Strands Agents

Splunk Agent Observability supports logging traces from Strands Agents SDK applications using OpenTelemetry.

Set up OpenTelemetry

To log Strands Agents using Splunk Agent Observability, the first step is to set up OpenTelemetry.

Installation

Add the OpenTelemetry packages to your project:

pip install opentelemetry-api opentelemetry-sdk \
            opentelemetry-exporter-otlp

The opentelemetry-api and opentelemetry-sdk packages provide the core OpenTelemetry functionality. The opentelemetry-exporter-otlp package enables sending traces to Splunk Agent Observability’s OTLP endpoint.

Create environment variables for your Splunk Agent Observability settings

Set environment variables for your Splunk Agent Observability settings, for example in a .env file. These environment variables are consumed by the SplunkAOSpanProcessorto authenticate and route traces to the correct Splunk Agent Observability Project and Agent Stream:

# Provide your Splunk Agent Observability
# API key and URL if you are using an
# on-premises, standalone, or custom deployment
# SPLUNK_AO_API_KEY="your-splunk-ao-api-key"
# SPLUNK_AO_CONSOLE_URL="your-splunk-ao-url"

# Your Splunk Agent Observability project name
SPLUNK_AO_PROJECT="your-splunk-ao-project-name"

# The name of the Agent Stream you want to use for logging
SPLUNK_AO_AGENT_STREAM="your-splunk-ao-agent-stream"

Self hosted deployments: Set the OTel endpoint

Skip this step if you are using a hosted version.

The OTel endpoint is different from Splunk Agent Observability’s regular API endpoint and is specifically designed to receive telemetry data in the OTLP format.If you are using:

A cloud deployment, then you don’t need to provide a custom OTel endpoint. The default endpoint <your-splunk-ao-api-url>/otel/traces will be used automatically.
A self-hosted deployment, replace the <your-splunk-ao-api-url>/otel/traces endpoint with your deployment URL. The format of this URL is based on your console URL, appending /otel/traces.

The convention is to store this in the SPLUNK_AO_CONSOLE_URL environment variable. For example:

os.environ["SPLUNK_AO_CONSOLE_URL"] = "<your-splunk-ao-url>"

Initialize and create the Splunk Agent Observability span processor

The SplunkAOSpanProcessor automatically configures authentication and metadata using your environment variables. It also:

Auto-builds OTLP headers using your Splunk Agent Observability credentials
Configures the correct OTLP trace endpoint
Registers a batch span processor that exports traces to Splunk Agent Observability

from splunk_ao import otel  

# SplunkAOSpanProcessor (no manual OTLP config required) loads the env vars for 
# the Splunk Agent Observability API key, Project, and Agent Stream. Make sure to set them first. 
splunk_ao_span_processor = otel.SplunkAOSpanProcessor(
    # Optional parameters if not set, uses env var
    # project=os.environ["SPLUNK_AO_PROJECT"], 
    # agentstream=os.environ.get("SPLUNK_AO_AGENT_STREAM"),  
)

Log a Strands ADK agent using OpenTelemetry

Once OpenTelemetry is configured, you can use the OTel capabilities of Strands to log traces.

Import the Strands Agent telemetry package

The Strands Agents SDK has telemetry support out of the box. Start by importing StrandsTelemetry with the following code:

from strands.telemetry import StrandsTelemetry

Set up the exporter

You can now set up an OTel exporter for your Strands Agent:

strands_telemetry = StrandsTelemetry()
strands_telemetry.setup_otlp_exporter()

When you run your Strands Agent code, traces will be logged to Splunk Agent Observability.

Opt in to experimental OpenTelemetry semantic conventions

Starting in strands-agents v1.34.0, the Strands Agents SDK can emit generative AI traces using either the legacy OpenTelemetry semantic conventions or the newer experimental conventions:

Legacy mode (default) — uses attributes such as gen_ai.system along with legacy event shapes.
Experimental mode — follows the latest OpenTelemetry generative AI semantic conventions, using gen_ai.provider.name and structured gen_ai.client.inference.operation.details events that carry inputs, outputs, and system instructions.

