What does it take to make a voice AI agent reliable?

Picture of Kane Simms
Kane Simms
  • CEO & Founder

Reliable voice AI comes from rigorous testing and evals, and Rohan Vasishth from Bluejay sees trust as the fundamental bottleneck holding back enterprise deployment.

More ways to listen and watch

About this episode

Rohan is Co-founder and CEO of Bluejay, which tests and monitors voice and chat AI agents for companies including Google and DoorDash. We work through what to test, when to test it and what each approach costs.

We discuss why testing voice AI introduces a whole new layer of complexity, from accents and background noise to interruptions and speech recognition errors. Rohan also shares how customers can stress-test agents, why starting with text-based evaluations can save time and money, and how businesses can identify and reduce the latency customers actually experience.

Rohan closes by exploring the widening gap between rapidly advancing AI capabilities and slower enterprise deployment, and why evaluation is essential to building the trust needed to close it.

Show notes

Article: How to Reduce Latency in Your Voice Agent Pipeline⁠

Article: Introducing Bluejay Labs and MIVAS

Guest

Rohan Vasishth

CEO & Co-Founder of Bluejay

Rohan Vasishth is Co-founder and CEO of Bluejay, a platform that tests, monitors and improves voice and chat AI agents. Before Bluejay, he worked on AWS Bedrock and studied computer science and economics at the University of Chicago. Rohan started out building voice agents for restaurants, and the hours spent manually calling those agents to test them led to Bluejay, a Y Combinator-backed company that uses simulated callers to stress-test agents before they reach real customers.

Share

Link

Weekly newsletter

The latest in AI-powered customer experience. Make better strategic decisions with the help of our weekly newsletter.

Host

Kane Simms

A strategic AI advisor who, for the past decade, has helped business leaders and product owners transform customer experience using conversational and generative AI.

Follow

Share

✓   Link copied
Link

Weekly newsletter

The latest in AI-powered customer experience. Make better strategic decisions with the help of our weekly newsletter.

Top articles and podcasts

What is SSML (Speech Synthesis Markup Language)? A beginner’s guide
  • •    14 min Read
Our deep analysis of the Gartner Magic Quadrant for Conversational AI Platforms 2026
  • •    11 min Read
How to build reliable AI agents: Test Driven Development is back!
  • •    7 min Read
The two things contact centres have been missing until now
From chatbot to voice AI: what changes?

Latest articles and podcasts

Related content

More articles
What does a good AI agent testing approach look like?
When is an AI agent ready to go live? Discover how development testing, stress testing and clear pass/fail criteria help build confidence before deployment.
AI agent testing: where are we now?
AI agent testing is evolving rapidly. Explore the growing market of evaluation, automated testing, observability and security tools, and why tools alone aren't enough.
Keeping control of your AI agents
Zammo's Stacey Kyler and Guy Tonye on the move from diagram flows to agentic systems, and why customers now want both the freedom of Gen AI and firm control.
The best AI use cases are right in front of your eyes

Loading the Elevenlabs Text to Speech AudioNative Player… CCW published a report recently that asked contact centre leaders how much impact AI has had on

Meet VUX at CCW Europe, Amsterdam, October 5-7

Register now

Register now: Why your contact centre playbook is obsolete

Save your spot