Ask one question of twenty companies at once.
Matrix is a comparison grid you build yourself. Companies across the top, your questions down the side, and every cell answered from that company's own earnings calls and filings — so a row reads as a like-for-like comparison instead of twenty summaries you have to reconcile by hand. Every answer traces back to the sentence it came from.
Start free trial See how it works →| Company | MSFTMicrosoft | GOOGLAlphabet | AMZNAmazon |
|---|---|---|---|
| Source Documents | Q4 2026 Earnings Call | Q4 2026 Earnings Call | Q4 2026 Earnings Call |
| Revenue | $90.0B (Q4 FY26) | $96.4B (Q2 26) | $167.7B (Q2 26) |
| Revenue growth | +18% y/y (+17% cc) | +14% y/y | +11% y/y |
| Margin | 46.2% GAAP | 32.4% GAAP | 11.0% GAAP |
| Beat or miss | Revenue above the top end of the guided range; management cited stronger cloud consumption than planned. | Ahead on advertising, in line on cloud. | Above on operating income, in line on revenue. |
| Guidance | Q1 revenue guided to $93.5–94.5B, ~16% growth at the midpoint. | No formal revenue guidance given. | Q3 operating income guided to $19.0–23.5B. |
Illustrative values, shown to make the shape clear. A real matrix reads your chosen companies' actual filings and transcripts.
Every answer is traceable
Each cell keeps the sentences it was taken from. Click one and the transcript opens at that passage with it highlighted — so you can check a number in a second rather than trusting it.
Read from primary sources
Answers come from the filings and earnings calls themselves, not from a model's memory. If the documents do not say, the cell says so rather than guessing.
Mix data with analysis
Drop in market data and financial-statement rows alongside the AI ones. They fill instantly, cost nothing, and sit in the same grid.
Question the whole grid
Ask across every cell at once — who grew fastest, who is most levered — and get an answer with a citation on each claim pointing back to the cell it came from.
Built for a team
Share a matrix, see who else has it open and which cell they are on, and watch answers appear as colleagues run them.
Start from a template
Ten ready-made grids — earnings scorecard, credit and leverage, unit economics, capital allocation — with the questions already written the way good questions are written.
Ask the market a question. Get a calculated answer.
The AI is not a chatbot bolted onto a document store. It calls the same analytics engine that powers every screen on this platform — so what comes back is a number it computed from raw history, with the command that produced it.
86,000+ instruments
Global equities, ETFs, funds, options, FX, commodities, crypto, economics, filings, transcripts and news — one normalised symbol universe with adjusted history.
A real analytics engine
Screening, backtesting, technicals, options analytics, correlations, seasonality and factor models — computed on demand from raw prices, never a stale cache.
It shows its working
Answers arrive with the charts, tables and tool calls behind them, so you can check the number instead of trusting a paraphrase.
Your own documents
Upload filings, decks and research. Ask across them and the answer cites the page it came from.
Agents and workflows
Multi-step research that runs the platform's tools for you — screen, pull the history, compute, compare, then write it up.
MCP, CLI and API
The same command catalogue from Claude, your own agent, a shell or your pipeline. The answer on screen is the answer your job gets at 4am.
You ask
“How does NVDA usually trade through earnings?”
It calls
→ ka.options_expected_move(NVDA)
It answers
NVDA has averaged a 9.2% absolute move on the day after earnings and closed higher 67% of the time. Two in three reactions land between −4.2% and +16.3% — the distribution is skewed right, not symmetric.
Every figure computed live from our own history — not scraped, not summarised.
Or start with