Amazon Bedrock AgentCore、オンプレミス・マルチクラウド AI エージェントの監視

When you deploy AI agents built with frameworks like Strands Agents, LangGraph, and CrewAI, you need observability into their performance. This holds true whether they run on Amazon Elastic Kubernetes Service (Amazon EKS), Amazon Elastic Container Service (Amazon ECS), AWS Lambda, on-premises, or another cloud provider such as Google Cloud Platform (GCP) or Microsoft Azure.

Amazon Bedrock AgentCore is a platform to build, connect, and optimize agents at scale, with any framework or model. Although Amazon Bedrock AgentCore Observability, a capability of Amazon Bedrock AgentCore, provides native tracing, monitoring, and analytics that local cloud monitoring tools don’t offer out of the box, it natively supports only agents deployed on AgentCore runtime in the AWS Cloud. If your agents run anywhere else, you need additional configuration to send telemetry to the dashboard.

In this post, we show you how to set up observability for agents running outside AWS. You learn how to configure the AWS Distro for OpenTelemetry (ADOT) auto-instrumentation in non-AWS environments, route telemetry to the AgentCore Observability dashboard, and validate the setup end to end.

The following diagram shows the end-to-end observability pipeline and how telemetry flows from agents to the AgentCore Observability dashboard.

**Figure 1: End-to-end observability pipeline from agents to the AgentCore Observability dashboard

Solution overview

The solution uses the AWS Distro for OpenTelemetry (ADOT) running in-process with the agent application. ADOT auto-instruments the agent framework and captures generative AI semantic convention spans, then exports the telemetry directly to the Amazon CloudWatch OpenTelemetry Protocol (OTLP) endpoint using SigV4 authentication with AWS Identity and Access Management (IAM) credentials.

Sending telemetry from your AI agent to Amazon Bedrock AgentCore Observability requires three core components:

• ADOT auto-instrumentation: The AWS Distro for OpenTelemetry handles the complexities of exporting telemetry from non-AWS environments.

• IAM credentials: The ADOT uses these access keys to authenticate with CloudWatch and forward your agent’s telemetry (traces, metrics, and logs) to the AgentCore Observability dashboard.

• Environment variables: These contain specific OpenTelemetry settings related to routing and authentication.

As seen in the following diagram, this cross-platform observability solution integrates several AWS services. Amazon CloudWatch serves as the foundation, handling telemetry ingestion and storage. Amazon Bedrock AgentCore Observability adds specialized monitoring dashboards for AI agents. AWS Distro for OpenTelemetry (ADOT) provides the cross-platform instrumentation capabilities. IAM secures the authentication between your external environments and AWS.

Figure 2: Cross-platform observability architecture and the AWS services involved

Observability is a foundational pillar of responsible AI. By routing telemetry to AgentCore Observability, you gain visibility into agent reasoning chains, tool invocations, and model outputs. This allows you to detect hallucinations, monitor for harmful or off-topic responses, track token usage for cost governance, and audit agent behavior across environments. This is especially critical for agents running outside AWS, where problematic outputs might go unnoticed without centralized observability.

Prerequisites

Before you begin, verify that you have:

• An AWS account:

with Amazon Bedrock model access configured (this walkthrough uses Claude Haiku). For model availability by AWS Region, refer to supported models by AWS Region in Amazon Bedrock.

• for designated AgentCore Observability and designated log group(s).

• CloudWatch Transaction Search turned on in your account (one-time setup)

• Python 3.10 or later installed on your non-AWS environment.

• IAM user credentials (access key ID and secret access key) with permissions for:

bedrock:InvokeModel.

• logs:CreateLogGroup, logs:CreateLogStream, logs:PutLogEvents.

• xray:PutTraceSegments, xray:PutTelemetryRecords, xray:GetSamplingRules, and xray:GetSamplingTargets.

• cloudwatch:PutMetricData.

• Outbound HTTPS access to AWS endpoints from your environment.

Turn on CloudWatch Transaction Search

If you haven’t turned on Transaction Search, run the following (one-time per account):

aws xray update-trace-segment-destination --destination CloudWatchLogs --region us-east-1

Verify it’s active:

aws xray get-trace-segment-destination --region us-east-1
# Expected: {"Destination": "CloudWatchLogs", "Status": "ACTIVE"}

How it works

The ADOT auto-instrumentation (aws-opentelemetry-distro) handles the complexity of exporting telemetry from non-AWS environments to CloudWatch:

• Auto-instrumentation: The opentelemetry-instrument command injects the ADOT into the Python runtime. It automatically patches boto3 (for Amazon Bedrock calls) and the Strands framework (for agent reasoning spans) to emit OpenTelemetry traces.

