In detail / 02 · RESEARCH

One question, taken to the evidence.

Ask with material and context: read the filing, pull the multi-year data, check the original announcement — and write conclusions with their basis and verification stated. Verified, inferred and doubtful claims stay separate; guesses never pose as facts.

  1. Analyze filingsStart from one quarter's numbers: what is operating improvement, what is one-off, and what a single quarter cannot answer.
  2. Pull dataRevenue, margins, capex and more, listed year by year — with differing calculation bases reconciled and the gaps explained.
  3. Track holdingsAgainst the original SEC 13F filings: adds and trims are judged on share counts, and value moving the other way is flagged as price.
  4. Check the original filingAnnouncements and prospectuses verified against the original document, with links so you can recompute yourself.
  5. Sessions that persistMaterial and dialogue stay in place; the next research session continues where the last one ended, with its basis one look away.

Scene 01 / Analyze filings

“How did Apple do on revenue and profit last quarter — and what can one quarter not answer?”


Facts pulled from the filing

Apple FY2026 Q3 (ended 2026-06-27): revenue $109.417B, net income $29.789B. Next come segment breakdown, cash flow and the year-ago quarter — two numbers alone cannot price a business.

FMP · AAPL income-statement · USD, quarterly; filed 2026-07-31

The structure of a real answer

Take “Research Unitree Robotics with a value-investing lens”: the answer verifies the facts first, then sets price against business, then lists the counterevidence — every part with its source and basis.

  • Verified factsRevenue 2023–2025: ¥159M → ¥393M → ¥1.70B; gross margin 44.2% → 60.1% (from the prospectus, read in full)
  • Price vs businessMarket cap ≈ ¥208.3B, PS(2025)≈123x — the price bets on an 'embodied-AI platform', not current earnings
  • Margin of safetyQ1 2026 adjusted profit −52.6% YoY; buying here means believing revenue grows an order of magnitude — otherwise the margin is thin
  • CounterevidenceDecelerating growth and falling profit coincide; more large share-based payment charges are still being recognized (per the prospectus)

Excerpted from a real research answer (Unitree Robotics).

What research does not do

  • No buy/sell signals and no promised returns — research supports your judgment, it does not replace it.
  • Evidence carries its grade: verified, inferred and doubtful stay separate; guesses never pose as facts.
  • Technical progress alone is not an investment opportunity — price, uncertainty and the business still require investigation.