Discover

G-Eval scores generated text with an LLM judge, no reference answer needed. How it works, what its correlation figures mean, and where the method breaks.

A human evaluator scores AI output that automated metrics cannot judge. What they measure, how much they agree with each other, and when to automate instead.

LLM testing checks model behaviour, not just code. Learn the five test layers, deterministic vs model-graded checks, and how to run an LLM test suite in CI.

Bland AI ships Testbed, Standards, Scenarios and Evals natively. Cekura adds a native Bland AI provider that places outbound test calls, scores delivered audio, and auto-fetches production calls every 30 seconds.

ConversationRelay splits your agent across a WebSocket, so no single tool sees the whole call. Compare Conversation Relay Insights, Conversation Intelligence, server unit tests and Cekura on what each one automates.

PolyAI ships native testing through its Agent Development Kit, and Cekura tests the same agent independently over SIP or a phone number. Together they cover scenario simulation, function-calling accuracy, telephony, and red-teaming.

How to test voice AI agents for telecom: SIP signaling, narrowband G.711 audio, ITU-T G.114 latency budgets, DTMF, and concurrent call load, with Cekura Bench's infrastructure-reliability data and its provider-selection caveat.

AI voice agent compliance explained: the 2024 FCC ruling, the TCPA and state duties binding outbound calls, and how to test your agent before it dials.

Call center quality assurance software compared: scoring, calibration, compliance, and how QA changes for AI agents. Includes a 12-point buyer checklist.

Export voice bot analytics data three ways: a CSV download from the Calls page, an API pull you schedule, and a webhook that pushes each completed call.

What p99 latency means for voice AI agents, how p50, p90 and TTFT differ, and why tail latency decides if callers talk over your bot. See the benchmark data.

Post dial delay explained: what PDD measures in SIP, the seven second carrier standard, why it stays invisible to voice AI metrics, and how to test for it.