Back to docs

Documentation

Data sources

Where the data comes from.

Every Sentinellis report is assembled from public and licensed data providers. We don't scrape and we don't resell raw feeds — and every figure is cited back to its origin. Here's how it's sourced.

I

Our data principles

  • Every claim in a report carries an inline citation.
  • We prefer T1 sources (Reuters, Bloomberg, AP) when stories overlap.
  • When a source is unavailable, we ship the report with a flagged gap rather than guessing.
  • We never sell, share, or aggregate user data with these providers.

II

Active providers

Financial data

Licensed

Fundamentals & market data

What it provides

  • ·Ticker resolution (company name → symbol)
  • ·Real-time quote: market cap, P/E, dividend yield
  • ·Income statement (revenue, EBIT, net income, EPS)
  • ·Balance sheet (assets, liabilities, equity)
  • ·Cash flow statement (operating, investing, financing)
  • ·Company officers (CEO, CFO, key VPs + total comp)
  • ·Sector, industry, employee count
Freshness

Updated within minutes for quotes; quarterly for statements (after company filings).

Gaps

Sparse for non-US tickers, very small caps, and companies not listed on major exchanges. Individual fields can fail upstream — handled by fail-soft.

News coverage

Licensed + public

Recent news, relevance-ranked

What it provides

  • ·Articles from tens of thousands of publishers globally
  • ·Recent-window filtering (last several days)
  • ·Publisher-tier metadata (Tier 1: Reuters, Bloomberg, AP)
  • ·Country + language filters
Freshness

Articles indexed within hours of publication. We cap to a recent window for relevance.

Gaps

Coverage is thinner for niche or non-English companies. Multiple providers run in parallel with fallbacks so a single outage doesn't blank the section.

AI synthesis

Proprietary pipeline

Report assembly & relevance scoring

What it provides

  • ·Final report synthesis with inline citations
  • ·News article relevance scoring
  • ·Per-article plain-English summaries
  • ·Strict JSON schema enforcement on all outputs
Freshness

On-demand. Each report run triggers fresh inference — no AI output is cached separately from the report.

Gaps

Subject to upstream rate limits and content policy. On hard errors, the report ships fail-soft with an "analysis unavailable" banner instead of a missing section.

Company logos

Public

Report & share-image branding

What it provides

  • ·Company mark resolved from the public company website
  • ·Used in report headers and OG share images
Freshness

Fetched at report time, cached implicitly with the report.

Gaps

Some companies have generic placeholder marks; we degrade gracefully to the company initial when none is available.

III

What we don't use (yet)

Direct regulatory-filing ingestion

Annual and quarterly filings flow through our financial data provider today. Direct filing ingestion is on the roadmap — it would unlock richer segment data and longer historical series.

Private-company registries

Legal-entity ground truth for private companies via national business registries. Designed but not yet wired into the pipeline. Priority for the B2B tier.

Social-platform scraping

We don't scrape. Executive data comes from official company filings, not social platforms — whose terms prohibit automated access without authorization, and we respect that.