ENSEMBLE

AI investment strategy builder for systematic backtesting

The asset allocation platform for the agentic era. Build any strategy, test it, and read exactly how it was built.

Start building
Universe
50,000+ assets
History
20 years, daily
Execution
Sandboxed, deterministic
To start
$100 credit, no card

How it works

Methodology →

Describe

State the strategy in plain language; ENSEMBLE writes the executable code.

Backtest

It runs sandboxed against daily history and returns the full tear sheet.

Run

It reruns nightly after the close. Pull current allocations by API or download them in your broker's format.

Every model runs sandboxed, re-runs deterministically, and exports the return series its metrics are computed from.

What you keep

Build anything.
Read exactly how it was built.

Every strategy is code you can open, a backtest you can check, and a result that stays current.

  1. 01

    Any strategy

    Describe it or write it. Assets, other models, or both. No presets.

  2. 02

    Nothing hidden

    The code, the data and every run are yours to read, question and take with you.

  3. 03

    Kept current

    Every strategy reruns after the close. Open it and today's allocation and metrics are waiting.

Web app, API, MCP, CLI

Web app

Describe, backtest, and read the tear sheet in the browser.

REST API

OpenAPI

Create, backtest, and re-run models from your own systems.

MCP server

Remote

Give Claude, Cursor, or any MCP client the platform as tools.

CLI

npx ensemble.markets

JSON to stdout for agents working in the shell.

Example strategies

Build your own →
Tear sheets-allweather
All-Weather Allocation
Since 2018· backtest
+6.6%
CAGR
0.92
Sharpe
−13.2%
Max DD
TLT +40.0%SPY +30.0%DBC +15.0%
Tear sheets-mag7rp
MAG7 Risk Parity
Since 2018· backtest
+12.5%
CAGR
0.78
Sharpe
−24.9%
Max DD
MSFT +18.0%AAPL +17.0%GOOGL +16.0%
Tear sheets-btcmstr
BTC / MSTR Basis
Since 2018· backtest
+15.5%
CAGR
1.43
Sharpe
−12.7%
Max DD
BTC-USD +50.0%MSTR −35.0%

Guides

All strategies →

Strategies

Plain-language explanations of the classic systematic strategies, each with its rules, its failure modes, a hypothetical backtest on ENSEMBLE, and the prompt that builds it.

Backtesting

How to backtest a portfolio without code, what the metrics on a tear sheet mean, and the mistakes that make a backtest lie to you.

AI agents

How Claude, Cursor, ChatGPT, and custom agents build and backtest systematic strategies through a finance MCP server or the REST API.

Compare

Factual comparisons of portfolio backtesting tools: what each one does well, where it stops, and when ENSEMBLE is or is not the better fit.

For advisors

Build, backtest, document, and keep model portfolios current from plain language, with white-label fact sheets and allocation files for Altruist and Interactive Brokers.

FAQ

Usage-based. You start with $100 in credit (valid 30 days), pay for the compute you use, and set your own spending cap. Rates are on the pricing page.

Start with $100 in credit. No card required.

Start building