Skip to main content
Agents can review and improve their own responses before returning.

​
Quick Start

1

Enable Reflection

import { Agent } from 'praisonai';

const agent = new Agent({
  instructions: 'You write professional content',
  reflection: true
});

await agent.chat('Write a business proposal');
// Agent writes, reviews, and improves before returning
2

Multiple Rounds

const agent = new Agent({
  reflection: {
    rounds: 2,  // Review twice
    prompt: 'Check for clarity and professionalism'
  }
});

​
User Interaction Flow

​
Configuration Levels

// Level 1: Bool - Enable with defaults
const agent = new Agent({
  reflection: true
});

// Level 2: Dict - With options
const agent = new Agent({
  reflection: {
    rounds: 2,
    prompt: 'Review for errors and clarity'
  }
});

// Level 3: Instance - Full control
const agent = new Agent({
  reflection: {
    rounds: 3,
    prompt: 'Focus on tone and accuracy',
    stopWhen: (output) => output.quality > 0.9
  }
});

​
How It Works

  1. Generate: Agent creates initial response
  2. Review: Agent critiques its own work
  3. Improve: Agent fixes identified issues
  4. Repeat: Process continues for specified rounds

​
API Reference

ReflectionConfig

Complete configuration options

​
Best Practices

More rounds don’t always mean better results.
Enable for proposals, articles, and important content.
Use reflection with criteria for validated quality.

Criteria

Define success conditions

Agent

Create agents