it_support · logistics · workflow
Genie: Uber's generative AI on-call copilot saves 13,000 engineering hours via RAG over internal docs
Uber's internal engineering Slack support channels received around 45,000 questions per month, but high volumes and long response wait times reduced productivity for both users and on-call engineers; relevant answers were hard to find because documentation was fragmented across Engwiki, internal Stack Overflow, and other locations, leading users to ask the same questions repeatedly.
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 · User posts question in Slack
A user posts a question in a Slack channel served by Genie.
Tools used
Slack · partnerRAGApache SparkOpenAI embedding modellangchainTerrablobSiaKafkaHiveMichelangelo Gateway
Outcome
Since its September 2023 launch, Genie has expanded to 154 Slack channels, answered over 70,000 questions, achieved a 48.9% helpfulness rate, and saved an estimated 13,000 engineering hours.
Results
Time saved45,000
Volume154
Running sinceSeptember 2023
Grounding & classification
Source type: technical build writeup
38 fields verified against source quotes.
chatbotconversational aiknowledge searchragchat transcriptknowledge basehuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedlogisticssoftwaredeflection rateemployee productivitytime savedtechnical build writeupincident managementit supportautonomous resolutionescalation workflowrag answering