Skip to main content
Reflection enables agents to critically evaluate their outputs and iteratively improve them before delivering the final response.

​
Quick Start

1

Enable Reflection

from praisonaiagents import Agent

agent = Agent(
    name="Reflective Agent",
    instructions="You write high-quality content",
    reflection=True  # Enable self-reflection
)

agent.start("Write a compelling product description")
2

With Configuration

from praisonaiagents import Agent, ReflectionConfig

agent = Agent(
    name="Quality Agent",
    instructions="You produce accurate, well-researched content",
    reflection=ReflectionConfig(
        min_iterations=1,    # Minimum reflection cycles
        max_iterations=3,    # Maximum reflection cycles
        llm="gpt-4o",        # Model for reflection
    )
)

​
How Reflection Works

​
The Reflection Process

PhaseWhat HappensPurpose
GenerateCreate initial responseFirst attempt
EvaluateAssess quality, accuracy, completenessFind issues
ImproveRefine based on feedbackBetter output
RepeatContinue until satisfactory or max iterationsQuality assurance

​
Configuration Options

from praisonaiagents import ReflectionConfig

config = ReflectionConfig(
    min_iterations=1,     # Minimum reflection cycles
    max_iterations=3,     # Maximum reflection cycles
    llm="gpt-4o",         # LLM for reflection (optional)
    prompt="Evaluate...", # Custom reflection prompt (optional)
)
OptionTypeDefaultDescription
min_iterationsint1Minimum reflection cycles
max_iterationsint3Maximum reflection cycles
llmstrNoneLLM for reflection (uses agent’s LLM if not set)
promptstrNoneCustom reflection prompt

​
Reflection Depth

​
Light Reflection

# Single pass - quick check
agent = Agent(
    instructions="You answer questions",
    reflection=ReflectionConfig(
        min_iterations=1,
        max_iterations=1,
    )
)

​
Standard Reflection

# Default - good balance
agent = Agent(
    instructions="You write articles",
    reflection=True  # Uses defaults: min=1, max=3
)

​
Thorough Reflection

# Deep reflection for critical content
agent = Agent(
    instructions="You write legal documents",
    reflection=ReflectionConfig(
        min_iterations=2,
        max_iterations=5,
        llm="gpt-4o",  # Use powerful model
    )
)

​
Custom Reflection Prompts

Customize what the agent evaluates: 
agent = Agent(
    instructions="You write technical documentation",
    reflection=ReflectionConfig(
        prompt="""Evaluate this response for:
1. Technical accuracy - Are all facts correct?
2. Completeness - Is anything missing?
3. Clarity - Is it easy to understand?
4. Code examples - Are they correct and runnable?

If any issues found, provide specific improvements."""
    )
)

​
When to Use Reflection

✅ Use Reflection For

  • Content writing
  • Code generation
  • Technical documentation
  • Research summaries
  • Customer-facing content

❌ Skip Reflection For

  • Real-time chat
  • Simple lookups
  • Time-critical responses
  • Trivial questions

​
Reflection vs Planning

AspectPlanningReflection
WhenBefore executionAfter generation
PurposeDecompose taskImprove output
FocusStrategyQuality
IterationsOnceMultiple

​
Best Practices

More iterations = better quality but slower. Use max_iterations=3 for most tasks, increase for critical content.
Generic reflection may miss domain-specific issues. Customize the prompt for your use case.
Use planning to break down the task, then reflection to ensure quality output.

Planning

Think before acting

Guardrails

Validate outputs