AI Crypto Backtest Research: Trace the Conclusion Back to the Tool Results
An AI backtest summary reports returns, win rates and drawdowns. Each figure should be traceable to a trade list and settings in the tool output.
Short answer
To verify an AI backtest, find the trade list in the tool output and recompute key figures: trade count, win rate, total return, max drawdown. Check settings: period, fees, slippage, fill model (next bar), and data source. If the summary's numbers can't be reproduced from the trade list, or settings aren't shown, the result isn't verified.
From claim to tool call
| Claim in the answer | Tool result that must support it | Check |
|---|---|---|
| 'Win rate 58%' | Trade list | Recompute |
| 'Return +31%' | Equity curve / list | Recompute |
| 'Fees included' | Settings | Values shown? |
| 'Next-bar fills' | Fill times vs signal times | Check |
Common mismatches
- Win rate not matching trade list
- Fees claimed but zero in settings
- Signal-bar fills
- Period different from stated
Worked trace
Illustrative: the summary said fees were included; the tool's settings showed 0%. Recomputed with realistic fees, the return fell to +12%.
Related: AI Crypto Backtest Research: How to Check Timestamps Before Trusting the Answer, AI Crypto Backtest Research: What the Assistant Should Say When Data Is Missing.
Run the backtest prompt in ChartsPod and open each tool call beside the answer.
Open the ChartsPod terminalIf the summary's numbers can't be reproduced from the trade list, or settings aren't shown, the result isn't verified.
Test AI Crypto Backtest Research on a perpetual chart; no account is needed to chart.
Launch ChartsPodQuestions readers ask
How do I check an AI backtest?
Recompute key figures from the trade list.
What settings matter?
Fees, slippage, fill model, period.
What if I can't reproduce?
Treat as unverified.
Sources and methodology
ChartsPod's AI agent (69 tools, visible tool calls, bring-your-own-key, no order placement) was checked on its public pages on 17 October 2026. Prompts are illustrative templates; outputs vary by model and data.
- ChartsPod: product overview, pricing and FAQ — free terminal, venues, modules, no order placement; checked 17 Oct 2026.
- ChartsPod documentation — guides for order flow, derivatives, alerts, backtests, journal and workspaces.
This article explains research tools and workflows. It is not financial advice, does not recommend buying or selling any asset and does not predict prices. Crypto derivatives carry a risk of rapid and total loss of margin.
CHARTSPOD EDITORIAL EDITION · RESEARCH AND EDUCATION ONLY · NOT FINANCIAL ADVICE.