For the complete documentation index, see llms.txt. This page is also available as Markdown.

Create a trading bot

Overview

A trading bot is an agent that follows defined rules to open and close positions, with no human intervention. Unlike a one-off trade, it runs continuously on the assets and timeframe you choose.

A bot is the ideal tool to automate:

  • A systematic strategy based on technical indicators.

  • A progressive investment plan (DCA, rebalancing).

  • Complex entry and exit rules combining multiple conditions.

How to phrase your request

Describe your strategy as if you were teaching it to someone: which assets, when to enter, when to exit, how to manage risk.

To go deeper on rule writing, see Description in natural language, Entry rules and Exit rules.

Example requests

Example #1 — Recurring DCA bot with filter

"DCA $200 into Bitcoin every Friday, and skip the buy if the RSI is above 70 on the daily."

Example #2 — Mean reversion

"Buy $1,000 of SPY whenever it closes more than 2% below its 20-day moving average, sell when it returns to the average."

Example #3 — News-driven bot

"Buy $500 of TSLA whenever Tesla unveils a new model, and sell after 5 trading days."

For more examples (short-term trading, long-term investing, multi-asset), see Example requests.


What's next?

Once the bot is created, it becomes an agent that you can:

  • Backtest on up to 20 years of historical data to evaluate past performance.

  • Run in demo mode (paper trading) to see how it behaves in real time without risk.

  • Run in live mode on a supported broker (depending on your region).

See Backtest an agent and Run an agent.

Mis à jour