Creating Agents

Agents are created and configured through a comprehensive interface that allows you to set up their behavior, capabilities, and integrations. This guide walks you through the agent creation process.

Required Information

• Name: Unique name for the agent (required)
• Description: Description of the agent's purpose (required)
• AI Provider: AI provider for the agent (required)
• Chat Model: Specific chat model to use (required)
• System Prompt: Instructions for the agent's behavior (required)

Agent Configuration Tabs

Agent creation consists of multiple configuration tabs:

1. Basic Information: Name, description, AI provider, and model
2. Vector Configuration: Configure vectors for RAG
3. AI Tools: Select tools the agent can use
4. Prompt Configuration: Configure system prompt and prompt library
5. Advanced Settings: Chat memory, chart rendering, database connection

Basic Information

Enter Agent Name

Provide a unique name for the agent.

Required: Yes

Field: Agent Name

Validation: Must be unique

Example: "Customer Support Agent", "Data Analyst Agent", "Report Generator"

Enter Description

Provide a description explaining the agent's purpose and capabilities.

Required: Yes

Field: Description

Example: "AI agent for answering customer questions and providing support"

Enter Display Description

Provide a user-friendly description displayed to users.

Required: No

Field: Display Description

Note: If not provided, the description is used as display description.

Select AI Provider

Choose the AI provider for the agent.

Required: Yes

Field: AI Provider

Available Providers:

• OpenAI: OpenAI models (GPT-4, GPT-3.5, etc.)
• Ollama: Local Ollama models
• VertexAI: Google Vertex AI models (Gemini, etc.)

How to select: Use the dropdown to select a provider. Available chat models will update based on your selection.

Select Chat Model

Choose the specific chat model to use.

Required: Yes

Field: Chat Model

How to select:

• After selecting a provider, choose from available chat models
• Different providers offer different models
• Model selection affects capabilities and performance

Note: Choose a model appropriate for your use case. More powerful models may have higher costs.

Vector Configuration

Configure vectors for RAG (Retrieval-Augmented Generation):

Select Vectors

Choose vector stores to use with the agent.

Required: No

Field: Vectors

How to select:

• Use multi-select dropdown to choose vectors
• Select multiple vectors for different context types
• Vectors provide context for agent responses

Configure Vector Parameters

For each selected vector, configure:

• Top K: Number of results to retrieve (default: 5)
• Similarity Threshold: Minimum similarity score (default: 0.2)
• Data Source Filters: Filter to specific Objects, Files, or Reports (optional)

Note: See Using Vectors with AI Agents for detailed vector configuration.

AI Tools Configuration

Select AI tools the agent can use:

Available Tools

Common tools include:

• Query Tools: Execute database queries on Objects
• Search Tools: Search Objects, workflows, and reports
• Report Tools: Generate and execute reports
• Additional Tools: Other specialized tools

Select Tools

Choose which tools the agent can use.

Required: No

Field: AI Tools

How to select:

• Use multi-select dropdown to choose tools
• Select multiple tools as needed
• Tool descriptions are shown to help selection

Note: Only select tools that are relevant to the agent's purpose. Too many tools may confuse the agent.

Prompt Configuration

System Prompt

Configure the system prompt that defines agent behavior:

Required: Yes

Field: System Prompt

How to configure:

• Manual Entry: Enter prompt directly in textarea
• Generate Prompt: Click "Generate Prompt" or "Improve Prompt" button
  • Requires: Agent name, description, provider, and model
  • Uses AI to generate or improve prompt based on configuration
  • Considers selected tools and vectors

Prompt Best Practices:

• Clear Instructions: Provide clear instructions on agent's role
• Capabilities: Describe what the agent can do
• Limitations: Specify any limitations
• Examples: Include examples of good responses
• Tool Usage: Explain how to use available tools

Prompt Library

Create prompt library entries for common tasks:

Required: No

Field: Prompt Library

How to add entries:

1. Click "Add Prompt" button
2. Fill in:
   • Icon: Select an icon for the prompt
   • Capability: What the prompt enables (e.g., "Generate revenue report")
   • Prompt: The suggested prompt text
   • Description: Description of the capability
3. Click "Save"

Use Cases:

• Common user queries
• Frequently performed tasks
• Example interactions
• Quick actions

Advanced Settings

Chat Memory

Enable or disable chat memory for the agent.

Field: Chat Memory Supported

Default: Enabled

When Enabled:

• Agent remembers conversation history
• Provides context-aware responses
• Maintains conversation context

When Disabled:

• Each query is independent
• No conversation history
• Useful for stateless interactions

Inline Chart Rendering

Enable inline chart rendering for responses.

Field: Inline Chart Rendering

Default: Disabled

When Enabled:

• Agent can render charts inline in responses
• Useful for data visualization agents
• Requires appropriate tools

Database Connection

Select a database connection for tools that need database access.

Field: Database Connection

Required: No

How to select:

• Use dropdown to select a database connection
• Only DB connections are shown
• Required for tools that query databases

Note: See Connections Introduction for creating database connections.

Creating from Templates

You can create agents from templates:

1. Navigate to Agents page
2. Click "Create from Template" (or similar)
3. Select a template agent
4. Template configuration is pre-filled
5. Modify as needed
6. Save the agent

Note: Templates provide starting points with common configurations.

Editing Agents

To edit an existing agent:

1. Navigate to the Agents page
2. Find the agent in the list
3. Click the "Edit" icon next to the agent
4. The agent builder opens with existing configuration
5. Modify settings as needed
6. Click "Save" to apply changes

Note: Changes take effect immediately. Test agents after making changes.

Best Practices

Agent Naming

• Descriptive Names: Use clear names that indicate purpose
• Consistent Naming: Use consistent naming conventions
• Include Context: Include context in names (e.g., "Customer Support Agent")

System Prompts

• Be Specific: Provide specific instructions
• Include Examples: Include examples of good behavior
• Tool Instructions: Explain how to use tools
• Update Regularly: Update prompts based on agent performance

Vector Configuration

• Relevant Vectors: Select vectors relevant to agent's purpose
• Appropriate Parameters: Set appropriate top-K and threshold
• Test Configuration: Test vector configuration with sample queries

Tool Selection

• Relevant Tools: Only select tools the agent needs
• Avoid Overload: Don't select too many tools
• Test Tools: Test that tools work correctly

Prompt Library

• Common Tasks: Add entries for common user tasks
• Clear Prompts: Use clear, actionable prompts
• Regular Updates: Update prompt library based on usage

Related Introduction

• Agents Introduction - Overview of agents
• Using Agents - Learn how to interact with agents
• Using Vectors with AI Agents - Detailed vector configuration
• Vectors Introduction - Understand vectors used with agents
• Connections Introduction - Learn about database connections