Agent Configuration
Create and configure agents within workgroups with LLM settings, tools, and integrations.
Workgroups can be created with Manual Setup or Create with AI; both end in the same configuration screens for agents after the workgroup exists.
Create Workgroup
A workgroup is the container that holds your agents.
- Navigate to the Main Dashboard and click Create Workgroup
- Enter Workgroup Name and Description
- Choose architecture:
- Single-Agent: Standalone agent for focused tasks
- Multi-Agent: Multiple agents working collaboratively (requires a supervisor agent)
- Click Create
Note: Workgroup architecture cannot be changed after creation. To switch types, create a new workgroup and migrate your agent configurations.
Agent Configuration
1. Agent Information
- Agent Name (required): Unique identifier. No special characters-use letters, numbers, spaces, and underscores only.
- Agent Description (required): Purpose and responsibilities of the agent.
2. LLM Configuration
Provider Selection: Anthropic, OpenAI, Azure OpenAI, Google Vertex AI, Together AI
Model Selection: Choose from available models or select Dynamic Model to specify via {{variable_name}} format.
Dynamic Variables: Use {{variable_name}} format for runtime values:
{{api_key}}- API key{{model_name}}- Model name (required for Dynamic Model){{llmConfig}}- JSON object with LLM parameters
Advanced Settings (click gear icon):
| Setting | Description |
|---|---|
| Temperature | Response randomness (0+) |
| Top-P | Nucleus sampling (0-1) |
| Reasoning Effort | Model reasoning effort (0-1) |
| Verbosity | Response verbosity (0-1) |
| Reasoning Summary | Summary level (0-1) |
Leave blank to use model defaults.
Provider-Specific Fields:
- Google Vertex AI: Service Account Info (
{{service_account_credentials}}), Project, Location - Azure OpenAI: Azure Endpoint, API Version, Azure Deployment
3. LLM Guards
Security mechanisms for input/output validation:
| Guard | Purpose |
|---|---|
| Ban Substrings | Block specific text patterns |
| Toxicity | Detect harmful content |
| Prompt Injection | Detect malicious prompts |
| Invisible Text | Detect hidden characters |
| Task Completion | Verify task completion |
Guards can be configured as Input Scanner or Output Scanner.
4. Agent Instructions
- System Prompt (required): Instructions defining agent behavior. Supports dynamic variables with
{{variable_name}}format. - Is Supervisor Agent: Enable for multi-agent hierarchy coordination.
- Max Iterations: Limit execution cycles (default: 10).
- Output Type: Text or JSON.
5. Tools
Add tools for the agent to perform tasks. Select from available enterprise integrations.
See Tools Overview for the full list of 50+ available tools.
6. MCP Clients (Pro)
Add MCP clients to extend agent capabilities with custom integrations.
- Click Add MCP Client
- Select from configured MCP clients
- Choose which tools to include/exclude
See MCP Clients for setup and configuration.
7. RAG Knowledge Base (Pro)
Connect knowledge bases for retrieval-augmented generation.
- Select RAG Knowledge Base from dropdown
- Configure: description, retrieval type, threshold, chunk count
See Knowledge Base for managing document collections.
Best Practices
- Agent Names: Use descriptive names reflecting the agent's role
- System Prompts: Be specific, include examples, define expected output format
- Guards: Add appropriate input/output validation
- Iterations: Set reasonable limits to prevent infinite loops