back_office_ops · ecommerce · workflow
Woowa Brothers builds QueryAnswerBird, an LLM-based AI data analyst using RAG and Text-to-SQL
More than half of Woowa Brothers employees who wanted to use SQL lacked time to learn it or struggled to generate queries reflecting business logic, and had concerns 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 via Slack
Employees can easily ask questions and receive answers anytime on the Slack application.
Tools used
LLMRAGLangchainLLMOpsGPT-4oGPT-3.5Microsoft Azure OpenAIVectorDBLangserve Playground
Outcome
QAB provides employees with high-quality SQL queries and interpretations within 30 seconds to 1 minute, and employees report it helped them greatly in better understanding their work.
What failed first
The initial hackathon version using GPT-3.5 had architectural limitations, and GPT-4 alone generated queries lacking company-specific domain knowledge, while LLM hallucination caused inconsistent query quality.
Results
Time saved30 seconds to 1 minute
Volume95%
Running sinceJanuary 2024
Grounding & classification
Source type: technical build writeup
34 fields verified against source quotes.
agentic workflowconversational aidata extractionragknowledge basefailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedecommerceemployee productivitytime savedtechnical build writeupback office opsagentic task executionrag answering