Automating Merchant Onboarding at DoorDash | Applied Compute
appliedcompute.com · 924 words · saved by 1 readers
How DoorDash trained a proprietary agent using internal experts and delivered a 30% relative reduction in critical menu errors
"AI has long been core to how DoorDash helps merchants succeed. By encoding our quality standards directly into model training, we scaled our internal expertise and raised the bar on menu accuracy on the platform." Andy Fang Co-Founder of DoorDash DoorDash is a global leader in food delivery, with a core focus on helping merchants run their businesses seamlessly. During onboarding, DoorDash enables merchants to go live in as little as one day by using AI to generate highly accurate menus. Menu accuracy is critical because it impacts whether orders run smoothly, restaurants prepare the right it
saved by
related reading
- Training an Agentic Router for Optimal Cost-Performance on SWE Tasks | Applied Computeappliedcompute.com
- Training a State-of-the-Art Legal Agent with Harvey | Applied Computeappliedcompute.com
- Building self-improving tax agents with Codex | OpenAIopenai.com
- Demystifying evals for AI agents \ Anthropicanthropic.com
- Convictionconviction.com
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- Parsed | Custom, interpretable AI systems that continuously learnparsed.com
- After Automation | Everyevery.to
- Stop Scrolling, Just Ask: A New Conversational Way To Search on DoorDash | DoorDashabout.doordash.com
- MAI-Thinking-1: Building a Hill-Climbing Machinemicrosoft.ai
- Musings on Building a Generative AI Productlinkedin.com
- Convictionconviction.com