Accuracy
Checks that the agent captured and confirmed information correctly.Actions & tools
Validates that tools and workflows were invoked correctly.Conversation quality
Measures how well the agent communicates throughout the call.Safety & compliance
Ensures the agent stays within required guardrails.Adding them to your agent
Pick from the library
Open the evals panel, browse by category, and add any predefined eval with one click. Each ships with a prompt optimized on real voice AI use cases.
Optimized AI judges
Every predefined eval is backed by a judge tuned on patterns from actual deployments — not generic LLM prompts. Fewer false positives, scores you can act on.
Write your own
Have a behavior specific to your use case? Describe it in plain language and Tuner runs it as a first-class judge alongside these.
Predefined evals run on every production call and every simulated call — the same criteria score both.
Next steps
Agents with Dynamic Instructions
How to use call to evaluate dynamic agents.
Red flags and labels
Turn eval results into tags you can filter and alert on.