customer_support · logistics · workflow

DoorDash deploys LLM-based RAG chatbot with guardrail and quality monitoring to autonomously support Dashers

DoorDash's existing automated Dasher support relied on flow-based resolution paths that could address only a small subset of issues. The knowledge base was hard to navigate, time-consuming to read, and available only in English despite many Dashers preferring other languages.

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 · Dasher presents issue
The process begins when a Dasher presents an issue to the chatbot.
Tools used
LLMsRAGLLM GuardrailLLM Judgevector storePromptfoo
Outcome

The LLM Guardrail reduced hallucinations by 90% and cut potentially severe compliance issues by 99%. The system now autonomously assists thousands of Dashers each day, allowing human agents to focus on more complex problems.

What failed first

The initial LLM RAG chatbot generated responses that diverged from the intended context, appearing natural but potentially inaccurate. Additional challenges included language consistency failures and a requirement for highly accurate conversation summarization before retrieval could function correctly.

Results
Time savedautonomously assists thousands of Dashers
Volume90%
Source

https://careers.doordash.com/blog/large-language-modules-based-dasher-support-automation/

How we source this →

Grounding & classification
Source type: technical build writeup
34 fields verified against source quotes.
chatbotconversational aiknowledge searchquality inspectionragsummarizationchat transcriptknowledge basefailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedvendor confirmedworkflow describedecommercelogisticsautomation rateemployee productivityerror reductiontechnical build writeupcustomer supportticket triageautonomous resolutionescalation workflowrag answering