customer_support · logistics · workflow
DoorDash pairs clustering algorithms and LLMs to auto-identify knowledge base gaps and draft support articles
As DoorDash's marketplace grew, manually maintaining the support chatbot knowledge base became unscalable — new policies, product changes, and a long tail of edge cases demanded constant fresh answers that were too resource-intensive and time-consuming to handle by hand.
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 · Escalated chat ingestion
Thousands of anonymized chat transcripts that were escalated to a live agent are fed into the semantic clustering pipeline.
Tools used
large language models (LLMs)clustering algorithmsopen-source embedding modelRAGLLM judge
Outcome
The system lowers escalation rates, improves customer satisfaction, and reduces specialist manual workload. In A/B tests, high-traffic escalation clusters saw escalation rates drop from 78% in the control group to 43% in the treatment group, and roughly 75% of KB retrieval events in the treatment group contained only UGC KB content.
Results
Time savedminutes instead of days
Volume78%
Grounding & classification
Source type: technical build writeup
34 fields verified against source quotes.
chatbotcontent generationdocument classificationragsummarizationchat transcriptknowledge basehuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedecommercelogisticscustomer satisfactiondeflection rateemployee productivitytime savedtechnical build writeupback office opscustomer supportai draft human approvalextract classify routerag answering