Ask a market question. Get a number back.
A typed API that answers questions about any symbol — not a chat box, not a chart. You write the rule, it returns a probability, a pick, a score or a figure, with the working attached.
Your first 25 calls are on us. After that, about $0.002 each.
-
One request, one answer
POST a small JSON object and get a typed answer back. {"symbol":"NVDA","decision_type":"rsi_check"} is a complete call.
-
A belief, not a verdict
Answers come back 0 to 1. 0.93 is a strong yes, 0.5 means the numbers do not tell you — which a true/false can never say.
-
The backtester's own language
rsi > 70, adx(14) > 25, C > highest(C,20) + 0.5 * atr(14). The same grammar as an entry condition in Backtest Quick, not a second dialect.
-
Five answer shapes
Yes/no, a choice with odds on every option, a score between rungs, a ranking with strengths, or a plain number out of the state.
-
Daily or intraday
Daily bars from our own database, or 1m to 1h built live. Mix timeframes in one rule — C@1d reads the last closed daily bar.
-
Or just ask in English
Swap the rule for "instructions" and a model answers in the same shape, against the same state. Rules stay free and instant.
-
142 worked examples
Every one runnable from the page, graded from a one-line preset to a full desk screen. Press Run on any of them.
-
Priced per call, not per seat
$1.00 per million processed tokens — about $0.002 a call. No subscription, no minimum, no invoice.
Write your first rule in about a minute.
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