Guides

Give an AI agent a way to pull structured market data, then let it analyse. A runnable walkthrough — the loop from the definition page, closed.

A backtest is the standard way to evaluate a rule — and the standard way to fool yourself. Three checks that separate a result from a screenshot: look-ahead protection, costs, and survivorship.

A REST call works once. An MCP server tells the agent what exists, what the parameters are, and what comes back — so it can plan without being taught each endpoint. When to use which.

A screener turns a vague idea — "cheap, quality, small" — into a reproducible filter. The discipline is in stating each factor precisely, and in knowing what the screen cannot tell you.

Single-stock backtests flatter almost everything. A portfolio backtest adds the parts that decide whether a strategy survives: correlation, rebalancing, and the costs that only appear when many positions trade at once.

Most "risk management" advice is about exits. The bigger lever is how much you put in each position — because a strategy survives or dies on position size long before it depends on the exit rule.