NTT DATA validates enterprise agent architectures on Amazon Bedrock AgentCore with Datadog
NTT DATA's Technology Innovation Headquarters validates emerging AI technologies and develops operational practices to help customers move generative and agentic AI into production. The team launched an initiative to validate enterprise agent architectures using Amazon Bedrock AgentCore, and used Datadog Agent Observability to understand how agents reach decisions, evaluate quality, and manage cost. The case title reports that agent quality was validated and costs cut by 50%.
- Agent or tool
- Amazon Bedrock AgentCore with Datadog Agent Observability
- Topic
- DevOps & Infra
- Reported on
- Case study (Datadog)
- Added
- 2026-11-13
Why it matters
Keeping servers and pipelines healthy is constant, detail-heavy work. Agents that can read logs and run routine fixes are a big help, as long as a person keeps an eye on what changes. It is one of 130 sightings filed under DevOps & Infra on Agent Sightings (number 19 by interest), and one of 1 involving Amazon Bedrock AgentCore with Datadog Agent Observability.
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into Amazon Bedrock AgentCore with Datadog Agent Observability or any similar agent and adjust the details to your situation.
I want an agent to watch this part of our operations, explain what it sees, and wait for approval before it changes anything. The tool in the source case was Amazon Bedrock AgentCore with Datadog Agent Observability.
Tip: Try it first on a staging system or with read-only credentials, and require approval for anything that changes production.
Source
Read the original first-hand account on Case study (Datadog): https://datadoghq.com/case-studies/ntt-data. Our summary is a paraphrase; details are in the source.
Featured in these guides
Built an AI agent? Feature your agent on Agent Sightings, free submission or a featured spot.