Assistants are AI-powered agents in Freddy that can be configured with specific behaviors, knowledge, and tools to help users accomplish tasks.
An assistant combines:
- AI Model: GPT-4, Claude, or other supported models
- Instructions: System prompts defining behavior
- Knowledge: Rules, documents, and context
- Tools: System tools, MCP integrations, and automations
- Configuration: Reasoning, output format, and context settings
- 🎯 Purpose-Built: Create specialized agents for different tasks
- 🧠Intelligent Reasoning: Configure chain-of-thought and multi-step planning
- 🔧 Tool Integration: System tools, MCP tools, and Streamline automations
- 📚 Knowledge Management: Attach rules, vector stores, and documents
- 🔒 Access Control: Organization and user-level permissions
Assistants use a normalized database structure with 7 related tables:
assistants- Main table with core assistant dataassistant_tool_configurations- Tools (system, MCP, Streamline)assistant_rules- Knowledge and guidelinesassistant_reasoning- Thinking configurationassistant_json_schemas- Structured output formatsassistant_vector_stores- Semantic search connectionsassistant_rule_attachments- File attachments
This design provides flexibility, data integrity, and efficient querying.
curl https://api.aitronos.com/v1/assistants \
-H "X-API-Key: $FREDDY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"name": "Support Agent",
"instructions": "You are a helpful customer support agent.",
"model": "gpt-4"
}'curl https://api.aitronos.com/v1/assistants/{assistant_id}/tools \
-H "X-API-Key: $FREDDY_API_KEY" \
-d '{
"system_tools": {
"file_search": {"enabled": true},
"web_search": {"enabled": true}
},
"mcp_tools": ["mcp_abc123"]
}'curl https://api.aitronos.com/v1/responses \
-H "X-API-Key: $FREDDY_API_KEY" \
-d '{
"assistant_id": "asst_abc123",
"thread_id": "thread_xyz789",
"messages": [{"role": "user", "content": "Hello!"}]
}'For comprehensive guides, see the dedicated assistants documentation:
- Assistants Overview - Complete introduction and use cases
- Database Schema - Detailed table structure and relationships
- Tool Configuration - System tools, MCP tools, and integrations
{
"name": "Support Agent",
"instructions": "You are a helpful customer support agent...",
"tools": {
"system_tools": ["file_search", "web_search"],
"mcp_tools": ["zendesk_integration"]
}
}{
"name": "Code Reviewer",
"instructions": "You are an expert code reviewer...",
"tools": {
"system_tools": ["code_interpreter"],
"mcp_tools": ["github_integration"]
},
"reasoning": {"enabled": true}
}{
"name": "Data Analyst",
"instructions": "You are a data analysis expert...",
"tools": {
"system_tools": ["code_interpreter"],
"mcp_tools": ["database_connector"]
}
}