For financial AI agents, accuracy is mandatory. Scraping third-party stock-tip sites introduces noise and stale calculations. Reliable financial grounding requires querying official regulatory reports directly from the U.S. Securities and Exchange Commission via the SEC EDGAR API.
To query corporate submissions, you need the company’s Central Index Key (CIK), padded to 10 digits. For example, Apple Inc.’s CIK is 0000320193.
The SEC API has a strict header requirement: you must declare an active User-Agent containing your organization’s name and email address. Failing to do this results in a 403 Forbidden response.
Here is a request in Python:
import requests
headers = {
'User-Agent': 'Deep Web Technologies support@deepwebtech.com'
}
# Fetch all recent submissions for Apple Inc.
url = "https://data.sec.gov/submissions/CIK0000320193.json"
response = requests.get(url, headers=headers)
data = response.json()
print(f"Company: {data['name']}")
print(f"Recent filings count: {len(data['filings']['recent']['form'])}")
This returns structured metadata for quarterly (10-Q) and annual (10-K) reports. By feeding these official reports directly to your retrieval pipelines, you ensure your financial agents analyze verified, compliant figures. To see how to wrap this endpoint into a standardized system interface, read our article on eliminating the connector tax.