Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.plaisolutions.com/llms.txt

Use this file to discover all available pages before exploring further.

​
Core Concepts

Understanding these core concepts will help you get the most out of PLai Framework and build effective AI agent systems.

​
Projects & Organizations

Organizations

Top-level containers that group users, projects, and billing

Projects

Workspaces containing agents, tools, and datasources

​
Organization Structure

Organizations provide:
  • Team Management: Invite and manage team members
  • Billing: Centralized billing and usage tracking IN PROGRESS
  • Access Control: Organization-level permissions IN PROGRESS

​
Projects

Projects are isolated workspaces where you:
  • Create and manage agents
  • Configure tools and datasources
  • Process batches
  • Monitor usage and performance

​
Agents

Agents are the core AI entities in PLai Framework. Each agent is a specialized AI assistant with its own configuration, tools, and capabilities.
  • Name & Description: Human-readable identification
  • Model Configuration: LLM provider and model selection
  • System Instructions: Base personality and behavior
  • Tools: Available capabilities and integrations
  • Datasources: Access to knowledge bases
  • Answer Filters & Guardrails: Safety and compliance controls

​
Tools

Tools extend agent capabilities by connecting them to external systems and services.

​
Tool Categories

  • API Requests: Connect to REST APIs
  • Web Search: Perplexity AI integration
  • Browser: Web scraping and automation
  • MCP Servers: Model Context Protocol integrations
  • External Datasources: Database connections

​
Tool Status Levels

  • Default: Production-ready, available to all users
  • Pro: Advanced features for premium users
  • Alpha: Early access, features may change

​
Datasources

Datasources provide agents with access to knowledge bases, documents, and structured data.

​
Supported Datasource Types

  • File Uploads: PDFs, text files, documents
  • Web Scraping: Extract data from websites
  • Database Connections: Google BigQuery databases
  • API Integrations: Real-time data from external services

​
Analytics & Monitoring

PLai Framework provides comprehensive analytics to help you understand and optimize agent performance.

​
Key Metrics

  • Conversation Volume: Number of interactions
  • Response Times: Agent performance metrics
  • Success Rates: Goal completion tracking
  • Cost Analysis: Usage-based billing insights
  • Error Rates: System reliability monitoring

​
Analytics Components

  • Progress Tracking: Real-time analysis status
  • Custom Filters: Filter data by various criteria
  • Report Generation: Automated reporting
  • Settings Panel: Configure analysis parameters

​
Batches

Batches enable processing large volumes of data or requests efficiently.

​
Batch Processing Flow

​
Batch Features

  • Bulk Processing: Handle thousands of requests
  • Status Tracking: Real-time progress monitoring
  • Error Handling: Automatic retry and error reporting
  • Result Export: Download processed data

​
Security & Compliance

​
Access Control

  • Role-Based Access Control (RBAC): Fine-grained permissions
  • Project-Level Permissions: Control access to resources
  • API Authentication: Secure API access with JWT tokens

​
Data Protection

  • Encryption: Data encrypted in transit and at rest
  • Audit Logs: Complete activity tracking
  • Data Retention: Configurable data lifecycle policies IN PROGRESS

​
Answer Filters & Guardrails

Answer Filters and Guardrails ensure agents operate safely and within defined boundaries:
  • Content Filtering: Prevent inappropriate responses
  • Rate Limiting: Control usage and costs
  • Safety Checks: Validate inputs and outputs
  • Compliance: Meet regulatory requirements

​
Model Context Protocol (MCP)

MCP enables agents to connect to external tools and services through a standardized protocol.

​
MCP Benefits

  • Standardization: Consistent interface for tools
  • Extensibility: Easy integration of new capabilities
  • Security: Secure communication between components
  • Scalability: Support for distributed architectures

​
MCP Server Types

  • Remote Servers: Cloud-based MCP implementations
  • Local Servers: Self-hosted MCP services
  • Hybrid: Mix of remote and local servers

​
Best Practices

Start Simple: Begin with basic agents and gradually add complexity as you learn the platform.
Monitor Performance: Use analytics to understand agent behavior and optimize performance.
Security First: Always implement appropriate guardrails and access controls for production deployments.
Cost Management: Monitor usage and set up billing alerts to manage costs effectively.

​
Next Steps

Now that you understand the core concepts, you’re ready to:

Create Your First Agent

Follow the quickstart guide

Explore Agent Features

Learn about agent capabilities

Configure Tools

Set up agent tools

View Tutorials

Step-by-step guides