Evalgent

Blog

Page 28 of 59

Voice Agent Call Duration Limits: What Gets Cut Off and How to Test It
Voice AI Testing
15 min read

Voice Agent Call Duration Limits: What Gets Cut Off and How to Test It

Documented duration and silence timeouts on Vapi, Retell, ElevenLabs, Twilio, LiveKit and OpenAI, what callers hear at the cut-off, and how to test it.

November 18, 2026Read more
Voice Agent Echo: Why Your Agent Hears Itself and How to Test for It
Voice AI Testing
15 min read

Voice Agent Echo: Why Your Agent Hears Itself and How to Test for It

Why a voice agent hears itself: echo, self-barge-in and feedback loops, how they show up on calls, and a silent-caller test plan for devices and telephony.

November 18, 2026Read more
AI Disclosure for Voice Agents: EU Article 50, California, Utah and How to Test It
Voice AI Testing
15 min read

AI Disclosure for Voice Agents: EU Article 50, California, Utah and How to Test It

What EU AI Act Article 50, California's BOT Act and Utah's law require when a voice agent talks to a person, and how to test the disclosure is spoken.

November 18, 2026Read more
Voice Agent Test Cases vs Assertions: What Each Is, Examples, and How to Version Them
Voice AI Testing
19 min read

Voice Agent Test Cases vs Assertions: What Each Is, Examples, and How to Version Them

Voice agent test cases vs assertions: clear definitions, a worked example, assertion types, pass^k, production monitors and a repo layout for versioning.

Updated November 18, 2026Read more
Voice Agent PII Redaction: Detecting Leaks in Spoken Readbacks, Transcripts and Logs
Voice AI Testing
23 min read

Voice Agent PII Redaction: Detecting Leaks in Spoken Readbacks, Transcripts and Logs

Where voice agents leak card numbers and SSNs: readbacks, STT, LLM logs, recordings, traces. Redaction failure modes, detection code, seeded test plan.

Updated November 18, 2026Read more
Answering Machine Detection for Outbound Voice Agents in LiveKit and Pipecat (and How to Measure It)
Voice AI Testing
25 min read

Answering Machine Detection for Outbound Voice Agents in LiveKit and Pipecat (and How to Measure It)

How AMD works in LiveKit, Pipecat and Twilio, what each error costs per 10k dials, how to time voicemail drops, and how to measure false hang-ups.

Updated November 18, 2026Read more
AI Receptionist for Home Inspectors: What It Must Handle and How to Test It
Voice AI Testing
15 min read

AI Receptionist for Home Inspectors: What It Must Handle and How to Test It

An AI receptionist for home inspectors must book by property type, serve realtors, handle add-ons and never invent prices. Test it first; vendor questions.

November 17, 2026Read more
What Is a Good Escalation Rate for an AI Voice Agent?
Voice AI Testing
13 min read

What Is a Good Escalation Rate for an AI Voice Agent?

No verified universal escalation rate exists. Set a range from your call mix, split required from avoidable handoffs, and see why a low rate traps callers.

November 17, 2026Read more
Cartesia Alternatives for Voice Agents: How to Compare TTS on Your Own Calls
Voice AI Testing
15 min read

Cartesia Alternatives for Voice Agents: How to Compare TTS on Your Own Calls

Cartesia alternatives for voice agents, with vendor facts as of Nov 17, 2026 and a method to compare TTS on your own calls instead of demo clips.

November 17, 2026Read more