Ecommerce ops · Production

DoorDash identifies five areas for leveraging generative AI in its delivery platform

The problem

DoorDash identified friction in the customer ordering journey, manual effort in data processing tasks, and limited personalization as gaps the company sought to address through generative AI.

Workflow diagram · grounded in source
1
Customer task automation
ai_action
“Generative AI can assist customers by automating tasks such as cart building, getting order status updates, retrieving account information, finding recipe information, and order checkout”
2
Personalized cart template generation
ai_action
“DoorDash could provide pre-built cart templates that cater to different family sizes and dietary preferences. By analyzing vast amounts of data, the models can suggest a list of items that are often ordered together for each meal category”
3
Personalized item discovery
ai_action
“Generative AI can analyze a customer's order history, location, time of day, and other factors to generate a personalized list of items that they might be interested in”
4
Merchant content and menu generation
output
“By automating the creation of menus, merchandising, top 10 lists, marketing campaigns, and videos with Generative AI”
5
OCR receipt data extraction
ai_action
“running Optical Character Recognition (OCR) on receipts to detect errors. This reduces manual effort and improves the accuracy and speed of data processing”
6
SQL and document generation for employees
output
“Generative AI can be used to accelerate DoorDash employees' productivity by automating tasks such as SQL writing, and document drafting”
Reported outcome

DoorDash described five aspirational use cases for generative AI spanning customer task assistance, personalized discovery, content generation, structured data extraction, and employee productivity; the only confirmed production use was generative AI helping to edit the blog post itself.

Reported metrics
Customer journey frictionreduce frictions in the customer journey
Customer ordering timesave time for customers
Manual data processing effortreduces manual effort
Restaurant inventory wastereduce waste
Show all 5 reported metrics
customer journey frictionreduce frictions in the customer journey
customer ordering timesave time for customers
manual data processing effortreduces manual effort
restaurant inventory wastereduce waste
employee task delivery timequicken task delivery times
Reported stack
ChatGPTOCR
Source
https://doordash.engineering/2023/04/26/doordash-identifies-five-big-areas-for-using-generative-ai/
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

DoorDash described five aspirational use cases for generative AI spanning customer task assistance, personalized discovery, content generation, structured data extraction, and employee productivity; the only confirmed…

What tools did this team use?

ChatGPT, OCR.

What results were reported?

Customer journey friction: reduce frictions in the customer journey; Customer ordering time: save time for customers; Manual data processing effort: reduces manual effort; Restaurant inventory waste: reduce waste (source-reported, not independently verified).

How is this ecommerce ops AI workflow structured?

Customer task automation → Personalized cart template generation → Personalized item discovery → Merchant content and menu generation → OCR receipt data extraction → SQL and document generation for employees.

Related ecommerce ops cases