Statistical proof for your trading strategies, in minutes rather than months.

Join the private betaSee how it works →
BTCUSDT.P · −2.20%ETHUSDT.P · −2.53%SOLUSDT.P · −3.83%XRPUSDT.P · −2.56%DOGEUSDT.P · −2.03%BTCUSDT.P · −2.20%ETHUSDT.P · −2.53%SOLUSDT.P · −3.83%XRPUSDT.P · −2.56%DOGEUSDT.P · −2.03%BTCUSDT.P · −2.20%ETHUSDT.P · −2.53%SOLUSDT.P · −3.83%XRPUSDT.P · −2.56%DOGEUSDT.P · −2.03%BTCUSDT.P · −2.20%ETHUSDT.P · −2.53%SOLUSDT.P · −3.83%XRPUSDT.P · −2.56%DOGEUSDT.P · −2.03%BTCUSDT.P · −2.20%ETHUSDT.P · −2.53%SOLUSDT.P · −3.83%XRPUSDT.P · −2.56%DOGEUSDT.P · −2.03%BTCUSDT.P · −2.20%ETHUSDT.P · −2.53%SOLUSDT.P · −3.83%XRPUSDT.P · −2.56%DOGEUSDT.P · −2.03%
Describe a strategy or refine the current one…↑

Tell us the idea the way you'd explain it to a friend, and we'll tell you honestly how it would have done.

BTC mean reversion · v3
BTCUSDT.P · 15m · net of fees
Complete
Net return
+18.4%
Sharpe
1.08
Max drawdown
−8.3%
Trades
1,284
4,718,788,287

Trades indexed

That is six years of Bybit perpetuals: every trade and every one-minute candle. Every fill you see was priced against it.

When a backtest looks good, watch it trade the live market in paper mode, with none of your money on the line.

Same engine, same fills, in real time. It runs on our side, so you can close the tab and come back to find it still going, with every fill, position and P&L shown as it happens. Pause it, resume it or flatten everything whenever you like.

Paper · BTC mean reversion v3
BTCUSDT.P · 15m · paper
Live09:40:00 UTC
Long · 0.5 BTC @ 64,357.664,240.7−0.18%
  • 09:35:50Filled · long 0.5 @ 64,357.6
  • 09:26:40Exit @ 64,251.1−0.15%
  • 09:18:45Filled · short 0.5 @ 64,154.4

Give the Lab one saved strategy and it searches, diagnoses, rewrites and stress-tests it, then hands you back a new one with the receipts.

Better variation, same idea
Start paper trading

Most backtesters sell hope. We would rather tell you the truth, so we replay the real order book, test on data the strategy has never seen, and publish what fails.

A backtest is only as honest as the checks around it, so we built more of them than anyone else.

Forward-walk windows, Monte-Carlo reshuffles, four cost models and full parameter sweeps, all on the same six years of data. Forward-walk tests on data the strategy has never seen, Monte-Carlo shows you the drawdowns you could have had, and fees, funding and slippage are priced into every single fill. If a strategy makes it through, it has been properly tested.

Here is what people usually try instead, and what each one leaves out.

AlphaProve
  • L2 order-book fills
  • Forward-walk validation
  • Monte-Carlo risk simulation
  • Describe a strategy in plain English
  • Paper trading on hosted servers
  • Priced for one person, not a desk
Chart-tool tester
  • L2 order-book fills—
  • Forward-walk validation—
  • Monte-Carlo risk simulation—
  • Describe a strategy in plain English—
  • Paper trading on hosted servers
  • Priced for one person, not a desk
DIY notebook
  • L2 order-book fills—
  • Forward-walk validationBy hand
  • Monte-Carlo risk simulationBy hand
  • Describe a strategy in plain English—
  • Paper trading on hosted servers—
  • Priced for one person, not a desk
Institutional platform
  • L2 order-book fills
  • Forward-walk validation
  • Monte-Carlo risk simulation
  • Describe a strategy in plain English—
  • Paper trading on hosted servers
  • Priced for one person, not a desk—

Start free. Pay only when you have an edge worth proving.

Trader
$29/ mo
Get started
  • ·300 AI credits / month
  • ·2-year data lookback
  • ·Code editor
  • ·Forward-walk optimization
  • ·Monte-Carlo risk sim
  • ·Up to 50× leverage
  • ·Priority backtest queue

NowLive today
  • AI strategy assist: describe an edge, get a strategy
  • L2 orderbook fills with depth-based slippage
  • Bybit margin, funding & liquidation modelling
  • Library, version history & full tearsheets
  • Forward-walk validation + Meta-ML
  • Sandboxed strategy execution running fully on our end
  • Hosted paper trading, nothing to install

Are backtests predictive?

Honestly, no. A backtest tells you how a strategy would have behaved in the past; nobody can tell you what it will do next week. What we can do is catch the ways a backtest fools you: pretend fills, curve-fitting, one lucky stretch of history. That way, when you decide to trade something, you're deciding on evidence rather than hope.

Where does the data come from?

Straight from Bybit. We keep six years of one-minute candles and order-book snapshots, and every fill in your backtest is priced against that book rather than a closing price.

What markets are supported?

Five Bybit USDT perpetuals for now: BTC, ETH, SOL, XRP and DOGE, on any timeframe from one minute up to a day. Paper trading covers the same five.

Do I need to know how to code?

Not at all. Tell the strategist what you have in mind and it drafts the rules for you, or click them together in the no-code editor. And if you do like writing rules yourself, the code editor is there whenever you want it.

Is this beginner-friendly?

Yes. You can go from an idea in plain English to a finished backtest without touching code, every number in the results is explained, and paper trading lets you watch a strategy run on live data before any real money is involved. The deeper tools, like forward-walk, Monte-Carlo and the code editor, wait until you want them.

Which plan should I choose?

Start on Free and see whether your idea has anything in it: 90 days of data, real order-book fills, full tearsheets. Trader is the plan for people who actually trade: two years of data, forward-walk validation, Monte-Carlo risk and the code editor. Quant is for when you want the whole history and the front of the queue. Move up when a backtest earns it, not before.

What are AI credits?

Think of a credit as one turn with the strategist: a draft, a revision, a fix. Bigger jobs, like an optimizer campaign or a Pine export, use a few more from the same monthly pool. Free includes 20 a month, Trader 300, Quant 1,500, and backtests themselves never cost credits.

Where does my strategy run?

In an isolated sandbox on our side. Nothing runs in your browser, and your strategies stay private to your account.

Is my data safe?

Yes. Your account and your strategies are stored in the European Union, we never sell your data, and we follow the GDPR, so you can ask for a copy of your data or have it deleted at any time. The one thing we hand to an AI model provider is the content of your chats with the strategist, which it needs in order to draft your rules. The full details are in our privacy policy.

What does the private beta include?

Everything, while we let people in a batch at a time. Put your name on the list and we'll email you the moment a spot opens up.

Prove it before you trade it.

Bring the idea. We will show you exactly how it would have done, with nothing hidden.

Join the private beta