Is word error rate just a vanity metric?

An agent that gets better every day compounds into a very different agent within months. That's the idea behind Wren, PolyAI's new release: an agent whose job is to make your other agents better. Some of what it finds is a small refinement, some of it is a big fix. Either way, Wren watches every real customer conversation, learns from what happens, and keeps improving your customer-facing agents. Nikola Mrkšić sits down with Arkadiusz Kwapiszewski, Head of Agent OS, to get into what that changes, how Wren is putting agent-building in the hands of people who could never touch it before, and why 95% of PolyAI's own production changes now ship through it. Listen to the full episode, and learn more about PolyAI at https://poly.ai?utm_source=youtube&utm_medium=podcast&utm_campaign=podcast&utm_content=podcastFollow PolyAI on LinkedInWatch this and other episodes of the Deep Learning pod on YouTube

Companies are pouring money into AI, but not everyone is getting the returns. Ian Jacobs, VP and Lead Analyst at Opus Research, thinks he knows why. In this episode, your host Nikola Mrkšić sits down with Ian to work through two ideas from his latest research. The first is Conversation Experience Orchestration: the wall between conversational AI and conversation intelligence is coming down, and conversations are becoming the layer that decides what happens next. The second is the AI agent control plane: as enterprises get pitched agents by every vendor at once, they need a shared operating layer to keep them coordinated. Listen to the full episode, and learn more about dialog AI at https://poly.ai?utm_source=youtube&utm_medium=podcast&utm_campaign=podcast&utm_content=podcastFollow PolyAI on LinkedInWatch this and other episodes of the Deep Learning pod on YouTube

When PolyAI built its Builder MCP, one client helped shape it: Vixxo Facility Solutions, one of the largest facilities providers in the US. In this episode, guest host Damian Sasso talks with Vixxo's CTO Derek Neighbors and VP of IT Bobby Hunnicut about getting AI agents into the hands of people who've never written code, from accounting to technicians in the field. They cover why an MCP or CLI has become their litmus test for adopting any technology, how they build and ship their own MCPs as they go, why REST APIs are still the foundation, and how to stop governance debates from swallowing the whole conversation. See how PolyAI's Builder MCP works at https://poly.ai?utm_source=youtube&utm_medium=podcast&utm_campaign=podcast&utm_content=podcastFollow PolyAI on LinkedInWatch this and other episodes of the Deep Learning pod on YouTube

PolyAI just launched Dialog-RSN-1, its first audio-native model, and your host Nikola Mrkšić sat down with its builder, Matt Henderson, to unpack why it’s a game-changer for building voice agents. Most voice AI either flattens a call into a transcript and loses the audio, or goes fully speech-to-speech and gives up control of the voice. Dialog-RSN-1 does neither. It hears the raw audio directly, decides when to speak, and keeps text-to-speech separate so the voice stays under your control, all in under 300 milliseconds. Nikola and Matt get into what audio-native really means, how auto-reasoning keeps it fast, and why it beats every other real-time model on quality and quickness. Hear the full episode, and see how PolyAI builds dialog agents that hear the whole call at https://poly.ai?utm_source=youtube&utm_medium=podcast&utm_campaign=podcast&utm_content=podcastFollow PolyAI on LinkedInWatch this and other episodes of the Deep Learning pod on YouTube

Voice AI vendors love to quote word error rate, usually somewhere around 2 to 3%, as proof their system understands customers. Oliver Shoulson, Agent Design & Engineering Lead at PolyAI, thinks it's one of the most misleading numbers in the business. He and Nikola Mrkšić go through a month of analysis across more than 100,000 real production call turns to explain why. Turns out not all words carry the same weight, most transcription errors are harmless, and task success barely moves even when the system mishears, because today's models recover the way a person would. Listen to the full episode, and see how PolyAI builds dialog agents that get this right at https://poly.ai?utm_source=youtube&utm_medium=podcast&utm_campaign=podcast&utm_content=podcastFollow PolyAI on LinkedInWatch this and other episodes of the Deep Learning pod on YouTube

Engineering teams are shrinking. But is that a crisis or an upgrade?In this episode of Deep Learning with PolyAI, Nikola Mrkšić sits down with Helen Greul, PolyAI's new SVP of Engineering, to explore what AI is doing to the shape of technical teams, the nature of engineering leadership, and who actually thrives when the rules change.They discuss why a new generation of non-traditional builders is outpacing seasoned development teams, how smaller nimble units with shared context are replacing large headcounts, and why complexity doesn't disappear when AI arrives: it just moves somewhere else.Follow PolyAI on LinkedInWatch this and other episodes of the Deep Learning pod on YouTube

Ten minutes to a working AI agent, tested and ready to deploy.In this episode of Deep Learning with PolyAI, Frank Ferro sits down with Ruari Phipps, Senior Forward Deployed AI Engineer at PolyAI, for a live demo of the Agent Development Kit — and a look at what it actually means to give developers real control over how they build AI agents.They explore why enterprise AI platforms so often force a tradeoff between speed and control, how the ADK changes that equation, and what it looks like when a developer pairs the toolkit with an AI coding agent like Claude Code to go from a blank canvas to a fully tested, branch-ready agent in real time.Follow PolyAI on LinkedInWatch this and other episodes of the Deep Learning pod on YouTube

What happens when the ability to build an AI agent is no longer limited to developers?In this episode of Deep Learning with PolyAI, Nikola Mrkšić sits down with Michael Chen, VP of Strategic Alliances at PolyAI, to explore what's driving the explosion in AI agent development — and what it means for how enterprises build, deploy, and think about AI.They cover the rise of personal AI agents, why Jensen Huang's $1 trillion data center bet might Follow PolyAI on LinkedInWatch this and other episodes of the Deep Learning pod on YouTube

Many AI models today are designed as generalists. But in customer experience, that approach often falls short.In this episode of Deep Learning with PolyAI, Nikola Mrkšić sits down with Matt Henderson, VP of Research at PolyAI, to unpack why specialized AI models outperform general-purpose ones in real-world CX environments.They explore the tradeoffs between speed, accuracy, and reasoning, why voice AI requires fundamentally different design decisions, and what makes PolyAI’s Raven 3.5 a step forward. The conversation offers a behind-the-scenes look at what it actually takes to build AI that works in production, not just in demos.Follow PolyAI on LinkedInWatch this and other episodes of the Deep Learning pod on YouTube

In this episode of Deep Learning with PolyAI, Nikola Mrkšić sits down with Bill Staikos, Founder of Be Customer Led, to unpack why many CX leaders are still on the sidelines of the AI conversation — and what that means for the future of the function.They explore how AI is reshaping the “interaction layer” of customer experience, why traditional CX metrics like NPS are no longer enough, and how leading organizations are starting to tie CX directly to revenue, cost, and risk.The conversation challenges CX leaders to think bigger and make their function into an outcome-driven engine for business growth. In an AI-driven world, the leaders who understand that shift will have a much bigger role to play.Follow PolyAI on LinkedInWatch this and other episodes of the Deep Learning pod on YouTube