Optimizer - PraisonAI

Agents can be optimized automatically - tune prompts and settings for better results.

Quick Start

Simple Usage

import { Agent, Optimizer } from 'praisonai';

const agent = new Agent({
  instructions: 'You answer questions'
});

const optimizer = new Optimizer({
  agent,
  examples: [
    { input: 'What is 2+2?', expected: '4' },
    { input: 'Capital of France?', expected: 'Paris' }
  ]
});

await optimizer.run();
// Agent instructions are now improved

With Configuration

const optimizer = new Optimizer({
  agent,
  examples: myExamples,
  evaluate: (output, expected) => {
    return output.toLowerCase() === expected.toLowerCase();
  }
});

User Interaction Flow

Configuration Levels

// Level 1: Array - Simple examples
const optimizer = new Optimizer({
  agent,
  examples: [
    { input: 'test', expected: 'result' }
  ]
});

// Level 2: Dict - With options
const optimizer = new Optimizer({
  agent,
  examples: myExamples,
  iterations: 5,
  targetScore: 0.9
});

// Level 3: Instance - Full control
const optimizer = new Optimizer({
  agent,
  examples: myExamples,
  iterations: 10,
  evaluate: customEvaluator,
  adjustments: ['instructions', 'temperature'],
  onIteration: (scores) => console.log(scores)
});

How It Works

Test: Run agent on examples
Score: Evaluate output quality
Adjust: Modify prompts/settings
Repeat: Continue until target score

API Reference

Eval Module

Evaluation and optimization

Best Practices

Use diverse examples

Cover different types of inputs the agent will see.

Set a target score

Stop optimization when good enough.

Review changes

Check what the optimizer changed before deploying.

Criteria

Success conditions

Reflection

Self-improvement

​Quick Start

​User Interaction Flow

​Configuration Levels

​How It Works

​API Reference