Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.praison.ai/llms.txt

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

Self-reflection enables agents to evaluate and improve their responses in async execution, bringing full feature parity with sync agents.

​
Quick Start

1

Basic Async Reflection

Enable reflection in async agents with simple boolean flag:
import asyncio
from praisonaiagents import Agent

agent = Agent(
    name="Writer",
    instructions="Write concise product blurbs.",
    self_reflect=True,
    min_reflect=1,
    max_reflect=3,
)

async def main():
    result = await agent.achat("Write a one-line blurb for a smart mug.")
    print(result)

asyncio.run(main())
2

Custom Reflection Criteria

Configure reflection with custom criteria for async agents:
import asyncio
from praisonaiagents import Agent, ReflectionConfig

agent = Agent(
    name="Technical Writer",
    instructions="Create technical documentation.",
    self_reflect=ReflectionConfig(
        min_reflect=2,
        max_reflect=5,
        criteria="Is the response clear, accurate, and complete?"
    )
)

async def main():
    result = await agent.achat("Explain async/await in Python.")
    print(result)

asyncio.run(main())

​
How It Works

Self-reflection in async agents follows the same process as sync agents:
ComponentPurposeAsync Behavior
Initial GenerationCreate first responseUses await agent.achat()
Self-EvaluationJudge response qualityAsync LLM call for evaluation
Iterative ImprovementRefine based on feedbackMultiple async iterations
Final OutputDeliver best responseReturns when criteria met

​
Feature Parity

Prior to PR #1704, async agents had limited reflection support:
Before PR #1704: Only legacy custom-LLM async branch supported reflection; the default OpenAI async path skipped it entirely.After PR #1704: Self-reflection works uniformly in both sync and async agents on all execution paths, including the default unified-dispatch path.
FeatureSync AgentsAsync Agents (Before #1704)Async Agents (After #1704)
Self-reflection✅ Full support❌ Limited/bypassed✅ Full parity
Custom criteria✅ Supported❌ Not available✅ Supported
Min/max reflect✅ Configurable❌ Not configurable✅ Configurable
Unified dispatch✅ Works❌ Bypassed reflection✅ Full support

​
Configuration Options

All reflection configuration options work identically in async agents:
OptionTypeDefaultDescription
self_reflectboolFalseEnable/disable self-reflection
min_reflectint1Minimum reflection iterations
max_reflectint3Maximum reflection iterations
criteriastrAuto-generatedCustom evaluation criteria

​
Best Practices

Set reasonable min_reflect and max_reflect values to balance quality with performance. Async reflection still involves multiple LLM calls.
Provide specific evaluation criteria for better reflection quality. Generic criteria like “Is this good?” are less effective than specific requirements.
Reflection increases response time and token usage. Monitor these metrics in production async applications.
Wrap async reflection calls in try-catch blocks to handle potential timeout or API errors gracefully.

Async Agents

Complete guide to async agent execution

Self-Reflection Concepts

Core concepts and architecture