ReflectionConfig

Configure self-reflection for agents to evaluate and improve responses

Enable agents to evaluate their own responses and iteratively improve quality through self-reflection.

Quick Start

1. Simple Enable

   Enable reflection with defaults:

   from praisonaiagents import Agent
   
   agent = Agent(
       name="Reflective Agent",
       instructions="You self-reflect on responses",
       reflection=True
   )
   
2. With Configuration

   Configure reflection behavior:

   from praisonaiagents import Agent
   from praisonaiagents.config import ReflectionConfig
   
   agent = Agent(
       name="Reflective Agent",
       instructions="You self-reflect on responses",
       reflection=ReflectionConfig(
           min_iterations=1,
           max_iterations=3,
           llm="gpt-4o",
           prompt="Evaluate accuracy and completeness..."
       )
   )
   

---

Configuration Options

from praisonaiagents.config import ReflectionConfig

config = ReflectionConfig(
    # Iteration limits
    min_iterations=1,
    max_iterations=3,
    
    # Reflection LLM (if different from main)
    llm=None,
    
    # Custom reflection prompt
    prompt=None
)

Parameter	Type	Default	Description
min_iterations	int	1	Minimum reflection iterations
max_iterations	int	3	Maximum reflection iterations. Bounds both “not yet good enough” passes and passes whose response cannot be parsed — the agent returns the current draft un-reflected once this cap is hit.
llm	str | None	None	Model for reflection (defaults to agent’s model)
prompt	str | None	None	Custom prompt for evaluation

max_iterations bounds parse-error retries too. If a reflection response persistently fails to parse (a structured-output refusal, a content-filter block, or a truncation), the agent stops after this many failed passes instead of looping. See the Reflection troubleshooting guide for the exact log line and next steps.

---

Common Patterns

Pattern 1: High-Quality Responses

from praisonaiagents import Agent
from praisonaiagents.config import ReflectionConfig

agent = Agent(
    name="Quality Agent",
    instructions="Produce high-quality analysis",
    reflection=ReflectionConfig(
        min_iterations=2,
        max_iterations=5,
        prompt="Check for: accuracy, completeness, clarity, actionability"
    )
)

Pattern 2: Different Model for Reflection

from praisonaiagents import Agent
from praisonaiagents.config import ReflectionConfig

agent = Agent(
    name="Dual Model Agent",
    instructions="Use GPT-4o to review responses",
    llm="gpt-4o-mini",  # Main model
    reflection=ReflectionConfig(
        llm="gpt-4o",   # Better model for evaluation
        max_iterations=2
    )
)

---

Best Practices

Set Reasonable Iteration Limits

Balance quality with response time. 2-3 iterations is usually sufficient.

Use Custom Prompts for Specific Domains

Customize the reflection prompt to evaluate domain-specific criteria.

Consider Cost vs Quality

More iterations and stronger models improve quality but increase cost and latency.

---

Related

Self Reflection

Learn about self-reflection features

PlanningConfig

Configure planning mode