Uber improves Genie on-call copilot answer quality by 27% with Enhanced Agentic-RAG
Genie's traditional RAG pipeline over 40+ internal engineering security and privacy policy documents produced responses with significant accuracy gaps—many answers were incomplete, inaccurate, or failed to retrieve relevant information—preventing SME approval for broad deployment across Slack channels.
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 · LLM-powered document enrichment
A custom Google document loader uses an LLM-powered enrichment process to convert extracted table contents into markdown-formatted tables and add metadata identifiers to table-containing chunks.
Transitioning to the Enhanced Agentic-RAG architecture increased the percentage of acceptable answers by a relative 27% and reduced incorrect advice by a relative 60%, while automated evaluation cut experiment cycle time from weeks to minutes and produced a measurable reduction in support load for on-call engineers and SMEs.
What failed first
Traditional PDF loaders (SimpleDirectoryLoader from LlamaIndex and PyPDFLoader from LangChain) failed to capture structured text and table formatting, fragmenting table cells from their row/column context and breaking downstream chunking and retrieval. Standard RAG accuracy improvements plateaued quickly and each evaluation cycle required weeks of SME bandwidth.