent and currently limits request rates to no more than ten per second in aggregate. The system should cache responses, use bulk files for large jobs and retain the source URL.
Choose the EDGAR surface that matches the task
The strongest architecture does not treat EDGAR as one endpoint. It selects a source according to whether the agent needs filing discovery, primary documents, structured facts or large-scale ingestion.
Keep three clocks separate: the fiscal period described, the filing date shown in indexes and the accepted timestamp recorded by EDGAR. A document may appear minutes after its timestamp under normal conditions, but availability is not a guaranteed real-time feed. For historical analysis, store when your own system first retrieved the record as well. That extra clock prevents a later backtest or agent evaluation from assuming evidence was available earlier than it actually was.
Submissions API
Use a CIK to discover recent forms, accession numbers, filing dates and primary documents. Preserve the returned metadata before ranking documents.
EDGAR Archives
Retrieve the filed HTML, exhibits and filing directory. Narrative disclosures, footnotes and risk language live here and cannot be replaced by numeric facts alone.
Companyfacts / Frames
Use XBRL facts for normalized values, units, periods, forms and filed timestamps. Validate taxonomy, context and amendments before comparison.
Bulk ZIP files
For broad ingestion, use the SEC’s nightly submissions and companyfacts archives rather than repeatedly crawling per-company endpoints.
Official references: EDGAR application programming interfaces, SEC developer resources and fair-access guidance, and accessing EDGAR data.
Build a seven-stage SEC filing RAG pipeline
Resolve the issuer
Map name or ticker to CIK, then verify legal name and exchange. Ticker mappings can change; the CIK is the stable EDGAR identity.
Define the filing scope
Specify form types, filing-date window, report period, amendments and exhibits. Do not silently mix annual, quarterly and event disclosures.
Fetch politely
Declare an organizational User-Agent, rate-limit globally, retry with backoff, cache immutable filings and log request status.
Preserve originals
Store the accession number, source URL, primary HTML, relevant exhibits, retrieval time and content hash before parsing.
Parse by section
Segment 10-K and 10-Q items, tables, footnotes and exhibits while keeping headings, anchors and page context attached to every chunk.
Retrieve with metadata
Filter by CIK, form, filed timestamp, period and amendment status before semantic ranking. Retrieve neighboring chunks for context.
Answer and verify
Require section-level citations, distinguish quoted facts from inference, surface conflicts and route consequential conclusions to human review.
Teach the agent what each filing can and cannot prove
Make every answer traceable to a filing section
Minimum evidence record
issuer_cik · legal_name · form · accession_number
filed_at · accepted_at · report_period · amendment
document_url · section · anchor · excerpt_hash
Separate fact, calculation and inference
A filing may state revenue; a margin is a calculation; a claim that pricing power improved is an inference. Label each layer, expose the formula and cite the exact filing text or XBRL fact used.
Resolve conflicts before synthesis
Prefer the correct issuer, period and latest applicable amendment, but retain conflicting evidence. A later filing may update prior disclosure without erasing what was known at the earlier date.
Treat filing text and exhibits as untrusted input
SEC-hosted content is authoritative as a filing record, but it is still external content supplied by filers. An AI agent must never follow instructions embedded in a document, reveal secrets, change tool permissions or execute links merely because the text appears in EDGAR.
Sandbox parsing
Disable active content, scripts and arbitrary file execution. Normalize HTML while retaining evidence anchors.
Bound tool authority
Retrieval tools should be read-only, domain-scoped and unable to access unrelated credentials or systems.
Validate outputs
Check every citation, number, unit, period and issuer against stored evidence before release.
Escalate impact
Legal, compliance and investment conclusions require qualified human review. A fluent answer is not proof of completeness.
Use QVeris to govern SEC and financial-data tools
Authorized discovery
QVeris can help an agent select approved SEC, FMP and research tools rather than inventing endpoints or mixing providers silently.
Bounded execution
Policies can constrain domains, methods, dates, quotas and credentials while logging which tool produced each artifact.
Provenance handoff
The workflow can preserve filing metadata and evidence links for the model and reviewer. QVeris does not certify completeness or provide legal or investment advice.
Continue with QVeris guides on financial RAG, financial statement analysis, and what a 13F filing shows.
SEC filings for AI agents: common questions
Can AI agents access SEC filings?
Yes. Agents can use public EDGAR APIs and archives, subject to SEC fair-access guidance, declared User-Agent identification, rate limits and appropriate caching.
Is the EDGAR API free and does it require an API key?
The public data.sec.gov APIs do not require authentication or an API key. That does not remove rate, identification and usage obligations.
Which SEC filings should an AI agent use?
Choose by question: 10-K for annual context, 10-Q for interim change, 8-K for material events, 13F for limited institutional holdings, plus amendments and exhibits when applicable.
How should an agent cite a filing?
Include issuer, form, filing date, accession number, document URL and exact section or anchor. Preserve the supporting excerpt and distinguish inference from filed fact.
How do I reduce hallucinations and prompt injection?
Retrieve bounded evidence, require citations, validate numbers and metadata, treat document instructions as data, restrict tool authority and send consequential outputs to review.
Can QVeris guarantee complete SEC research?
No. QVeris can govern authorized tools and provenance, but completeness, interpretation, legal compliance and investment judgment remain the responsibility of the research process and reviewer.