ENSEMBLE
Author

Maddox Southard

Founder, ENSEMBLE

Maddox Southard builds ENSEMBLE, research software that turns plain-language descriptions of systematic investment strategies into executable code and sandboxed backtests. He writes about portfolio backtesting, systematic strategy design, and agent-native tooling for quantitative research.

Portfolio backtestingSystematic investment strategiesTactical asset allocationModel Context ProtocolQuantitative finance software

Guides by Maddox

  1. StrategiesDual momentum: the rules, the evidence, and a backtestDual momentum combines relative momentum (hold the recent winner) with absolute momentum (move to cash when the winner is falling). Here are the exact rules, why it works, when it fails, and a hypothetical backtest you can rerun.
  2. StrategiesRisk parity: how it works, how to size it, and a backtestRisk parity weights each asset so that it contributes equal risk to the portfolio, instead of equal dollars. Here is the logic, the simple inverse-volatility version you can implement yourself, where it breaks, and a hypothetical backtest to rerun.
  3. StrategiesThe 60/40 portfolio: rules, variants, and a backtestThe 60/40 portfolio holds 60 percent stocks and 40 percent bonds and rebalances back to those weights. Here is why it became the default, how rebalancing frequency and bond duration change it, the permanent and all-weather variants, and a hypothetical backtest to rerun.
  4. StrategiesThe 200-day moving average strategy: rules, evidence, and a backtestThe 200-day moving average rule holds an asset when its price is above its long-term average and moves to cash when it is below. Here are the exact rules, the research behind them, the whipsaw problem, and a prompt that backtests it in under a minute.
  5. BacktestingHow to backtest a portfolio without writing codeA step-by-step walkthrough of backtesting a portfolio from a plain-language description: choosing the universe, stating the rule, running the test, reading the tear sheet, and deciding what to change. Takes about ten minutes.
  6. BacktestingBacktest metrics explained: CAGR, volatility, Sharpe ratio, and max drawdownWhat each number on a backtest tear sheet means, how it is computed, what a reasonable range looks like for a diversified portfolio, and how the metrics mislead when read alone. Definitions for CAGR, volatility, Sharpe ratio, maximum drawdown, turnover, and time in market.
  7. BacktestingCommon backtesting mistakes and how to avoid themThe ways a backtest lies: lookahead bias, survivorship bias, overfitting, ignored costs, short or regime-limited samples, and misread metrics. What each one looks like, how to detect it, and what a backtesting tool can and cannot protect you from.
  8. AI agentsWhat is a finance MCP server, and is there one for backtesting?A finance MCP server gives an AI assistant tools for investment research. This guide explains how MCP works, what separates a data-lookup server from a backtesting server, hosted versus local servers, authentication, and the tools ENSEMBLE's server exposes.
  9. AI agentsHow to backtest a strategy with ClaudeConnect Claude Desktop or Claude Code to ENSEMBLE's MCP server and backtest a strategy in conversation. Setup for both clients, a real session from idea to tear sheet to revision, and the prompts that get good results from an agent.
  10. ComparePortfolio Visualizer alternative: when to switch and when not toAn honest comparison of Portfolio Visualizer and ENSEMBLE for portfolio backtesting: what Portfolio Visualizer does well, its pricing and limits as of September 2026, what it cannot express, and the cases where each tool is the better choice.
  11. Comparetestfol.io alternative: an honest comparison with ENSEMBLEtestfol.io is the community favorite for fast, free portfolio backtests on daily data. This comparison covers what it does well, its pricing as of September 2026, where its form-based approach stops, and when ENSEMBLE's plain-language strategies, composition, and agent access are the better fit.