Complete reference for all Reflexio configuration options including profile extraction, playbook, and evaluation settings.

Configuration Guide

This guide explains all configuration options available in Reflexio. Configuration controls how profiles are extracted, playbooks are generated, and agent performance is evaluated.

Overview

Reflexio uses a centralized Config object that contains settings for:

Storage - Where data is stored (local, S3, or Supabase)
LLM - API keys and model selection for LLM providers
Profile Extraction, Playbooks & Evaluation - How user profiles are generated, playbooks are collected, and agent performance is measured

Getting and Setting Configuration

Configure Reflexio programmatically using the client:

Enterprise

If you're using Reflexio Enterprise, you can also configure settings visually via the web portal under the Settings page.

from reflexio import ReflexioClient

client = ReflexioClient()  # uses REFLEXIO_API_KEY env var
# Self-hosted: client = ReflexioClient(url_endpoint="http://localhost:8081")

# Get current configuration
config = client.get_config()

# Modify configuration
config.profile_extractor_configs = [...]

# Save configuration
client.set_config(config)

General Settings

Agent Context

Optionally provide global context about the agent's environment that should be shared across all extractors and evaluations.

config.agent_context_prompt = """
This agent is a customer service representative for an e-commerce platform.
The agent helps customers with:
- Product inquiries and recommendations
- Order tracking and status updates
- Returns and refunds
- Technical support for the website
"""

Extraction Window Configuration

Reflexio uses a sliding window to batch interactions for extraction. This controls how many interactions are processed together and how frequently extraction runs.

config.batch_size = 10  # Number of interactions per extraction
config.batch_interval = 5  # New interactions before next extraction

Field	Type	Description
`batch_size`	int	Number of interactions included in each extraction batch
`batch_interval`	int	Number of new interactions that trigger the next extraction
`skip_should_run_check`	bool	Skip the LLM pre-extraction eligibility check — extraction always runs (default: `False`)

Example: With batch_size=10 and batch_interval=5:

First extraction processes interactions 1-10
After 5 new interactions arrive, next extraction processes interactions 6-15
After 5 more, next extraction processes interactions 11-20

This overlapping window ensures context continuity between extractions while avoiding redundant processing of every single interaction.

Complete Configuration Example

from reflexio import ReflexioClient
from reflexio.models.config_schema import (
    Config,
    ProfileExtractorConfig,
    PlaybookConfig,
    PlaybookAggregatorConfig,
    AgentSuccessConfig,
    ToolUseConfig
)

client = ReflexioClient()  # see Quickstart for connection options

# Get current config (storage defaults to SQLite — no configuration needed)
config = client.get_config()

# Configure agent context
config.agent_context_prompt = """
Customer service agent for an online booking platform.
Helps users book hotels, flights, and activities.
"""

# Configure profile extraction
config.profile_extractor_configs = [
    ProfileExtractorConfig(
        extractor_name="traveler_profile",
        profile_content_definition_prompt="""
        Extract: name, travel preferences, budget range,
        frequent destinations, loyalty program status
        """,
        context_prompt="Travel booking conversation",
        metadata_definition_prompt="category: 'traveler_profile'"
    )
]

# Configure playbook collection
config.playbook_configs = [
    PlaybookConfig(
        playbook_name="booking_experience",
        playbook_definition_prompt="""
        Was the booking process smooth? Any pain points?
        Did the agent provide helpful recommendations?
        """,
        playbook_aggregator_config=PlaybookAggregatorConfig(
            min_cluster_size=10,
            reaggregation_trigger_count=5
        )
    )
]

# Configure tools the agent can use (shared across evaluation and extraction)
config.tool_can_use = [
    ToolUseConfig(
        tool_name="search_availability",
        tool_description="Search available options"
    ),
    ToolUseConfig(
        tool_name="create_reservation",
        tool_description="Create a new reservation"
    )
]

# Configure success evaluation
config.agent_success_configs = [
    AgentSuccessConfig(
        evaluation_name="booking_completion",
        success_definition_prompt="""
        Success: Customer completed a booking or has clear next steps.
        Failure: Customer left confused, frustrated, or without resolution.
        """,
        sampling_rate=1.0
    )
]

# Configure extraction windows
config.batch_size = 20
config.batch_interval = 10

# Save configuration
client.set_config(config)

Best Practices

Start with profile extraction - Configure profile_extractor_configs first to ensure user data is captured correctly
Use specific prompts - Be explicit about what to extract. Vague prompts lead to inconsistent results
Test with sampling - Use sampling_rate < 1.0 during development to reduce API costs
Monitor playbook thresholds - Set min_cluster_size high enough to get meaningful aggregations
Filter by source - Use request_sources_enabled to process only relevant interaction types
Iterate on definitions - Review extracted profiles and adjust prompts based on results

Next Steps

Quick Start Guide - Basic usage examples
API Reference - Complete method documentation

Configuration Guide

On this page