Overview

OHouseAI is an AI-powered interior design generation service at Bucketplace (오늘의집). I led the systematization of the GenAI workflow, modularizing the architecture into a Pipeline Provider + Subgraph pattern using LangGraph. The service reached Korea #8 ranking in the Graphics/Design category.

OHouseAI Architecture

Key Achievements

  • Net Satisfaction Score (NSS): +253%
  • Positive-Negative Ratio (PN): +205%
  • User Engagement: Requests per user increased by 2.3x
  • Retention: Improved from 7% to 14%
  • Latency: Reduced from 71.7s to 35.7s
  • Model Quality: Outperformed GPT-IMAGE-1.5 and Gemini Nano (8.3/10 intent reflection, 8.1/10 context preservation)

Technical Approach

Pipeline Provider + Subgraph Architecture

Modularized the GenAI workflow into composable components using LangGraph:

  • Pipeline Provider: Centralized orchestration layer managing the lifecycle of generation requests
  • Subgraph Pattern: Each generation capability is implemented as an independent subgraph, enabling independent iteration

OHouseAI Comparison

LLM-as-a-Judge Evaluation Pipeline

Built a batch evaluation pipeline for data-driven model selection:

  • Scale: 4 evaluation rounds x 99 test sets
  • Methodology: Automated side-by-side comparisons with structured scoring:
    • Intent Reflection: How well the output matches the user’s design intent
    • Context Preservation: How faithfully the output preserves the original context
  • Application: Used to compare candidate models (including GPT-IMAGE-1.5 and Gemini Nano) for production model selection

OHouseAI Judge Scores

Monitoring and Observability

Production monitoring through LangFuse for end-to-end tracing of the generation pipeline.

OHouseAI Dashboard

Architecture Systematization

Restructured the existing LangGraph pipeline into a modular Pipeline Provider + Subgraph pattern:

  • Before: Monolithic LangGraph graph handling all generation types in a single flow
  • After: Composable subgraphs per generation capability, orchestrated by a centralized Pipeline Provider with checkpointed state, Redis persistence, and MongoDB storage
  • Benefits: Independent iteration on each generation type, modular prompt management, structured request monitoring, and performance evaluation

Tech Stack

  • Agent/Workflow Framework: LangChain, LangGraph
  • Backend: FastAPI, Kafka
  • Storage: MongoDB (domain objects), Redis (LangGraph persistence)
  • Observability: LangFuse
  • Evaluation: LLM-as-a-Judge (4 rounds x 99 test sets)
  • Architecture Pattern: Pipeline Provider + Subgraph

Period

July 2025 - November 2025 | Bucketplace (오늘의집)