智能体
infoq.com ·
@Leela Kumili
DoorDash 用 AI Agent 将杂货复购延迟从 16 秒降至 2 秒
DoorDash 通过批量 LLM 推理预计算周期性采购需求，结合确定性校验和实时商品目录解析，将杂货复购延迟从 16 秒降至 2 秒；可编辑购物界面避免不必要的模型调用。公司称购物清单浏览量翻倍，该流程下单率提升约 34%。数据为公司自报。
AI推荐理由 InfoQ 报道 DoorDash 用批量 LLM 推理预计算周期性采购需求，配合确定性校验与实时商品目录解析，将杂货复购延迟从 16 秒降至 2 秒，并称购物清单浏览量翻倍、该流程下单率提升约 34%。有具体架构做法与量化指标，属可验证的产业落地案例；指标为公司自报，缺少独立验证。
78
正文
DoorDash reduced grocery reorder latency from 16 to 2 seconds by precomputing recurring purchase needs using batch LLM inference and deterministic validation. Live catalog resolution keeps product selections current, while an editable shopping interface avoids unnecessary model calls. The company reports that shopping list views doubled and the flow’s order rate increased by approximately 34%
*By Leela Kumili*