Create Your First Agent

This comprehensive tutorial will guide you through creating your first AI agent in PLai Framework. You’ll learn the fundamentals of agent creation, configuration, and testing.

What You’ll Build

In this tutorial, you’ll create a Customer Support Agent that can:

Answer Questions

Provide helpful responses to customer inquiries

Search Information

Look up real-time information using Perplexity AI

Process Requests

Handle various customer service tasks

Escalate Issues

Know when to escalate complex issues to humans

Prerequisites

Before you begin, ensure you have:

A PLai Framework account with Pro access (for Perplexity AI)
Access to a project (create one if needed)
Basic understanding of AI agents and customer service

Step 1: Create the Agent

Access Your Project

Log in to PLai Framework Dashboard
Select your organization and project
Navigate to the Agents section

Start Agent Creation

Click the Create Agent button (+ icon) in the top right

Configure Basic Information

Fill in the agent details:Name: Customer Support Agent Description: Helpful customer support agent that can answer questions and provide assistance

Set System Instructions

Copy and paste this system prompt:

You are a helpful and professional customer support agent. Your role is to:

1. Provide accurate and helpful information to customers
2. Maintain a friendly and professional tone
3. Search for current information when needed
4. Escalate complex issues to human agents when appropriate
5. Always prioritize customer satisfaction

Guidelines:
- Be concise but thorough in your responses
- Ask clarifying questions when needed
- Provide specific solutions and next steps
- If you can't help with something, explain why and suggest alternatives
- Always end conversations on a positive note

Step 2: Configure the Model

Select LLM Provider

Choose OpenAI as your provider (recommended for customer support)

Choose Model

Select GPT-4 Turbo for the best performance, or GPT-3.5 Turbo for cost efficiency

Adjust Parameters (Optional)

Temperature: 0.3 (more focused responses)
Max Tokens: 1000 (sufficient for most support responses)

Save Configuration

Click Save to store your model configuration

Step 3: Add Tools

Now let’s enhance your agent with the Perplexity AI tool for real-time information lookup.

Navigate to Tools

Go to the Tools section in your project

Create Perplexity AI Tool

Click Create Tool
Select Perplexity AI
Configure the tool:

Name: Web Search Tool Model: sonar-pro System Message: Search for current information to help answer customer questions. Focus on official sources and recent information. Search Domain Filter: Leave empty for general search

Test the Tool

Click Test and try a sample query like “latest iPhone features”

Add Tool to Agent

Return to your agent’s settings
Go to the Tools tab
Click Add Tool and select your “Web Search Tool”

Step 4: Configure Agent Settings

Set Agent Avatar (Optional)

Upload a professional avatar image or use the default

Enable Features

Turn on these recommended features:

File Upload: Allow customers to share screenshots or documents
Voice Input: Enable voice conversations (if supported)

Configure Guardrails

Set up basic safety measures:

Enable Content Filtering
Set Rate Limiting to 10 messages per minute
Enable Inappropriate Content Detection

Activate Agent

Toggle the agent status to Active

Step 5: Test Your Agent

Now let’s test your agent with realistic customer support scenarios.

Start a Test Chat

Click the Chat button on your agent to open the chat interface

Test Basic Interaction

Try this conversation starter:You: Hi, I need help with my accountYour agent should respond professionally and ask for more details.

Test Tool Integration

Ask a question that requires current information:You: What are the latest features in the iPhone 15?Your agent should use the Perplexity tool to search for current information.

Test Escalation

Present a complex scenario:You: I've been charged twice for the same order and need an immediate refundYour agent should recognize this needs human intervention.

Step 6: Refine and Optimize

Based on your testing, let’s optimize the agent’s performance.

Improve System Instructions
Adjust Tool Configuration
Add More Tools (Optional)

If responses aren’t quite right, refine your system prompt:

You are a helpful customer support agent for [Company Name]. 

Key responsibilities:
- Answer product questions using current information
- Help with account and billing issues
- Provide troubleshooting guidance
- Escalate complex issues to human agents

Response guidelines:
- Keep responses under 150 words when possible
- Use bullet points for step-by-step instructions
- Always include next steps or follow-up actions
- For billing issues, always escalate to human agents
- For technical issues, try to resolve first, then escalate if needed

Tone: Professional, helpful, and empathetic

Fine-tune your Perplexity tool:

Search for the most current and accurate information to help answer customer questions. 
Prioritize:
1. Official company documentation
2. Recent product announcements
3. Authoritative news sources
4. User guides and help articles

Provide concise, actionable information.

