Usage limit best practices

Ziva AI Agent leverages advanced AI models to assist you with your Godot development. To ensure fair usage and sustainability, we have implemented usage limits based on your subscription plan.

What are Usage Limits?

Usage limits control how much you can interact with Ziva AI Agent over a specific time period. Think of this as your “conversation budget” that determines how many messages you can send to the agent before needing to wait for your limit to reset.

Your usage is affected by several factors, including the length and complexity of your conversations, the size of the scripts the agent processes, and which AI model you’re chatting with. Different subscription plans have different usage allowances, with paid plans offering higher limits.

Rate Limits by Plan

Each plan has specific weekly and monthly usage limits measured in USD. These limits cover the cost of the AI models you use.

Reset Cycles

The reset cycle for your usage limits depends on your plan type:

• Hobby Plan: Usage limits reset at the start of each calendar month.
• Paid Plans (Basic, Pro, Ultra): Usage limits reset based on your billing start date. For example, if your subscription started on the 15th, your limits will reset on the 15th of each month.

Best Practices

To get the most out of your Ziva AI Agent subscription and stay within your limits, consider these best practices:

1. Plan Your Conversations

Before sending a request, think about what specific information or assistance you need. If you have multiple related questions, try to combine them into a single message. Providing necessary context upfront can reduce the need for back-and-forth clarifications.

2. Be Specific and Concise

Clear and detailed instructions help the AI understand your request immediately. Avoid vague queries that might require follow-up questions. Specific prompts often lead to better code generation and fewer corrections.

3. Batch Requests

If you have several small tasks, group them into one request. For example, instead of asking “Create a player script,” then “Add movement,” and then “Add jumping,” you can ask: “Create a player script with movement and jumping mechanics.”

4. Review Your Prompts

Take a moment to check your prompt for clarity and completeness before sending it. This helps avoid wasting usage on requests that need to be re-run due to typos or missing information.

5. Pick the Right Model

Choose the model that best fits your task complexity:

• Small, easy tasks: Use a lower-cost model to save on usage limits.
• Complex, critical tasks: Use a larger, more capable model to ensure high-quality results.

6. Keep Scripts Small

Try to keep your GDScript files small and focused. When the AI agent views or edits a script, it consumes tokens based on the file size. Breaking large scripts into smaller, modular components helps reduce token usage and context overhead.

7. Start Fresh Chats for New Topics

When you switch to a different topic or task, start a new chat session. Long chat histories carry over all previous context, which consumes more tokens with every new message. Starting fresh ensures the AI only processes relevant information and keeps your usage efficient.

By following these tips, you can maximize the value you get from Ziva AI Agent while managing your usage effectively.