> For the complete documentation index, see [llms.txt](https://algoalpha.gitbook.io/algoalpha-user-manual/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://algoalpha.gitbook.io/algoalpha-user-manual/atlas-ai-backtesting-agent/prompting-tips.md). # Prompting Tips #### Say the important details up front Atlas works best when your first message already names what matters for a strategy search: * **What you want** — e.g. strong Sharpe, high win rate, limited drawdown * **Instrument** — e.g. BTCUSDT, AAPL, SPY * **Timeframe** — 5m, 15m, or 1h * **Indicator** — **SSA**, **ILPAC**, or **MC** (Momentum Concepts) * **Direction** — long only, short only, or both Example: > "Show me top **SSA** **long** strategies on **BTCUSDT**, **1h**, sorted by **Sharpe**." > "Find the best **MC** **short** strategies on **ETHUSDT**, **15m**, with at least 50 trades." More patterns and partial-query examples are in Finding strategies and Your first strategy search. #### Narrow or widen after you see results If the first answer is too broad or not quite right, say what to change in plain language: * *"Same idea but on 15m."* * *"Prefer lower drawdown."* * *"Sort by win rate instead."* * *"Try ILPAC instead of SSA."* * *"Now try MC on the same setup."* Atlas keeps **conversation context** in a session, so short follow-ups usually work. #### Mix strategy search with explanations You can ask what a metric means, what a filter does, or how to read a chart in the same chat as your searches—see Reading strategy results for the vocabulary. If Atlas asks you to pick from **buttons** (multiple-choice), you can click an option or type your own answer; both are fine. See Chatting with Atlas. #### Keep asks realistic * Prefer **specific goals** ("Sharpe-focused, moderate drawdown") over vague superlatives ("the best strategy in the world"). * If something fails or looks empty, **rephrase** (different asset, timeframe, indicator, or sort) before assuming there are no strategies at all. #### Switching models * There are 2 available models for you, **Atlas Lite** (the default) and **Atlas** * If **Atlas Lite** fails to find your desired strategy, consider switching to **Atlas**, be aware that **Atlas** uses more credits * The app supports switching between different models between messages #### Tips to find reliable strategies * Tell Atlas to find strategies with more trades, at least 30-100 * Tell Atlas to not settle on immediate search results, and to dig deeper with more iterations to widen the search space * If a single indicator doesn't yield strong setups, **ask Atlas to try a different indicator** — for example, swap SSA for MC if you want pure momentum logic, or ILPAC if you want structure-based entries #### Choosing between SSA, ILPAC, and MC A quick guide on when to ask for each indicator family: * **SSA (Smart Signals Assistant)** — trend and reversal signal engine with ML regime detection. Good when you want a directional bias filter or trend confirmation built in. * **ILPAC (Institutional Liquidity & Price Action)** — market structure, swing pivots, liquidity sweeps, FOMO, trend-line breaks. Good for structure-based entries and liquidity-driven setups. * **MC (Momentum Concepts)** — Fast Oscillator (including divergence and reversal signals), Scalper's Momentum, Momentum Impulse, Hidden Liquidity Flow. Good for pure momentum and overbought/oversold logic. You can also mention "**any indicator**" if you want Atlas to search across SSA, ILPAC, and MC simultaneously. --- # 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/prompting-tips.md?ask= ``` 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.