Common Test Scenarios

Here are realistic scenarios to test your agent:

Product Information Requests

Test Input: “What’s the difference between your Pro and Enterprise plans?”Expected Behavior:

Use web search tool to find current pricing information
Provide clear comparison
Offer to help with plan selection

Technical Support

Test Input: “I can’t log into my account, it says my password is incorrect”Expected Behavior:

Provide password reset instructions
Suggest checking for caps lock, typos
Offer alternative solutions
Escalate if issue persists

Billing Issues

Test Input: “I was charged $99 but I cancelled my subscription last month”Expected Behavior:

Acknowledge the concern empathetically
Explain it needs human review
Provide escalation path
Give reference number or next steps

Feature Questions

Test Input: “Does your platform support integration with Slack?”Expected Behavior:

Search for current integration information
Provide specific details about Slack integration
Explain setup process if available
Offer additional resources

Advanced Configuration Tips

Performance Optimization

Response Speed: Use GPT-3.5 Turbo for faster responses if speed is more important than complexity handling.

{
  "model_config": {
    "provider": "openai",
    "model": "gpt-3.5-turbo",
    "temperature": 0.2,
    "max_tokens": 500,
    "top_p": 0.9
  }
}

Cost Management

Monitor your agent’s usage:

Token Usage: Track input/output tokens per conversation
Tool Calls: Monitor Perplexity AI usage
Conversation Length: Set reasonable limits
Rate Limiting: Prevent abuse

Quality Assurance

Regular Testing

Test your agent weekly with new scenarios

User Feedback

Collect and analyze user feedback

Performance Metrics

Monitor response quality and resolution rates

Continuous Training

Update system prompts based on learnings

Troubleshooting Common Issues

Agent Not Responding

Possible Causes:

Agent is set to inactive
Model configuration errors
Network connectivity issues

Solutions:

Check agent status is “Active”
Verify model configuration
Test with simple queries first

Tool Not Working

Possible Causes:

Tool not properly configured
Authentication issues
Tool not added to agent

Solutions:

Test tool independently
Check tool configuration
Verify tool is assigned to agent

Poor Response Quality

Possible Causes:

Unclear system instructions
Wrong model selection
Inappropriate temperature setting

Solutions:

Refine system prompt with specific examples
Try different model (GPT-4 for complexity)
Adjust temperature (lower for more focused)

High Costs

Possible Causes:

Using expensive models unnecessarily
Long conversations without limits
Excessive tool usage

Solutions:

Use GPT-3.5 for simple tasks
Set conversation length limits
Monitor and optimize tool usage

Next Steps

Congratulations! You’ve created your first AI agent. Here’s what to do next:

Deploy to Production

Learn how to deploy your agent for real users

Add More Tools

Enhance your agent with additional capabilities

Monitor Performance

Set up analytics and monitoring

Advanced Configurations

Explore advanced agent features

Best Practices Summary

Production Readiness: Always test thoroughly before deploying agents to handle real customer interactions.

✅ Do’s:

Test with realistic scenarios
Set clear system instructions
Monitor performance regularly
Collect user feedback
Start simple and iterate

❌ Don’ts:

Deploy untested agents
Use overly complex prompts initially
Ignore cost monitoring
Forget to set guardrails
Skip regular updates

Getting Help

If you encounter issues:

Documentation

Review core concepts and features

Community

Join our Discord community

Support

Contact our support team

You’ve successfully created your first AI agent! This foundation will serve you well as you build more sophisticated agents and explore advanced features of PLai Framework.

Step-by-Step Guides

​Create Your First Agent

​What You’ll Build

Answer Questions

Search Information

Process Requests

Escalate Issues

​Prerequisites

​Step 1: Create the Agent

​Step 2: Configure the Model

​Step 3: Add Tools

​Step 4: Configure Agent Settings

​Step 5: Test Your Agent

​Step 6: Refine and Optimize

​Common Test Scenarios

​Advanced Configuration Tips

​Performance Optimization

​Cost Management

​Quality Assurance

Regular Testing

User Feedback

Performance Metrics

Continuous Training

​Troubleshooting Common Issues

​Next Steps

Deploy to Production

Add More Tools

Monitor Performance

Advanced Configurations

​Best Practices Summary

​Getting Help

Documentation

Community

Support

Create Your First Agent

What You’ll Build

Prerequisites

Step 1: Create the Agent

Step 2: Configure the Model

Step 3: Add Tools

Step 4: Configure Agent Settings

Step 5: Test Your Agent

Step 6: Refine and Optimize

Common Test Scenarios

Advanced Configuration Tips

Performance Optimization

Cost Management

Quality Assurance

Troubleshooting Common Issues

Next Steps

Best Practices Summary

Getting Help