Agent Details
The Agent Details section is where you define the core configuration of your AI Agent.
This is the first step in creating an agent and determines:
Which AI model powers the agent
How the agent behaves
What its purpose and identity are
Without completing this step, the agent cannot function.
Overview
Agent Details consists of two main parts:
Model Configuration — defines the AI provider and model
Agent Configuration — defines the agent’s identity and behavior
Model Configuration
This section defines which AI model your agent will use.
Provider
Select the AI provider:
Azure OpenAI
OpenAI
Credential
Choose a credential to authenticate with the selected provider.
Credentials store:
API keys
Endpoint configurations
Access settings
The agent will use this credential to communicate with the AI provider.
Model
Select the model to power your agent.
Examples:
GPT-based models
Provider-specific deployments (for Azure OpenAI)
The selected model directly impacts response quality, speed, and cost.
Agent Configuration
This section defines how your AI Agent behaves.
Agent Name
Provide a unique name for your agent.
This name is used to identify the agent across the platform.
Instructions (Role Prompt)
Define the behavior and role of the AI Agent.
You have two options:
Use Ready-Made Instructions
Select from predefined templates to quickly configure common agent types.
Create Custom Instructions
Write your own instructions to fully control:
Agent personality
Scope of knowledge
Allowed actions
Response style
Instructions are the brain of the agent. They determine how the agent interprets and responds to user input.
Save Configuration
After completing both sections, click Save at the top of the page.
This finalizes the initial setup of your AI Agent.
What’s Next
Once the Agent Details are configured, you can continue building your agent by:
Adding Knowledge (for context and RAG)
Defining Skills (for actions and integrations)
Connecting Channels (WhatsApp, Teams, Webhook, Mate Chat.)
Summary
Agent Details is the foundation layer of your AI Agent.
Model → defines intelligence
Instructions → define behavior
Everything else (skills, channels, knowledge) builds on top of this.
Last updated
Was this helpful?