VUX World

What does it really take to build AI that can resolve customer support at scale reliably, safely, and with measurable business impact? We explore how Intercom has evolved from a traditional customer support platform into an AI-first company, with its AI assistant, Fin, now resolving 65% of customer queries without human intervention. Intercom's Chief AI Officer, Fergal Reid, discusses the company's journey from natural language understanding (NLU) systems to their current retrieval augmented generation (RAG) approach, explaining how they've optimised every component of their AI pipeline with custom-built models. The conversation covers Intercom's unique approach to AI product development, emphasising standardisation and continuous improvement rather than customisation for individual clients. Fergal explains their outcome-based pricing model, where clients pay for successful resolutions rather than conversations, and how this aligns incentives across the business. We also discuss Intercom's approach to agentic AI, which enables their systems to perform complex, multi-step tasks, such as processing refunds, by integrating with various APIs. Fergal shares insights on testing methodologies, the balance between customisation and standardisation, and the challenges of building AI products in a rapidly evolving technological landscape. Finally, Fergal shares what excites and honestly freaks him out a bit about where AI is heading next. Timestamps 00:00 - Intro 02:31 - Welcome to Fergal Reid 05:26 - How to train an NLU solution effectively? 08:56 - What gen AI changed for Intercom 10:57 - How would you describe Fin? 14:30 - Fin’s performance increase 17:18 - Inrercom’s custom models 22:14 - Large Language Models vs Small Language Models 30:40 - RAG and 'the full stop problem' 40:08 - Agentic AI capabilities at Intercom 50:40 - Intercom’s approach to testing 1:04:46 - About the most exciting things in the AI space Show notes Learn more about Intercom Connect with Fergal Reid on LinkedIn Follow Kane Simms on LinkedIn Article - The full stop problem: RAG’s biggest limitation Take our updated AI Maturity Assessment Subscribe to VUX World Subscribe to The AI Ultimatum Substack Hosted on Acast. See acast.com/privacy for more information.

In this episode, Joe Kim, the new CEO of DRUID AI, unpacks what might be the biggest shift in technology since the internet. We discuss the evolving landscape of artificial intelligence and its growing impact on businesses. Joe, who has been in his role for 70 days, brings fresh perspectives on how DRUID AI positioned itself as a workflow automation platform years before the market caught up, a bet that's now paying off as companies move beyond AI experimentation into real implementation. The discussion covers the current state of the AI market, including the challenges of customer adoption, why some customers actively prefer interacting with AI over humans, and the importance of maintaining a balance between generative and agentic AI. Joe also shares his vision of AI as the next major distribution platform. Just as Amazon has tried to make Alexa the operating system of our lives, OpenAI’s ChatGPT and similar platforms could become the primary gateway to accessing services in the future. Chapters 00:00 - Meet Joe Kim 00:33 - Celebrating 70 days at DRUID AI 01:35 - What attracted Joe to DRUID 03:06 - The real value of AI 06:43 - What Joe learnt about the market 11:19 - The AI God Box for enterprises 14:08 - The state of the AI market 20:29 - Why you should learn about AI as much as you can 23:47 - Generative AI adoption among enterprises 27:36 - The concept of agent washing 36:05 - Is AI bigger than the internet? 39:11 - ChatGPT as the new distribution platform 48:52 - Will chatbots replace websites and apps? 50:31 - The next 6–12 months for DRUID AI 56:59 - The biggest AI ultimatum facing businesses today 1:01:29 - AI replacing people is not growth 1:05:33 - The systems of record at enterprises and LLMs 1:08:46 - The future of AI automation 1:14:13 - LLMs could replace apps Show notes Find out more about DRUID AI Follow Joe Kim on LinkedIn Sign up for our webinar: How to run AI like your business depends on it Follow Kane Simms on LinkedIn Take our updated AI Maturity Assessment Subscribe to VUX World Subscribe to The AI Ultimatum Substack Hosted on Acast. See acast.com/privacy for more information.

