Intelligence (AI Models)
Overview
The intelligence of an agent is determined by the underlying AI model. The chosen model significantly influences how the agent understands requests, generates responses, and handles complex tasks.
Selecting an AI Model
When creating or configuring an agent, you can choose from various AI models. Each model has different characteristics:
- Performance: High-quality models understand more complex contexts and deliver more precise answers
- Speed: Smaller models respond faster but are better suited for simpler tasks
- Cost: More powerful models incur higher usage costs
Impact on Agent Behavior
The chosen AI model determines:
- Understanding: How well the agent interprets complex requests
- Response Quality: Precision, depth of detail, and relevance of generated answers
- Multilinguality: Ability to understand and use multiple languages
- Creativity: How flexibly the agent responds to unusual requests
Best Practices
Model Selection
Choose the model based on the intended use:
- Simple FAQ bots: Smaller, faster models
- Complex advisory agents: High-quality, powerful models
- Specialized applications: Models with specific capabilities (e.g., code generation)
Model Changes
Changing the AI model can alter your agent's behavior. Test changes before production deployment.
Related Topics
- AI Models Overview - Detailed information about available models
- Instructions (Prompt) - How to control agent behavior through instructions
- Advanced Settings - Additional configuration options