Noritz uses a Diagnostics AI Assistant to shorten customer support resolution time
Quality assurance and field engineers at Noritz use the Noritz Diagnostics AI Assistant, built on AWS Bedrock and orchestrated through DataRobot, to standardise data entered by field engineers, automatically classify breakdown cases and recommend suitable resolutions. The page reports a 70% reduction in the effort needed to review and process data.
- Agent or tool
- DataRobot with AWS Bedrock
- Topic
- Customer Support
- Reported on
- Case study (DataRobot)
- Added
- 2026-11-13
Why it matters
Support is repetitive and time-sensitive. Agents can draft answers, look things up and handle simple requests, so people can focus on the tricky ones. It is one of 554 sightings filed under Customer Support on Agent Sightings (number 172 by interest), and one of 1 involving DataRobot with AWS Bedrock.
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into DataRobot with AWS Bedrock or any similar agent and adjust the details to your situation.
I want an agent to handle this kind of customer request end to end, follow our policy, and hand anything unclear to a person. The tool in the source case was DataRobot with AWS Bedrock.
Tip: Start small: run it once on a low-stakes example, read what the agent did, and only then let it run on real work.
Source
Read the original first-hand account on Case study (DataRobot): https://datarobot.com/customers/noritz. Our summary is a paraphrase; details are in the source.
Built an AI agent? Feature your agent on Agent Sightings, free submission or a featured spot.