LLM Observability Certification

From text classification to code generation, there’s a huge demand for large language models to be deployed in a variety of industries. But as use cases for LLM applications rapidly expand, so does the importance of having visibility into every layer of the LLM system. These workflows can be very complex, requiring continuous improvement for better performance and a better end-user experience. Our self-paced LLM observability course is designed to give AI engineers, data scientists, and developers the confidence to run a reliable LLM app. Through pre-recorded instructor videos, code along exercises, checkpoint questions and unit labs, you’ll gain a hands-on understanding of every part of an LLM system. LLM observability is a key tool for building trust, improving model reliability, and responsibly deploying language models across many different use cases.

Enroll now
LLM University

Arize University Courses

LLM Badge-Agents
Agents, Tools, and Chains
Enroll now →
LLM Badge-Evaluations
Evaluations
Enroll now →
LLM Badge-Traces
Traces & Spans
Enroll now →

Course Curriculum

LLM Observability Agents, Tools, and Chains

This course covers common simple and complex agent architectures, as well as when and how to implement an agent into your LLM system. Upon completion of this course you will gain an understanding of how to implement a specialized agent for your use case.

Video icon

Course video (22 minutes)

Quiz

Quiz (10 minutes)

Lab

Lab (7 minutes)

Enroll now →
LLM Observability Evaluations

The LLM evaluation metrics course teaches how implementing LLM evaluations provide scalability, flexibility, and consistency for your LLM orchestration framework. Upon completion of this course you will gain understanding of how to implement LLM observability for your application.

Video icon

Course video (26 minutes)

Quiz

Quiz (10 minutes)

Lab

Lab (6 minutes)

Enroll now →
LLM Observability Traces & Spans

This course covers span types and how to view traces from a LLM callback system. Upon completion of this course you will gain a hands-on understanding of how to utilize spans and traces in a variety of language use cases.

Video icon

Course video (16 minutes)

Quiz

Quiz (10 minutes)

Lab

Lab (6 minutes)

Enroll now →

Skills you will learn

Retrieval Augmented Generation
Prompt Engineering and Templates
Traces and Spans for LLM calls
LLM Evaluation Metrics
Model Evals vs. System Evals
Agent and Tool Architectures

Technical requirements

Python version
OS

Earn your certificate in only a few hours

Enroll now
LLM Certificate

Completion requirements

Upon completing all units of the LLM Observability Curriculum, you will receive a Certificate of Completion to highlight your new skillset. Completing the lab and passing the quiz are required to receive each Certificate of Completion.

Join the Arize LLM Observability Course

Enroll for free