Built for ideas, not overhead
Anyone can come up with a trading idea, but few test it correctly. PTQ runs the professional-grade stress tests your strategy has to survive.
Real app screenshots only. No mock-ups.
Complete professional testing
No shortcuts. Your strategy goes through a strict, step-by-step verification process until you hold something that has been through everything a professional would put it through.
Step 01
Write it down
Your strategy is written in plain English, defining exactly when to buy, sell, size, and exit. No coding required.
The system checks your rules instantly as you type so you never accidentally break your own risk limits.
Step 02
See the evidence
Test your strategy against real historical market data instead of relying on memory or guesswork.
If your rule has a flaw, the test fails immediately. An unverified or unrealistic test is worse than no test at all.
Step 03
Separate luck from edge
This step turns your spreadsheet idea into a rigorous, quantitative strategy by running three deep statistical checks for luck.
Most strategies fail here—even the ones you feel certain about. That is exactly how the system protects you.
Step 04
Watch it work
Strategies that pass run with fake money using real-time prices and hours. None of your money is involved.
You can observe its behaviour for weeks. Every order is clearly labelled as a simulation so you never confuse it with live trading.
Step 05
You decide when it is real
You control the final switch. The software runs locally on your computer using your broker keys, and nothing goes live without your manual approval.
Disclaimer: The live path is an experimental single-shot Alpaca order path, never tested against the live venue. Fully automated multi-broker execution and production safety are not yet available; we prefer to be upfront about this limitation now.
Why you can trust the verdict
Every test is based on published academic research. We always show the underlying data and working maths.
If you test enough rule versions, one will look brilliant by pure luck. This check calculates the exact odds that your strategy is just a fluke.
Probability of backtest overfitting
Bailey, Borwein, López de Prado & Zhu, Journal of Computational Finance 20(4), 2017.
Standard backtest scores look better than they should because they ignore failed past attempts. This metric adjusts your final score based on how many versions you tried.
Deflated Sharpe ratio
Bailey & López de Prado, Journal of Portfolio Management 40(5), 2014.
A true test requires data your strategy has never encountered. We hide a section of market history during development and score your rules entirely on that unseen data.
Out-of-sample holdout
Standard practice; the split is shown on every run.
It runs on your machine, not ours
You keep total control of your sensitive data. Our website processes the logic, but it never stores or touches your broker API keys.
Integrate Claude directly into the app to ask questions about your strategies in plain English. Your data and conversations stay entirely local.
Both halves are included in one simple plan. Your own computer is the only place live trading ever occurs.
Five things it will not do
- Not a signals service. PTQ never tells you what to trade.
- Not financial advice. It is software with no opinion on markets.
- Not a bot marketplace. You cannot buy or rent anyone else's strategy.
- Not a broker. Your trading funds always stay in your own brokerage account.
- Not a performance promise. We measure historical logic, never future returns.