Get started with OpenLLMetry and AI Observability.

• Latest Dynatrace
• Getting started guide
• 4-min read
• Updated on Feb 25, 2026

OpenLLMetry captures and transmits AI model or agent KPIs to the Dynatrace environment, empowering businesses with unparalleled insights into their AI deployment landscape.

The collected data seamlessly integrates with the Dynatrace environment, so users can analyze LLM metrics, spans, and logs in the context of all traces and code-level information.

Who is this for?

This getting started guide is for:

What will you learn?

By following this guide, you'll learn:

Before you begin

In order for this to work, you need to have:

Prior knowledge

It's helpful to have some basic knowledge of:

About OpenLLMetry and AI observability

OpenLLMetry supports AI model observability by capturing and normalizing key performance indicators (KPIs) from diverse AI frameworks. Utilizing an additional OpenTelemetry SDK layer, this data seamlessly flows into the Dynatrace environment, offering advanced analytics and a holistic view of the AI deployment stack.

OpenTelemetry's auto-instrumentation provides valuable insights into spans and basic resource attributes. However, it doesn't capture specific KPIs crucial for AI models, such as model name, version, prompt and completion tokens, and temperature parameter.

OpenLLMetry bridges this gap by supporting popular AI frameworks like OpenAI, HuggingFace, Pinecone, and LangChain. By standardizing the collection of essential model KPIs through OpenTelemetry, it ensures comprehensive observability. The open-source OpenLLMetry SDK, built on top of OpenTelemetry, enables thorough insights into your LLM application.

Get started with OpenLLMetry and Dynatrace

In this example, we demonstrate the implementation of a customizable LLM using OpenAI's cloud service and the LangChain framework. This compact example showcases the integration of LangChain to construct a template layer for the LLM model.

Once you've configured your application, you can use Dynatrace to:

import os
import openai
from langchain.llms import OpenAI
from langchain.chat_models import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
from traceloop.sdk import Traceloop
from traceloop.sdk.decorators import workflow, task

os.environ['OTEL_EXPORTER_OTLP_METRICS_TEMPORALITY_PREFERENCE'] = "delta"

headers = { "Authorization": "Api-Token <YOUR_DT_API_TOKEN>" }
Traceloop.init(
    app_name="<your-service>",
    api_endpoint="https://<YOUR_ENV>.live.dynatrace.com/api/v2/otlp",
    headers=headers,
    disable_batch=True
)

openai.api_key = os.getenv("OPENAI_API_KEY")

@task(name="add_prompt_context")
def add_prompt_context():
    prompt = ChatPromptTemplate.from_template("explain the business of company {company} in a max of {length} words")
    model = ChatOpenAI()
    chain = prompt | model
    return chain

@task(name="prep_prompt_chain")
def prep_prompt_chain():
    return add_prompt_context()

@workflow(name="ask_question")
def prompt_question():
    chain = prep_prompt_chain()
    return chain.invoke({"company": "dynatrace", "length" : 50})

if  __name__ == "__main__":
    print(prompt_question())

> python chaining.py

Traceloop exporting traces to https://<MY_ENV>.live.dynatrace.com/api/v2/otlp,  /
          authenticating with custom headers content='Dynatrace is a software   /
          intelligence company that provides monitoring and analytics solutions /
          for modern cloud environments. They offer a platform that helps       /
          businesses optimize their software performance, improve customer      /
          experience, and accelerate digital transformation by leveraging       /
          AI-driven insights and automation.'

Congratulations!

Now that you've set up your AI app to send observability data directly to Dynatrace, you can: