# How Cox Automotive uses AWS Bedrock

**30 minutes**: “30 minutes to complete estimates that previously took 8-48 hours”

As published on [aws.amazon.com](https://aws.amazon.com/es/solutions/case-studies/cox-auto-case-study/). Captured by usedby on 2026-10-09.

- Company: [Cox Automotive](https://www.usedby.ai/companies/cox-automotive-coxautomotive-com.md)
- Tool: [AWS Bedrock](https://www.usedby.ai/tools/aws-bedrock.md)

## What the story says

Cox Automotive builds and runs agentic AI solutions on Amazon Bedrock, Bedrock AgentCore and Strands Agents across fleet services, dealer-consumer communication and retail. AgentCore provides the runtime, memory, observability and permission controls for the agents.

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

> Cox's FleetMate internal solution helps transform complex fleet repair estimates from 8-48 hours down to just 30 minutes — and the initial version was built in just 4 days.

- **17,000 work hours**: “One process automation projected to save 17,000 work hours in pilot”
- **50%**: “50% reduction in technical debt through rapid modernization”
- **3x**: “response rates from consumers are more than 3x higher”
- **17**: “17 production solutions deployed from 57 evaluated ideas”

> The watershed moment came during FleetMate deployment," Johnson recalled. "We went from concept to production in days.
>
> Marianne Johnson, EVP & Chief Product Officer at Cox Automotive

Source: [aws.amazon.com](https://aws.amazon.com/es/solutions/case-studies/cox-auto-case-study/), captured 2026-10-09.

## What usedby checked

We compared the story with its live page on 2026-10-09.

- Checked: the figure 30 minutes is printed word for word on the page, near the name of Cox Automotive.
- Checked: the passage quoted above is copied word for word from the page, near the name of Cox Automotive.
- Checked: Cox Automotive uses AWS Bedrock. Confirmed line. Latest check across sources: 2026-10-09.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/cox-automotive-aws-bedrock · How we check: https://www.usedby.ai/methodology