Splunk Agent Observability automatically detects and maps both modes, so traces from either mode will appear in your Splunk Agent Observability Agent Stream without any changes to your Splunk Agent Observability setup. If you want to opt in to the experimental conventions, set the following environment variable before your Strands Agent starts:

OTEL_SEMCONV_STABILITY_OPT_IN=gen_ai_latest_experimental

OTEL_SEMCONV_STABILITY_OPT_IN is read by the Strands Agents SDK at startup. Make sure it is exported in your process environment (or loaded from your .env file) before StrandsTelemetry is initialized.

Full example

Here is a full example based off the Strands Agent quickstart. You can find this project in the Splunk Agent Observability SDK examples repo. To run this example, create a .env file with the following values set, or set them as environment variables:

.env

# AWS environment variables
AWS_BEARER_TOKEN_BEDROCK=your-aws-bedrock-token

# Splunk Agent Observability environment variables
SPLUNK_AO_API_ENDPOINT=your-splunk-ao-otel-api-endpoint
SPLUNK_AO_PROJECT=your-splunk-ao-project
SPLUNK_AO_AGENT_STREAM=your-agent-stream
# Only required for on-premises, standalone, or custom deployments
# SPLUNK_AO_API_KEY=your-splunk-ao-api-key

Remember to update these to match your Splunk Agent Observability API key, AWS Bedrock token, Splunk Agent Observability OTel endpoint, project name, and Agent Stream name.

import os

from strands import Agent, tool
from strands.telemetry import StrandsTelemetry
from strands_tools import calculator, current_time

# Load environment variables from the .env file
from dotenv import load_dotenv
load_dotenv(override=True)

# Export the Splunk Agent Observability OTel API endpoint for OTel
os.environ["OTEL_EXPORTER_OTLP_TRACES_ENDPOINT"] = os.environ.get(
    "SPLUNK_AO_API_ENDPOINT", 
    "<your-splunk-ao-api-url>/otel/traces"
)

# Export the Splunk Agent Observability OTel headers pointing to the correct API key,
# project, and Agent Stream
headers = {
    # Only required for on-premises, standalone, and custom deployments
    # "Splunk-AO-API-Key": os.environ["SPLUNK_AO_API_KEY"],
    "project": os.environ["SPLUNK_AO_PROJECT"],
    "agentstream": os.environ["SPLUNK_AO_AGENT_STREAM"],
}

os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = ",".join(
    [f"{k}={v}" for k, v in headers.items()]
)

# Setup telemetry for the Strands agent using Splunk Agent Observability as the OTel backend
strands_telemetry = StrandsTelemetry()
strands_telemetry.setup_otlp_exporter()

# Define a custom tool as a Python function using the @tool decorator
@tool
def letter_counter(word: str, letter: str) -> int:
    """
    Count occurrences of a specific letter in a word.

    Args:
        word (str): The input word to search in
        letter (str): The specific letter to count

    Returns:
        int: The number of occurrences of the letter in the word
    """
    if not isinstance(word, str) or not isinstance(letter, str):
        return 0

    if len(letter) != 1:
        raise ValueError("The 'letter' parameter must be a single char")

    return word.lower().count(letter.lower())


# Create an agent with tools from the community-driven strands-tools
# package as well as our custom letter_counter tool
agent = Agent(tools=[calculator, current_time, letter_counter])

# Ask the agent a question that uses the available tools
message = """
I have 4 requests:

1. What is the time right now?
2. Calculate 3111696 / 74088
3. Tell me how many letter R's are in the word "strawberry" 🍓
"""
agent(message)

Overview

Get Started

Observability

Evaluators

Signals

AI Assistant

Luna Studio

Experiments

Agent Control

Annotations

Integrations

Security

References

Set up OpenTelemetry

Log a Strands ADK agent using OpenTelemetry

Opt in to experimental OpenTelemetry semantic conventions

Full example

​Set up OpenTelemetry

​Log a Strands ADK agent using OpenTelemetry

​Opt in to experimental OpenTelemetry semantic conventions

​Full example

Set up OpenTelemetry

Log a Strands ADK agent using OpenTelemetry

Opt in to experimental OpenTelemetry semantic conventions

Full example