back_office_ops · ecommerce · workflow
DoorDash builds a multi-agent internal AI platform for unified data and operations intelligence
DoorDash's knowledge was distributed across experimentation platforms, metrics hubs, dashboards, wikis, and Slack, requiring significant context-switching to answer complex business questions.
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 submits business query
A user submits a complex business question, such as investigating a drop in conversions.
Tools used
LangGraphGoogle DocsGoogle SheetsSlackCursorJiraDeepEvalMCPA2Avector database
Outcome
DoorDash's agentic platform now enables operators to get trustworthy, evidence-backed answers in seconds, democratizing data access for business leaders and operations managers without requiring them to write SQL.
What failed first
Existing self-service tools were sub-optimal because they assumed users already knew which data sources to query and how to interpret them correctly; skillset gaps and the risk of misinterpretation limited their usefulness for critical analyses.
Results
Time savedanswer in seconds, not hours
Running sincePhase 1 launched (date unspecified)
Grounding & classification
Source type: technical build writeup
36 fields verified against source quotes, 3 dropped as unverifiable.
agentic workflowai agentcode generationenterprise searchmulti agent workflowragsummarizationknowledge basesupport ticketfailure mode describednamed customerproduction runtime claimedtools describedworkflow describedecommercelogisticsemployee productivitytime savedtechnical build writeupback office opsdata entry opsfinance opsagentic task executionrag answering