Free learning series
Agent Evaluation Fundamentals
Learn how to observe an agent, turn reviewed failures into eval definitions, and understand what a separate runner would need to test next. Perseval itself stops before execution.
Five scenarios, one evidence boundary
The lessons use concrete failure shapes, including the published sanitized timeout, optional-recovery, SpanLink-handoff, missing-telemetry, and baseline/repaired scenarios.
Agent run
→ OpenTelemetry trace
→ evidence-backed finding
→ reviewed eval definition
│ Perseval stops here
→ external or future runner
→ new result and gradeChapter 1
Observe the agent
Learn what traces record, how observability differs from logging, and where OpenTelemetry fits.
- 01 What Is an AI Agent Trace? A trace records how an agent reached an answer, including model calls, tool use, handoffs, retries, and verification.
- 02 What Is Agent Observability? Agent observability connects individual executions to recurring behavior, evidence, and changes across builds.
- 03 What Is OpenTelemetry for AI Agents? OpenTelemetry provides a vendor-neutral way to create, transport, and interpret telemetry from agent runs.
- 04 Logs, Traces, and Evals: What Is the Difference? Logs record events, traces connect an execution, and evals test behavior against an explicit expectation.
Chapter 2
Define useful evals
Separate cases, suites, runners, graders, and results so each part has one clear job.
- 05 What Is an Agent Eval? An agent eval is a repeatable test that combines an input, expected behavior, execution evidence, and a grader.
- 06 Offline, Online, and Shadow Agent Evals Offline evals test controlled cases, online evals judge production behavior, and shadow evals observe a candidate without affecting users.
- 07 Eval Definitions, Cases, Suites, Runs, and Results A precise vocabulary makes agent evaluation reproducible and prevents a test definition from being confused with its execution.
- 08 What Is an Eval Runner? An eval runner invokes the agent for each case, captures the result and trace, and hands that evidence to graders.
- 09 Deterministic Graders vs LLM Judges Use deterministic checks for facts you can state precisely, and LLM judges for bounded semantic questions that preserve evidence and uncertainty.
- 10 What Is LLM-as-a-Judge? LLM-as-a-judge uses a language model to evaluate an agent result against a rubric, with evidence, uncertainty, and provenance kept explicit.
- 11 Ground Truth and Calibration for Agent Evals Ground truth records the best supported label for a case, while calibration measures whether graders and confidence estimates deserve trust.
Chapter 3
Rerun and replay
Understand regrading, re-execution, black-box testing, gray-box runs, and controlled replay.
- 12 Replay, Re-execution, and Regrading Are Not the Same Regrading reuses evidence, re-execution invokes the agent again, and controlled replay fixes selected dependencies.
- 13 Black-Box, Gray-Box, and White-Box Agent Testing The three modes differ by how much of the agent execution and its dependencies the evaluation system can observe or control.
- 14 What Is White-Box Replay for AI Agents? White-box replay reruns agent logic while controlling recorded model, tool, time, or state dependencies.
- 15 How to Compare Two Agent Runs A useful comparison preserves both run identities, aligns equivalent work, and highlights the first meaningful divergence.
Chapter 4
Define the next regression test
Turn real failures into representative, reviewable definitions without pretending they already ran.
- 16 How to Turn Production Agent Failures Into Regression Evals A practical workflow for moving from recurring trace evidence to a reviewed eval definition, with the execution boundary kept explicit.
- 17 Why One Failed Trace Is Not an Eval A failed trace is evidence from one execution. An eval requires a representative case, expected behavior, and a repeatable way to judge new runs.
- 18 From First Failure to First Eval Definition Follow a sanitized mutating timeout from trace evidence through human review to an accepted eval definition—the point where Perseval stops today.