Skip to main contentWhat does it do?
Profile nodes define the core identity and personality of your assistant. Think of the Profile as writing a job description for your digital employee - it establishes who they are, how they behave, and what they’re responsible for.
The Profile acts as the foundation that all other nodes reference. It sets the overall personality, expertise, and boundaries for your assistant.
How do I use it?
Setting Up Your Assistant’s Identity
Fill in these key fields to establish your assistant’s core identity:
Agent Name: Give your assistant a clear, recognizable name that reflects their purpose (e.g., “Customer Support Assistant”, “Sarah the Marketing Helper”)
Role: Define what job this assistant performs (e.g., “Customer Service Representative”, “Content Creator”, “Data Analyst”)
Agent Handle: Create a unique handle like @support, @marketing, or @sales that allows users and other assistants to mention and collaborate with this assistant. This handle enables multi-assistant workflows where assistants can reference each other’s expertise.
Collaboration Examples:
- A customer service assistant (@support) can escalate technical issues to a specialist (@tech)
- A content creator (@marketing) can request data insights from an analyst (@analytics)
- A sales assistant (@sales) can get product details from a product expert (@product)
Writing the Description
The description is where you define your assistant’s personality and approach to work. Be specific about:
- Their expertise and responsibilities
- How they should communicate (formal/casual, brief/detailed)
- Their approach to problem-solving
Example descriptions:
- “You are a friendly customer support specialist who helps solve technical issues with patience and clear explanations”
- “You are a data analyst who provides accurate insights and explains complex findings in simple terms”
- “You are a content creator who writes engaging marketing copy that matches our brand voice”
Setting Goals
Define what your assistant should accomplish:
Examples:
- “Resolve customer issues quickly and professionally”
- “Create engaging content that drives user engagement”
- “Provide accurate data analysis and actionable insights”
Setting Constraints
Define what your assistant should NOT do or important boundaries to follow:
Examples:
- “Never share confidential customer information”
- “Escalate billing issues over $500 to the finance team”
- “Always maintain a professional tone, even with frustrated customers”
- “Only provide information about our own products and services”
Knowledge Base Integration
Turn on “Embed Knowledge” to connect your assistant to a knowledge base containing relevant information like:
- Product documentation
- Company policies
- FAQs and best practices
Model Settings
AI Provider: Choose between OpenAI, Anthropic (Claude), or Google (Gemini)
Model: Select the specific model version based on your needs
Creativity Level: Adjust how creative vs. focused the responses should be:
- Focused: Precise and consistent responses
- Balanced: Good mix of creativity and reliability
- Creative: More varied and innovative responses
- Experimental: Highly creative but less predictable
Best Practices
Write Clear, Specific Descriptions
Be specific about what your assistant does and how they should behave. Avoid vague descriptions like “helpful assistant.”
Set Clear Boundaries
Use constraints to define what your assistant should never do or when they should escalate to humans.
Choose the Right Model
- Use more powerful models (GPT-4, Claude Sonnet) for complex reasoning tasks
- Use faster models for simple tasks
Test Your Configuration
Try different creativity levels and refine your description based on how your assistant performs in real conversations.