For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to page URLs; this page is available as Markdown.

Step 1: Type Your Query

In the Atlas chat, type what you're looking for. For example:

"Show me the best SSA strategies for Bitcoin on the 1-hour timeframe"

Press Enter or click the send button.

Step 2: Answer Any Follow-Up Questions

If Atlas needs more detail, it will present you with multiple-choice options. For example, it might ask which direction you prefer — Long Only, Short Only, or Both.

Click an option to continue, or type your answer.

Step 3: Review Your Results

Atlas displays up to 5 matching strategies, each with:

• A metrics panel showing Net Profit, Trades, Win Rate, Max DD, Profit Factor, Sharpe ratio, and Overfit %
• An equity curve chart showing how the strategy performed over time
• The entry and exit conditions (which trigger and states were used)

Step 4: Keep Exploring

Continue the conversation to dig deeper:

• "Show me the same for ETH"
• "Any of these with a drawdown under 10%?"
• "Sort by win rate instead"
• "What does the Fair Value Trail filter do?"

Atlas remembers your conversation context (within each session), so you can refine naturally.

Atlas remembers your conversation context (within each session), so you can refine naturally.

Step 5: Save the Ones Worth Tracking

Found a strategy you want to keep? Click the star icon on its result card to save it to your Saved Strategies dashboard. Saved strategies are re-validated weekly against the refreshed database, so you'll know when one stops clearing the quality filters.

Agent Instructions

This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the ask query parameter:

GET https://algoalpha.gitbook.io/algoalpha-user-manual/atlas-ai-backtesting-agent/your-first-strategy-search.md?ask=<question>

The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.