Build a strategy with AI-assisted formula writing
Build a strategy by defining a trading idea, supplying the supported calculator catalogue to your AI assistant, and reviewing separate BUY, SELL and STOPLOSS formulas. Test before relying on the rules, manage versions and sharing deliberately, and understand AI review eligibility and charges. The formulas below are educational examples, not a proven strategy or a promise of returns.
Build a strategy with AI-assisted formula writing — MP4 · SRT
Define a trading idea first
Start on the Strategies page with an understandable trading idea, a market and a risk budget. A strategy contains explicit BUY, SELL and STOPLOSS rules.
Treat the sample strategy and formulas as educational examples. They do not establish profitability or promise returns.
Name, describe and choose visibility
Give the strategy a meaningful name and explain what it is intended to do. Describe the trading idea and its limits rather than advertising guaranteed performance.
Choose Private for your own use, Limited for listed referrals or Public for community access.
Copy the indicator guide for your AI
Open Available calculators and click Copy indicators + AI guide. The button copies the calculator definitions and an AI-ready formula-writing guide.
You can filter the table by RSI. Verify that the copied material still contains the full catalogue and formula-writing guide, not just the filtered entries.
Give the copied material to your chosen AI assistant together with your market, timeframe, entry, exit and risk requirements. This helps avoid invented indicator names or unsupported operators.
Ask for formulas you can inspect
Ask your assistant to return separate BUY, SELL and STOPLOSS formulas using only the supported catalogue. Request a plain-language explanation and review the assumptions.
An example response is an illustration, not evidence that an AI produced a profitable trading system. Inspect each expression before using it.
Paste the BUY formula
Copy only the BUY expression into BUY strategy, in the strategy-buy field, without prose or code fences.
Example: CurrentPrice > 5m-EMA-20 AND 5m-RSI > 52 AND 5m-MACD-hist > 0
This example combines price above a short-term moving average with momentum confirmation. Review the exact thresholds and missing-data behavior before testing it.
Paste the ordinary SELL formula
Paste the ordinary exit rule into SELL strategy, in the strategy-sell field.
Example: ProfitSinceBuyPct >= 2 AND 5m-MACD-hist < 0
The example waits for a profit threshold and momentum deterioration. An ordinary SELL may have different eligibility conditions from protective STOPLOSS, so do not assume it covers every losing position.
Paste and understand STOPLOSS
Put the protective rule into StopLoss strategy, in the strategy-stop-loss field.
Example: ProfitSinceBuyPct <= -2.5
This example uses a negative 2.5 percent position threshold. It is a rule condition, not a guaranteed maximum fill loss. The Plan must also enable StopLoss for it to act. Execution timing, gaps and costs still matter.
Test before relying on a formula
Use the formula-test controls to check evaluation against the selected symbol, and review the result.
A valid expression or one successful evaluation does not prove profitability. Backtest and review behavior before risking capital, then use Save strategy deliberately.
Keep versions and sharing deliberate
The strategy list shows the strategy’s name, ID, version and usage. Check the version information and Plan usage count, and review which version a Plan follows before changing rules.
Use the edit and sharing controls deliberately. The sharing control can produce an invitation linked to a strategy, but public visibility alone does not prove quality.
Request evidence-based AI optimization
The strategy owner can request AI review once per strategy family per UTC day when Plan evidence is available. A new strategy with no usage evidence may not be eligible.
Open AI review to inspect the scope and cost before confirming a request. The educational example uses an owned strategy with three example Plans and sufficient demo credits; its review dialog is not submitted.
Understand the review charge and follow-up
The current review costs 100 credits after a successful AI analysis, even when the conclusion is to leave formulas unchanged. Queueing alone does not charge, and a transport failure or unavailable response is not charged.
Read the cost, timing and confirmation text before proceeding, or cancel without submitting. The request is processed asynchronously and the result arrives by email.
Review any adopted change against later evidence.