# How Doordash uses AWS Bedrock

**50x** increase in testing capacity

As published on [aws.amazon.com](https://aws.amazon.com/solutions/case-studies/doordash-bedrock-case-study/). Captured by usedby on 2026-10-03.

- Company: [Doordash](https://www.usedby.ai/companies/doordash.md)
- Tool: [AWS Bedrock](https://www.usedby.ai/tools/aws-bedrock.md)
- Industry: [Logistics & Supply Chain](https://www.usedby.ai/companies/industry/logistics-supply-chain.md)
- Teams: Contact Center

## What the story says

DoorDash uses Anthropic's Claude models in Amazon Bedrock, with retrieval-augmented generation over its public help center, to power a voice self-service contact center assistant that answers common support questions from Dashers. The assistant runs within Amazon Connect Customer and handles routine inquiries so live agents can focus on complex issues.

Summary written by usedby from the source page, in English. The figures are those of AWS Bedrock and Doordash, not ours.

> The Amazon Bedrock–based solution reduced generative AI application development time by 50 percent.

- **2.5 seconds or less**: “With the release of Claude 3 Haiku, DoorDash achieved the accuracy and speed it needed for its voice application, achieving a response latency of 2.5 seconds or less.”
- **50x**: “This framework helps DoorDash to complete thousands of automated tests per hour—a 50x increase in capacity—and semantically evaluates responses against ground-truth data.”

> Using AWS and Anthropic’s Claude, we’ve built a solution that gives Dashers reliable and simple-to-understand access to the information they need, when they need it,
>
> Chaitanya Hari, Contact Center Product Lead

## What usedby checked

We compared the story with its live page on 2026-10-03.

- Checked: the figure 50x is on the page; its label is our wording.
- Checked: the passage quoted above is copied word for word from the page, near the name of Doordash.
- Checked: Doordash uses AWS Bedrock. Confirmed line. Latest check across sources: 2026-10-03.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/building-a-generative-ai-contact-center-solution-f · How we check: https://www.usedby.ai/methodology