awslabs / awslabs/agentcore-samples
01-tutorials - [Content Improvement] - Add Datadog observability integration tutorial for AgentCore Runtime with Strands Agents.
- Dominant language
- Python
- Stars
- 3.4k
- Forks
- 1.3k
- Avg merge
- 1d 22h
- Merged PRs (30d)
- 30
Description
**Which component is impacted by this improvement?**
- [ ] 01-AgentCore-runtime
- [ ] 02-AgentCore-gateway
- [ ] 03-AgentCore-identity
- [ ] 04-AgentCore-memory
- [ ] 05-AgentCore-tools
- [x] 06-AgentCore-observability
- [ ] 07-AgentCore-E2E
**Improvement Description**
A clear and concise description of the improvement.
```
Add Datadog observability integration tutorial for AgentCore Runtime with Strands Agents.
This improvement adds a complete tutorial demonstrating how to deploy a Strands agent to
Amazon Bedrock AgentCore Runtime with Datadog as the observability backend using OpenTelemetry (OTLP).
The tutorial includes:
- Step-by-step Jupyter notebook for deploying agents with Datadog telemetry
- Strands agent implementation with web search tool and automatic trace export
- Configuration guidance for all Datadog regions (US1, US3, US5, EU1, AP1)
- Integration with StrandsTelemetry for capturing agent invocations, tool calls, and LLM interactions
This enables users to leverage Datadog's APM, distributed tracing, and monitoring capabilities
for their AgentCore-hosted agents as an alternative to the default AgentCore observability.
```
Contributor guide
Assessment
This issue has not been assessed yet.