Skip to content
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 backtestDefine relative and absolute momentum separately, inspect a public model, and compare a parameter change. The example explains the research workflow without promising a historical or future result.
  2. StrategiesRisk parity: how it works, how to size it, and a backtestUnderstand risk contributions and the simpler inverse-volatility weighting rule. Inspect a public model, test one assumption, and distinguish a model specification from a performance claim.
  3. StrategiesThe 60/40 portfolio: rules, variants, and a backtestDefine a stock-and-bond allocation, inspect a public 60/40 model, and test rebalancing or asset changes over matched dates. Learn what the model shows and what it leaves out.
  4. StrategiesThe 200-day moving average strategy: rules, evidence, and a backtestDefine a moving-average allocation rule, specify signal and execution timing, and inspect its tradeoffs in a model run. An illustrative prompt helps you build and compare your own version.
  5. BacktestingHow to backtest a portfolio without writing codeResearch two assets, build an allocation model, inspect its saved results, and compare one change. A practical first workflow for DIY investors using ENSEMBLE.
  6. BacktestingBacktest metrics explained: CAGR, volatility, Sharpe ratio, and max drawdownRead ENSEMBLE backtest metrics with their actual conventions: CAGR, annualized volatility, a zero-risk-free Sharpe calculation, maximum drawdown and trading activity. Compare matched windows and inspect assumptions.
  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 agentsBuild and maintain investment models with an AI agentUse current ENSEMBLE tools to research assets, create a saved model, inspect a run, compare inputs and maintain reviewed allocations through explicit refreshes.
  9. AI agentsA finance MCP server for allocation models and researchUse ENSEMBLE's hosted MCP server to research available assets, build allocation models, inspect saved runs, and retrieve allocations. Understand connection requirements, data coverage, and metered execution before starting.
  10. AI agentsHow to research and backtest a model with ClaudeConnect a compatible Claude client to ENSEMBLE, verify asset coverage, build an allocation model, and inspect a parameter test. An illustrative workflow with current tool names and clear execution limits.
  11. Comparetestfol.io and ENSEMBLE: choosing a research workflowCompare testfol.io's portfolio research tools with ENSEMBLE's stored allocation models, custom Python, model composition, and connected workflows. Check current features and costs before choosing.
  12. For advisorsExport reviewed model allocations for your brokerage workflowInspect a model's run and target weights, select a supported Business export, and review the file before using it with Altruist or Interactive Brokers.