quant_* tool: series transforms and algebra, calendar operations, rolling statistics and regression, returns, realized and exponentially weighted volatility, correlation and beta, drawdown, Sharpe ratio, technical indicators (moving averages, Bollinger bands, RSI, MACD, trend and seasonal adjustment), basket and rule backtests with rebalancing and costs, event studies, SIR/SEIR epidemic models and business-day calendars with your own holidays. It runs on Fincept’s servers; your agent sends numbers or data references and gets back a result envelope with tables and charts.
Fincept Quant tools are free. They count toward the rate limit only; a
$fincept reference inside a call is charged like a direct call to that tool.Modules
Tools are grouped in modules. Each module is a toolset namedquant_<module>, so you can list it or search within it. The Fincept Quant reference lists every module and tool.
quant_catalog returns the live list of modules and tools from inside your agent.
Inputs
Limits
A computation that runs past its time limit answers
timeout; a busy engine answers busy and the call can be retried a few seconds later.
Outputs
Series tools return the result as a datedseries with a line chart (an area chart for drawdowns, a band chart for Bollinger bands). Backtests return the basket level or equity curve with total return, annualized volatility and maximum drawdown, and rule backtests add every order and the trade ledger. Date tools return one row per date as a table.
Example
Prompt
realized volatility, finds quant_volatility, quant_sharpe_ratio and quant_correlation, and passes each series’ closes and dates as $fincept references to market_get_candles (candles.close and candles.time).