• SigV4 authentication: The aws_configurator uses the boto3 credential chain to sign OTLP export requests with SigV4. From non-AWS environments, this uses the AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY environment variables.

• CloudWatch OTLP endpoint: The ADOT exports traces and logs to the CloudWatch native OTLP ingestion endpoint. The OTEL_EXPORTER_OTLP_LOGS_HEADERS header directs logs to the specific AgentCore log group, which is how CloudWatch indexes the data under the generative AI observability dashboard. For details on how the CloudWatch OTLP endpoint URL is determined and configured, see CloudWatch OTLP endpoint.

• Generative AI semantic conventions: The Strands [otel] package emits spans following the OpenTelemetry generative AI semantic conventions, including agent reasoning steps, tool invocations, and model calls with token usage.

The following diagram shows how telemetry export through ADOT auto-instrumentation works from non-AWS environments to CloudWatch.

Figure 3: Telemetry export through ADOT auto-instrumentation from non-AWS environments to CloudWatch

Walkthrough

Follow these steps to configure and run a Strands agent in a non-AWS environment, with telemetry routed to AgentCore Observability.

Step 1: Install dependencies

On your non-AWS environment (on-premises server, GCP VM, Azure VM, or a compute with internet access):

pip install "aws-opentelemetry-distro>=0.10.0" boto3 "strands-agents[otel]"

The aws-opentelemetry-distro package includes the ADOT auto-instrumentation with OTLP exporters specific to AWS and the aws_configurator that handles SigV4 authentication. The strands-agents[otel] package provides OpenTelemetry trace emission from the Strands framework.

Step 2: Configure AWS credentials

Set your IAM user credentials as environment variables.

export AWS_ACCESS_KEY_ID=
export AWS_SECRET_ACCESS_KEY=
export AWS_REGION=us-east-1

Security note**: For production deployments, consider using IAM Roles Anywhere instead of long-lived access keys. With IAM Roles Anywhere, on-premises workloads can obtain temporary credentials using X.509 certificates.

Step 3: Set OpenTelemetry environment variables

These environment variables configure the ADOT to route telemetry to the AgentCore Observability dashboard:

export AGENT_OBSERVABILITY_ENABLED=true
export OTEL_PYTHON_DISTRO=aws_distro
export OTEL_PYTHON_CONFIGURATOR=aws_configurator
export OTEL_RESOURCE_ATTRIBUTES="service.name=my-external-agent,aws.log.group.names=/aws/bedrock-agentcore/runtimes/my-external-agent"
export OTEL_EXPORTER_OTLP_LOGS_HEADERS="x-aws-log-group=/aws/bedrock-agentcore/runtimes/my-external-agent,x-aws-log-stream=runtime-logs,x-aws-metric-namespace=bedrock-agentcore"
export OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf
export OTEL_TRACES_EXPORTER=otlp

Key configuration details:

• AGENT_OBSERVABILITY_ENABLED=true activates generative AI-specific telemetry processing in the ADOT.

• OTEL_PYTHON_DISTRO=aws_distro and OTEL_PYTHON_CONFIGURATOR=aws_configurator activate the OpenTelemetry configuration specific to AWS, including SigV4 signing for the CloudWatch OTLP endpoint.

• OTEL_RESOURCE_ATTRIBUTES with aws.log.group.names tells CloudWatch to index the telemetry under the AgentCore Observability dashboard. Without this, traces go to generic Amazon CloudWatch Logs.

• OTEL_EXPORTER_OTLP_LOGS_HEADERS with x-aws-metric-namespace=bedrock-agentcore routes metrics in embedded metric format to the correct CloudWatch namespace.

