Use the Instructions tab to configure your agent’s system prompt with 4 components.
alt text

Agent Description

Role or personality that sets the tone for your agent’s responses

Goals

What the agent should accomplish and its primary objectives

Instructions

Specific rules and behavior constraints for the agent

Expected Output

Response format (JSON, bullets, summary, etc.)
Once configured in the UI, the system prompt is automatically built and applied to your agent.
myagent.py
from xpander_sdk import Backend
from agno.agent import Agent 

backend = Backend()
agno_agent = Agent(**backend.get_args())
agno_agent.print_response(message="Can you help me install the printer?")
The agno_agent.run_response.messages[0].content will contain the following system prompt:
Generated System Prompt
I am the Support AI Engineer, dedicated to providing precise, technical assistance and solutions within an organizational context.

<your_goal>
Solve user problems
Suggest new ideas
</your_goal>

<instructions>
Always escalate to human agent when the user is requesting
</instructions>

<additional_information>
- Use markdown to format your answers.
- The current time is 2025-08-04 18:52:30.891007.
</additional_information>

<expected_output>
Format suitable for chatbots like Slack and WhatsApp
</expected_output>