Skip to main content

​
Agents Overview

Agents are the core AI entities in PLai Framework. Each agent is a specialized AI assistant that can chat with users, use tools, access datasources, and execute complex workflows.
Agents Dashboard

​
What are Agents?

Agents in PLai Framework are intelligent AI assistants that can:

Chat & Interact

Engage in natural language conversations with users

Use Tools

Execute actions through connected tools and APIs

Access Data

Query datasources and knowledge bases

Process Requests

Handle batch operations and complex workflows

​
Agent Features

​
Core Capabilities

Every agent in PLai Framework includes:
  • Natural Language Processing: Powered by advanced LLMs
  • Tool Integration: Connect to 6+ different tool types
  • Memory & Context: Maintain conversation history and context
  • Customizable Personality: Define behavior through system instructions
  • Multi-Modal Support: Handle text, images, and other media types

​
Advanced Features

  • Real-time conversation analytics
  • Performance metrics and insights
  • Custom reporting and filtering
  • Progress tracking for batch operations

​
Agent Configuration

​
Basic Settings

Each agent has fundamental configuration options:
  • Name: Human-readable agent identifier
  • Description: Purpose and capabilities summary
  • System Instructions: Core personality and behavior guidelines
  • Avatar: Visual representation for chat interfaces
  • LLM Provider: OpenAI, Anthropic, Together AI, Azure, etc.
  • Model Selection: GPT-4, Claude, Llama, and other models
  • Temperature: Response creativity and randomness
  • Max Tokens: Response length limitations
  • RouteLL: Smart model routing for cost optimization
  • Tools: Available actions and integrations
  • Datasources: Knowledge bases and data access
  • File Upload: Document processing capabilities
  • Voice Input: Audio conversation support

​
Agent Status & Management

​
Agent States

Active

Agent is running and can handle requests

Inactive

Agent is paused and won’t respond to requests

Processing

Agent is busy processing batch operations

​
Management Operations

Common agent management tasks:
  • Create: Set up new agents with configuration
  • Update: Modify settings, tools, and behavior
  • Clone: Duplicate agents for testing or variants
  • Share: Generate public or private sharing links
  • Delete: Remove agents and associated data
  • Export: Backup agent configurations

​
Agent Types & Use Cases

​
Customer Support Agents

Purpose: Handle customer inquiries and support tickets
Tools: 
  - Knowledge Base Search
  - Ticket System API
  - Email Integration
Features:
  - Escalation to human agents
  - Sentiment analysis
  - Multi-language support

​
Data Analysis Agents

Purpose: Process and analyze data from various sources
Tools:
  - Database Connections
  - Code Interpreter
  - Visualization Tools
Features:
  - Automated reporting
  - Data insights generation
  - Chart and graph creation

​
Content Creation Agents

Purpose: Generate and edit content across formats
Tools:
  - Web Search (Perplexity AI)
  - Document Processing
  - Image Generation
Features:
  - Multi-format output
  - Fact-checking
  - Style consistency

​
Research Agents

Purpose: Gather and synthesize information from multiple sources
Tools:
  - Web Scraping
  - Academic Databases
  - Document Analysis
Features:
  - Source verification
  - Citation management
  - Summary generation

​
Model Providers & Selection

PLai Framework supports multiple LLM providers:
  • GPT-4 Turbo: Latest and most capable model
  • GPT-4: Balanced performance and cost
  • GPT-3.5 Turbo: Fast and cost-effective
  • Usage: Excellent for general chat and reasoning

​
RouteLL Integration

RouteLL automatically routes requests to the most appropriate model based on complexity and cost:

​
RouteLL Benefits

  • Cost Optimization: Use cheaper models for simple tasks
  • Performance: Route complex queries to advanced models
  • Automatic: No manual configuration required
  • Transparent: Full visibility into routing decisions

​
Getting Started

Ready to create your first agent?
1

Navigate to Agents

Go to the Agents section in your project dashboard
2

Click Create Agent

Use the ”+” button or “Create Agent” button
3

Configure Basic Settings

Set name, description, and system instructions
4

Select Model

Choose your preferred LLM provider and model
5

Add Tools (Optional)

Connect tools to extend agent capabilities
6

Test & Deploy

Test your agent in chat and activate when ready

​
Next Steps

Create Your First Agent

Step-by-step agent creation guide

Agent Settings

Configure advanced agent features

Analytics

Monitor and analyze agent performance

First Agent Tutorial

Complete walkthrough with examples

​
Common Questions

The number of agents depends on your subscription plan. Free plans typically allow 3 agents, while premium plans offer unlimited agents.
Currently, agents operate independently. Multi-agent workflows are on our roadmap for future releases.
Conversation history is stored securely and can be accessed through the analytics dashboard. Data retention policies vary by plan.
Yes, agent configurations can be exported as JSON files for backup or migration purposes.