Uploaded February 2026 | Updated November 2026, 23 hours ago
Arize AX is the managed AI engineering platform for teams building and operating production AI agents and LLM applications. Evaluation is a core part of that workflow: defining what success looks like, measuring quality, finding failures, and validating improvements before they ship.
This workshop is an AI evaluation 101 primer for teams looking for practical, research-driven guidance on evaluating LLM applications and agents.
We cover:
• Evaluation fundamentals and how to choose the right evaluation approach
• Practical tradeoffs of LLM-as-a-Judge
• How and when to use code-based evaluators
• A concrete code evaluation example
• How evaluations connect with tracing, datasets, experiments, and other workflows in Arize AX
The workshop wraps with an Arize AX demo showing how evaluation fits into the broader AI engineering lifecycle.
Learn more:
Agent evaluation guide: arize.com/ai-agents/agent-evaluation
Arize AX: arize.com/products/ax
Arize AX docs: arize.com/docs/ax
Arize AX is the managed AI engineering platform for teams building and operating production AI agents and LLM applications. Evaluation is a core part of that workflow: defining what success looks like, measuring quality, finding failures, and validating improvements before they ship.
This workshop is an AI evaluation 101 primer for teams looking for practical, research-driven guidance on evaluating LLM applications and agents.
We cover:
• Evaluation fundamentals and how to choose the right evaluation approach
• Practical tradeoffs of LLM-as-a-Judge
• How and when to use code-based evaluators
• A concrete code evaluation example
• How evaluations connect with tracing, datasets, experiments, and other workflows in Arize AX
The workshop wraps with an Arize AX demo showing how evaluation fits into the broader AI engineering lifecycle.
Learn more:
Agent evaluation guide: arize.com/ai-agents/agent-evaluation
Arize AX: arize.com/products/ax
Arize AX docs: arize.com/docs/ax










