> For the complete documentation index, see [llms.txt](https://zkcross-network.gitbook.io/zkcrossnetwork/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://zkcross-network.gitbook.io/zkcrossnetwork/about-zkcross-network/superaccounts-your-gateway-to-defai/creating-and-launching-ai-agents.md).

# Creating & Launching AI Agents

### Why Build Your Own?

While pre-built AI Agents offer a hassle-free start, custom agents let you encode personal strategies, risk tolerance, or niche market insights—making your approach truly unique.

### **Key Features**

* **No-Code/Low-Code Configuration**: Create or adjust agents through a user-friendly interface, selecting triggers like price thresholds or social sentiment cues.
* **Advanced Settings for Pros**: For tech-savvy users, an in-depth editor could allow scripting complex strategies or linking external data feeds (e.g., Oracle services).

### Step-by-Step Walkthrough

1. **Define Objectives**
   * Trading, staking, arbitrage, NFT flipping—choose a main goal.
2. **Set Parameters**
   * Market pairs, price floors/ceilings, volume thresholds, or risk appetite.
3. **Deploy & Authorise**
   * Grant the agent permission to interact with your SuperAccounts wallet in a secure, permissioned environment.
4. **Monitor & Refine**
   * Use analytics dashboards to track performance and adjust parameters on the fly.

### Best Practices

* **Start Simple**: Stick to core rules like “buy dips” or “rebalance every 24 hours” before layering in complexity.
* **Regular Updates**: Markets evolve—review agent performance weekly or monthly, tweaking triggers as needed.
* **Risk Management**: Give agents a budget or max daily trade volume to cap potential losses.