Skip to main content
Driven connects to 245 endpoints across 28 categories. This page categorizes what that coverage includes. The specific source behind any given figure depends on the market and data type; the Agent selects and cross-checks sources as part of each Skill. For coverage boundaries, see Supported markets.

​
Why this matters

The data layer is what separates Driven’s answers from a general model’s recall. Figures are pulled from these sources, not remembered. You can always ask the Agent to cite what it used and flag anything it could not retrieve.

​
Market data

  • Real-time quotes
  • Historical price data
  • Technical indicators
  • Trading volume and liquidity data

​
Fundamental data

  • Financial statements (income statement, balance sheet, cash flow)
  • Historical financials
  • Earnings and dividend calendars
  • Key ratios and metrics
For Hong Kong, A-share, and Chinese ADR stocks, statement data is sourced to match local accounting standards, with faster refresh cycles and cleaner field mappings.

​
Filings and disclosures

  • SEC and exchange filings
  • Company disclosures and announcements

​
Ownership and positioning

  • Institutional holdings and changes
  • Insider activity
  • ETF and fund data and flows

​
A-share-specific data

Driven covers categories of A-share data that general tools usually miss: Capital flow
  • Institutional versus retail fund flow
  • Dragon & Tiger (龙虎榜) lists
  • Block trades (大宗交易)
  • Margin trading (融资融券)
Shareholder structure
  • Shareholder count (股东户数)
  • Share capital breakdown (股本结构)
  • Institutional holdings and changes
  • Executive share changes (高管持股变动)
Company intelligence
  • Thematic sector links (概念联动)
  • Business segment commentary (主营点评)
  • Share pledging (股权质押)
  • Valuation bands (估值带)
  • Historical earnings
  • Peer comparison (同行对比)

​
News and market intelligence

  • Market news
  • Community and social sentiment from Xueqiu and from X / Twitter (X content powered by Grok running xAI’s official X search)

​
How sources are used

When a Skill runs, it knows which source to pull which field from, how to cross-check across sources, and how to handle missing data. This orchestration, rather than the raw endpoint count, is what makes the data layer reliable. See Data and coverage for the concept.