Process context and prompt to generate tool actions and results
| Property | Details |
|---|---|
| Purpose | Process context and prompts to generate tool actions and results |
| Usage | Core building block for AI assistants and automated tool execution |
| Category | Intelligent Assist |
| Type | Agentic |
| Security | Safe AI processing with result validation |
| Parameter | Type | Description |
|---|---|---|
| Model | modelSettings |
AI model for processing and tool generation |
| Additional Context | textarea |
Extra context information for the agent |
| Prompt to Answer | textarea |
The main prompt or question to process |
| Describe Result | textarea |
Specifications for result format and style |
| Data | object |
Input data containing context and variables |
| Parameter | Type | Default | Description |
|---|---|---|---|
| Model Config | object |
- | Additional model configuration options |
{
tools: any[], // Array of generated tool actions to execute
result: {
response: string // Formatted AI response based on specifications
}
}
Provides both executable tools and formatted AI responses
The Generic Agent node provides comprehensive AI processing:
| Feature | Description |
|---|---|
| Model Selection | Choose appropriate AI models for different tasks |
| Context Integration | Incorporate additional context for better responses |
| Prompt Processing | Handle complex natural language prompts |
| Result Specification | Define exact output format and style requirements |
Choose the Generic Agent node when you need to:
| Aspect | Requirement | Impact |
|---|---|---|
| Model Selection | Choose based on task complexity | Affects processing quality and response accuracy |
| Context Quality | Provide relevant, clear context | Improves response relevance and accuracy |
| Prompt Clarity | Write clear, specific prompts | Determines tool generation and result quality |
| Result Specs | Define specific output requirements | Controls result format and meets user expectations |
| Factor | Description | Optimization |
|---|---|---|
| Token Usage | Tracks prompt and completion tokens | Monitor for cost optimization |
| Processing Time | Model inference time | Choose appropriate models for speed vs quality |
| Context Size | Amount of context data provided | Balance relevance with processing efficiency |
| Security Feature | Protection | Benefit |
|---|---|---|
| Input Validation | Validate all inputs | Prevent malicious input processing |
| Output Sanitization | Clean generated outputs | Ensure safe result consumption |
| Rate Limiting | Control processing speed | Prevent resource exhaustion |
Purpose: Generate insights from business data
Model: GPT-4 for complex analysis
Context: Business metrics and KPIs
Prompt: Analyze sales trends and provide recommendations
Result: Structured JSON with insights and recommendations
Purpose: Generate personalized email responses
Model: GPT-3.5-turbo for speed
Context: Customer data and interaction history
Prompt: Generate response to customer inquiry
Result: Professional email format with personalization
Purpose: Create marketing content from product data
Model: GPT-4 for creative content
Context: Product specifications and target audience
Prompt: Write product description for website
Result: SEO-optimized HTML content
Last updated: 2025-11-28 - revision 697b76812