The key figures on a subject, sourced and dated, with the ones to read carefully marked.
2 credits·in-depth·about 2–4 min·12 domains
Name the subject. It leads with the headline number, lays out the figures that matter with their sources and dates, sets comparisons beside them, flags the numbers that need care, and reads where the numbers point.
Anyone who needs the numbers before the meeting, and wants to know which of them are solid.
These are the headings the result renders, read from the same promise the form makes before you spend a credit. A section that depends on what the record holds is rendered when it can be and never promised here.
A figure without a source does not appear. It does not forecast the series, and two figures that disagree are shown as a spread with both issuers named, never averaged into one.
A claim the scan could not source is marked as such rather than dressed up. How the grades work →
A domain may name it in its own words and price it on its own terms; each row is what that domain shows.
Boeing has recorded roughly $8 billion in cumulative losses on the KC-46 tanker program alone, per company disclosures through the fourth quarter of 2025 — the clearest documented case of fixed-price risk transfer failing to…
88% of organizations use AI in at least one business function (Stanford HAI AI Index 2026 / McKinsey), but only 6% attribute 5%+ of EBIT to AI with significant impact — a 82-point gap between adoption and monetization.
Teachers earned 74.8 cents on the dollar in 2025 versus comparable college graduates (a 25.2% pay penalty) — EPI/CEPR, August 2026 — while prep-program completions have fallen from ~214,000 to ~160,000 a year since 2010-11.
The fastest way to judge the result is to pick a subject you know cold and read it against what you know. The scan names its credit cost before it runs.