back_office_ops · ecommerce · workflow
Woowa Brothers' BADA team builds LLM-based AI data analyst QueryAnswerBird (QAB) with RAG and Text-to-SQL
More than half of Woowa Brothers employees wanted to use SQL for data extraction but lacked time to learn it or had difficulty generating queries reflecting business logic, and they were concerned about the reliability of data extraction.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Employee asks question in Slack
Employees can easily ask questions and receive answers anytime on the Slack application.
Tools used
LLMRAGLangchainLLMOpsVectorDBLangserve Playground
Outcome
QAB provides high-quality query responses within 30 seconds to 1 minute, won first place at Woowa Hackathon 2023, and generated enough employee demand to warrant full-scale development starting January 2024.
What failed first
The initial hackathon prototype using Microsoft Azure OpenAI's GPT-3.5 API was simple and had limitations in achieving systemization, efficiency, accessibility, and automation; generated queries lacked domain knowledge and suffered from LLM hallucination.
Results
Time savedwithin 30 seconds to 1 minute
Volumeabout 95%
Running sinceJanuary 2024
Grounding & classification
Source type: technical build writeup
32 fields verified against source quotes.
agentic workflowconversational aidata extractionenterprise searchragknowledge basebuilder submittedfailure mode describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedecommercecycle time reductionemployee productivitytechnical build writeupback office opsextract classify routerag answering