> ## Documentation Index > Fetch the complete documentation index at: https://docs.everstrike.xyz/llms.txt > Use this file to discover all available pages before exploring further. # AI Strategies: Automate Your Trading with Natural Language > Write plain-English prompts, configure markets and confidence thresholds, and let Everstrike's AI evaluate markets and execute trades automatically. Strategies are the core of Everstrike's vibetrading system. Each strategy uses a plain-English prompt to instruct an AI model on how to evaluate markets, when to enter or exit positions, and how to manage risk. Active strategies evaluate every selected market at your chosen frequency, produce a detailed [event](/ai/events) for every evaluation, and can submit orders automatically when the AI's confidence exceeds your minimum threshold. Start with one market and a low **Max Trade Quantity**. Review the events your strategy generates before increasing exposure, adding more markets, or raising the evaluation frequency. ## Strategy Configuration Every strategy you create has the following configurable properties: | Property | Description | | ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------- | | **Nickname** | Display name chosen when you create the strategy. | | **Markets** | Markets the strategy evaluates. Unselected markets are ignored. Each additional selected market increases credit use. | | **Max Trade Quantity** | Maximum USD value for each order. Start low, then increase as you validate the strategy's performance. | | **Timeframe** | Data horizon used for the strategy's decisions. | | **Evaluation Frequency** | How often the strategy evaluates each selected market. More frequent evaluations create more events and cost more credits. | | **Min. Confidence** | Confidence level required before the AI submits a `BUY`, `SELL`, or `CLOSE` order. | | **Prompt** | Instructions that define the strategy. Supports natural language up to 5,000 characters. English produces the best results. | | **Status** | `ACTIVE` strategies evaluate markets and may place trades. `PAUSED` strategies do neither and consume no credits. | | **Creation Time** | Time when you created the strategy. | | **Model** | AI model used for evaluations. See [Models](/ai/models) for available options and costs. | | **Temperature** | Temperature setting passed to the AI model during evaluation. | | **Discretion** | Whether the strategy allows the AI to apply discretion beyond the literal prompt. | | **Cost Savings Mode** | Reduces token consumption by up to 30%. Disabled by default. Reasoning output is minimal for events created in this mode. | | **Lookback Period** | Number of historical bars considered during each evaluation. Defaults to 5. Higher values increase token consumption. | | **Trigger Strategy** | Triggers another strategy instead of trading directly. Use this to chain strategies or build market screeners. Disabled by default. | | **Max Slippage** | Maximum slippage the strategy accepts when submitting orders. | ## Key Controls ### Prompt The prompt is the most important part of your strategy. It tells the AI what to evaluate and how to act. Prompts can reference any [supported data](/ai/supported-data) available to the AI. Write prompts that are specific about: * Which markets or market conditions to evaluate * Entry, exit, and position-management rules * When the strategy should hold rather than trade Prompts support plain English and allow up to **5,000 characters**. Being specific and unambiguous produces the most consistent results. ### Timeframe The timeframe sets the data horizon used during each evaluation. A shorter timeframe (such as `1m`) focuses the AI on recent price action, while a longer timeframe (such as `4h` or `24h`) gives it a broader view of market structure. Available timeframes: | Timeframe | Description | | --------- | ----------- | | `1m` | 1 minute | | `3m` | 3 minutes | | `5m` | 5 minutes | | `15m` | 15 minutes | | `30m` | 30 minutes | | `1h` | 1 hour | | `2h` | 2 hours | | `4h` | 4 hours | | `6h` | 6 hours | | `24h` | 1 day | Choose a timeframe that matches your intended trading horizon — a scalping strategy pairs naturally with `1m` or `5m`, while a swing strategy benefits from `4h` or `24h`. ### Min. Confidence The minimum confidence threshold controls how certain the AI must be before it submits an order. The default is **90%**. Lowering this threshold can generate more trades, but may also increase incorrect decisions. | Min. Confidence | Description | | --------------- | --------------------------------------------------------------------------- | | **95%** | Very conservative. Use when decisions require very high certainty. | | **90%** | Default. Suitable for most strategies. | | **85%** | Aggressive. The AI may trade more often and make more incorrect decisions. | | **80%** | Very aggressive. Use only when frequent trades justify a higher error rate. | ## Strategy Costs Strategies consume AI credits for every event they generate. The estimates below use **GPT-4.1-mini** (the default model) and apply per market. Adding more markets multiplies these costs proportionally. | Evaluation Frequency | Events per Market per Day | Est. Credits per Market per Hour | | -------------------- | ------------------------- | -------------------------------- | | 1s | 86,400 | \$0.54 | | 5s | 17,280 | \$0.108 | | 15s | 5,760 | \$0.036 | | 30s | 2,880 | \$0.018 | | 1m | 1,440 | \$0.009 | | 3m | 480 | \$0.003 | | 5m | 288 | \$0.0018 | | 15m | 96 | \$0.0006 | | 30m | 48 | \$0.0003 | | 1h | 24 | \$0.00015 | Pausing a strategy immediately stops event generation, trading, and credit consumption. You can resume a paused strategy at any time. ## Limits Everstrike enforces the following limits per account: * **Maximum strategies:** 10 * **Maximum markets per strategy:** 10 * **Maximum total market-strategy pairs:** 100 (10 strategies × 10 markets each)