Step 4: Create the agent application

Create a file named agent_test.py with a Strands agent:

from strands import Agent
from strands.models.bedrock import BedrockModel
from opentelemetry import baggage
from opentelemetry.context import attach
import time

# Configure the Bedrock model
model = BedrockModel(
    model_id="us.anthropic.claude-haiku-4-5-20251001-v1:0",
    region_name="us-east-1"
)
# Create the agent
agent = Agent(
    model=model,
    system_prompt="You are a helpful travel assistant."
)

# Set session ID for AgentCore session tracking
# All agent calls after attach() share same session ID for multiple requests/responses
session_id = f"external-session-{int(time.time())}"
ctx = baggage.set_baggage("session.id", session_id)
attach(ctx)

# Run the agent
response = agent("What are the top 3 things to do in Tokyo?")
print(response)

Step 5: Run with ADOT auto-instrumentation

The opentelemetry-instrument command wraps your Python process with the ADOT, automatically instrumenting Amazon Bedrock calls and Strands framework operations:

opentelemetry-instrument python3.12 agent_test.py

The agent’s response appears in the terminal. Behind the scenes, the ADOT captures traces, spans, and logs, and exports them to CloudWatch.

Step 6: Verify in AgentCore Observability

You see telemetry data within two to three minutes of execution. Open the Amazon CloudWatch console:

• Choose GenAI Observability, then Bedrock AgentCore.

• In the Agents tab, look for my-external-agent.

• Choose the agent to view sessions, traces, and span metrics.

The following screenshot shows the telemetry from the Strands agent (my-external-agent) running in a non-AWS environment, as seen in the AgentCore Observability dashboard in CloudWatch.

Figure 4: The my-external-agent telemetry in the AgentCore Observability dashboard

The console shows:

• Agent name: my-external-agent.

• Sessions: at least one session.

• Traces: trace spans showing the agent’s reasoning and Amazon Bedrock model invocations.

• Span details: invoke_agent, chat, execute_event_loop_cycle, and chat.us.anthropic.claude-haiku spans with latency and token metrics.

The following screenshot shows a successful trace from the Strands agent (my-external-agent) with four spans, model information, and latency and token details in the AgentCore Observability dashboard.

Figure 5: Trace detail for my-external-agent with span, latency, and token metrics

Validating from Google Cloud Platform

To confirm the solution works from a third-party cloud provider, we tested the same setup from Google Cloud Shell, a browser-based terminal running on GCP infrastructure.

Set up the environment on Google Cloud Shell:

# Create a virtual environment
python3.12 -m venv venv
source venv/bin/activate
# Install dependencies
pip install "aws-opentelemetry-distro" boto3 "strands-agents[otel]"
# Set AWS credentials
export AWS_ACCESS_KEY_ID=
export AWS_SECRET_ACCESS_KEY=
export AWS_REGION=us-east-1
# Set ADOT environment variables
export AGENT_OBSERVABILITY_ENABLED=true
export OTEL_PYTHON_DISTRO=aws_distro
export OTEL_PYTHON_CONFIGURATOR=aws_configurator
export OTEL_RESOURCE_ATTRIBUTES="service.name=gcp-hosted-agent,aws.log.group.names=/aws/bedrock-agentcore/runtimes/gcp-hosted-agent"
export OTEL_EXPORTER_OTLP_LOGS_HEADERS="x-aws-log-group=/aws/bedrock-agentcore/runtimes/gcp-hosted-agent,x-aws-log-stream=runtime-logs,x-aws-metric-namespace=bedrock-agentcore"
export OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf
export OTEL_TRACES_EXPORTER=otlp

Run the agent from GCP:

cat > agent_test.py << 'EOF'
from strands import Agent
from strands.models.bedrock import BedrockModel
from opentelemetry import baggage
from opentelemetry.context import attach
import time

model = BedrockModel(
    model_id="us.anthropic.claude-haiku-4-5-20251001-v1:0",
    region_name="us-east-1"
)
agent = Agent(model=model, system_prompt="You are a helpful assistant.")

# Set session ID for AgentCore session tracking
# All agent calls after attach() share same session ID for multiple requests/responses
session_id = f"gcp-session-{int(time.time())}"
ctx = baggage.set_baggage("session.id", session_id)
attach(ctx)

response = agent("What are the top 3 things to do in Paris?")
print(response)
EOF
opentelemetry-instrument python3.12 agent_test.py

The following screenshot shows the Strands agent (gcp-hosted-agent) running on Google Cloud Shell (GCP) and returning a successful response.

Figure 6: The gcp-hosted-agent running in Google Cloud Shell

Verify cross-cloud telemetry

Within two to three minutes of execution, the gcp-hosted-agent appears in the AgentCore Observability dashboard alongside agents running on AgentCore runtime or other environments.

The following screenshot shows a successful trace from the Strands agent (gcp-hosted-agent) running on GCP with four spans, model information, and latency and token details in the AgentCore Observability dashboard.