Quality tab overview

The Quality tab gives you automated quality scoring and runtime safeguards for every specialized agent run. Define your quality criteria, score each execution against them, and recover or block runs that deviate from expected behavior.

The Quality tab has the following two sub-tabs:

Output Evaluation – Scores every run against criteria, examples, and a baseline evaluation score you define. See Configure Output Evaluation.
Execution Guardrails – Detects runs that deviate from your agent's normal behavior. See Configure Execution Guardrails.

Screenshot of the Quality tab with the two sub-tabs, Output Evaluation and Execution Guardrails highlighted.

A third feature, Execution Advisor, intervenes during runs to handle anomalies, retry failed tool calls, and review sensitive tool calls. Execution Advisor does not have its own configuration screen. It runs automatically based on what Output Evaluation and Execution Guardrails detect. See Execution Advisor.

The execution details display two independent verdicts for each run. Output Evaluation calculates the Evaluation Score. Execution Guardrails calculate the Guardrail Status. A run sometimes passes one and fails the other.

When to use each feature

Each Quality tab feature targets a different aspect of agent quality. Use the following list to choose the right feature for your goal.

Output Evaluation – Score every run against quality criteria you define.
Execution Guardrails – Stop runs that behave unlike a normal run for the agent.
Execution Advisor – Recover flagged runs and gate sensitive tool calls automatically.

Output Evaluation and Execution Guardrails work independently. Many agents start with Output Evaluation only, then add Execution Guardrails when they have established a stable behavior baseline.