AI engineering glossary · Agents tools MCP
What is agent evaluation?
Agent evaluation (also called Agent evals): Measuring how well an agent performs, looking at whether it reached the goal, whether its steps and tool choices were sensible, and its cost and speed. It is harder than testing a single answer because runs differ from one execution to the next.
Agent evaluation: an example
A test set of 100 support tasks reports a 78% task success rate and an average of 6 tool calls per task.
Related terms
More Agents tools MCP terms
- Agent handoff
- Agent loop
- Agent memory
- Agent observability
- Agent skills
- Agent trace
- Agent-to-agent protocol
- Agentic workflow
Where you learn it
Agent evaluation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.