Simulate the next chapter
Paper trading uses a separate run on incoming market data. Orders and fills are simulated; they are not evidence of identical live execution.
Paper trading
Observe the strategy beyond the backtest.
Monitor strategies built by the AI factory after they pass admission checks. The paper engine runs them on incoming market data with simulated orders, positions and performance records.
See the strategy factory in motion.
Illustrative example · not a live result
Watch AI agents build and review a strategy.
AI agents develop the idea, write code and assess the test results. Review findings can send the strategy back for another iteration.
Watch the path, not just the endpoint.
An illustrative equity curve reveals setbacks along the way. Inspect drawdown and trading costs before interpreting a result.
Keep open positions in the picture.
Compare account equity with closed-trade balance. An open position can change equity before a trade closes.
- Describe
- Build & verify
- Backtest
- Stress-test
- Paper-trade
EquityClosed-trade balanceDrawdown
Net return—
Max drawdown—
Checkpoint—
Monitor positions and outcomes
Review paper positions, trades and equity over time. Compare behavior with the research assumptions rather than judging a strategy from one short window.
Keep release and execution separate
Starting research or buying a plan does not enable real-money trading. Live execution is a separate restricted path requiring explicit authorization and additional controls.
Build, observe and reassess.
Live market conditions can expose behavior that historical tests miss. Paper records help you review that behavior while keeping simulated execution clearly separate from real capital.
Admission
Approved strategy and paper slot
Observation
Positions, trades, equity
Reassessment
Review, continue or retire
Follow what happens after a signal.
Paper trading combines incoming market data with simulated execution. The resulting record lets you compare actual strategy behavior with the research assumptions.
Incoming market data
New prices reach the strategy.
Strategy decision
The implemented rules decide whether to act.
Simulated execution
The paper engine models orders and fills.
Recorded outcome
Positions, trades and equity support review.
The diagram describes the paper path. Available feeds and execution models vary by venue; simulated fills are not exchange confirmations.
Observe behavior, not just the latest P&L.
Use the paper record to investigate whether the strategy is acting as designed. A quiet period can be informative when the entry conditions have not occurred.
Scroll horizontally to see all columns.
| Review | Compare with the research | Investigate |
|---|---|---|
| Positions | Direction, size and intended holding period. | Unexpected exposure or positions held beyond the intended exit. |
| Trades & fees | Expected activity and modeled trading costs. | Overtrading, missing expected trades or cost-sensitive results. |
| Equity & drawdown | The historical range of losses and recovery periods. | A change in loss pattern or prolonged deterioration. |
| Observation window | The number of trades and market conditions seen. | Conclusions based on a few trades or only one market regime. |
Pause or stop paper work when you need to investigate. A pause is a control on the run, not proof that existing simulated positions were closed; inspect the position record.
Interactive illustration
Follow equity between closed trades.
Open positions can change equity before a trade closes. Inspect the same checkpoint across equity and drawdown to see the path behind the final result.
Read both the level and the path
A rising closed-trade balance can still coincide with falling equity. Review open exposure and drawdown alongside completed trades; a short paper record cannot establish future performance.
Total equityClosed-trade balance
Account value index · starts at 100
Drawdown from running peak
- Total equity
- Open P&L (index points)
- Drawdown from running peak
Questions, answered.
More questions and answersHow do you compare paper trading with a backtest replay?
The Paper Trading workspace shows available decision-parity measurements: matched decisions, quantity differences, entry and exit timing, and trades seen only in paper or replay. A comparison helps identify implementation differences; a match does not establish profitability or guarantee live fills.
Does every research market support paper trading?
No. Research coverage, live data browsing and paper execution are different capabilities. Availability depends on the venue and enabled execution path.
Is paper trading the same as live trading?
No. Real orders can face different liquidity, latency, fills and operational constraints. Paper performance is hypothetical.
What must happen before a strategy enters paper trading?
The run must pass the applicable reviews and admission checks, have a matching release record and fit within the available paper capacity. The venue and execution path must also be supported. A research result or a purchased plan alone does not admit a strategy.
Why might a paper strategy show no trades?
Its entry conditions may not have occurred, it may still need enough incoming data, or it may be paused or waiting on an operational condition. Check the run status, data availability and expected trading frequency before assuming that no trades means the strategy is broken.
What should I monitor once paper trading starts?
Review positions, trade frequency, fees, equity and drawdowns against the research assumptions. Check whether positions exit as intended and whether enough trades and market conditions have been observed. One short profitable window is not sufficient evidence of consistent behavior.
Does pausing a run close its paper positions?
Do not assume so. Pause and stop controls change whether the run is eligible to continue executing; they are not a promise that every existing simulated position has been closed. Inspect the position and trade records when reviewing the outcome.
Start with a question worth testing.
Explore published strategies, or open a workspace to build, test and monitor your own with AI agents.
Stratmill is an AI trading strategy platform, not financial advice or a broker. Backtest and paper results are hypothetical. Trading involves risk of loss.