Everyone's slapping 'agentic' on their AI products, but what does that even mean? Anne Jenkins, Vice President of Solution Architecture at Teneo, helps us separate substance from buzzwords. In this episode, Anne shares her expertise on agentic AI and the evolution of conversational AI technologies. We explore what truly makes an AI ‘agentic’ versus the marketing hype all over your LinkedIn feed and beyond. Anne explains why Teneo's hybrid approach, combining traditional NLU capabilities with large language models, creates more reliable, cost-effective, and latency-friendly solutions than pure LLM implementations. We also discuss the challenges organisations face when adopting AI solutions, including the misconception that LLMs alone can solve all problems without proper conversation design or business rule integration. Anne shares valuable insights on how companies can prepare for AI adoption through education, competitive pilots, and architectural considerations. We touch on many best practices when it comes to implementation, with Anne emphasising the importance of proper context engineering, state management, and dynamic prompting. Chapters 00:00 - Meet Anne Jenkins 05:01 - AI is now a boardroom conversation 06:48 – OpenAI’s agentic AI platform 08:48 – What is an AI agent? 21:38 – The hybrid AI model or end-to-end LLMs 26:49 – AI in debt collection 34:55 – How Teneo helps implement agentic AI 42:39 – Context engineering 47:19 – State management and LLMs 55:40 – How Teneo designs AI experiences 01:00:32 – Demo – teaching Teneo something new 01:10:26 – How businesses should adopt AI 01:16:44 – What sets Teneo apart Show notes Check out Teneo Follow Anne Jenkins on LinkedIn Read Kane’s article - What agentic AI actually is: a deeply researched and definitive explanation Follow Kane Simms on LinkedIn Take our updated AI Maturity Assessment Subscribe to VUX World Subscribe to The AI Ultimatum Substack Hosted on Acast. See acast.com/privacy for more information.

Once switched off during busy periods, Lloyds Banking Group’s chatbot now handles more than 15 million conversations a year. Learn what it really takes to build AI solutions that customers trust with their money. We sit down with Cainan Wright, Senior Product Owner, and John Young, AI Lead - Chatbots and Generative AI, from Lloyds Banking Group, to explore their remarkable nine-year journey in building one of the UK's most successful banking chatbots. From handling 3 million conversations in 2021 to over 15 million in 2025, they share the hard-earned lessons of transforming a rather "unloved" virtual assistant into a mission-critical service for almost 27 million customers. We cover how the team stabilised their service by focusing on the basics, investing in design expertise, and securing organisational buy-in through demonstrating clear value. Cainan and John also share valuable insights into their pragmatic approach to generative AI, explaining how they combine deterministic processes with generative language capabilities to deliver the best customer experience while maintaining brand consistency and ensuring regulatory compliance. The team's journey offers important lessons about perseverance and the importance of striking a balance between innovation and responsibility when deploying AI in a highly regulated industry. Show notes Follow Kane Simms on LinkedIn Discover VUX Consulting Take our updated AI Maturity Assessment Subscribe to VUX World Subscribe to The AI Ultimatum Substack Hosted on Acast. See acast.com/privacy for more information.

In this episode, we dive into the art and science of context engineering with Martin Cross, President of Connect, a company that empowers enterprises to transform through the use of AI and automation. Martin shares how most businesses still approach AI with a technology-first mindset, deploying solutions before clearly defining the customer problem they’re solving. He explains why successful AI experiences begin with understanding the user journey, designing the right interaction, and then selecting the appropriate tools, not the other way around. We also unpack Connect’s acquisition of Elerian AI and why contact centre voice recordings represent an untapped goldmine of training data. Martin explains how fine-tuning models with real-world conversations, including dialects, accents, and customer intents, can dramatically improve AI accuracy and empathy. The conversation delves into the various layers of context - from session-level to journey-wide to CRM-integrated, and how they work together to transform generic interactions into deeply personalised, proactive experiences. We also reflect on why the industry continues to repeat old mistakes and how businesses can design AI that truly understands and anticipates customer needs. Show notes Follow Martin Cross on LinkedIn Find out more about Connect Follow Kane Simms on LinkedIn Discover VUX Consulting Take our updated AI Maturity Assessment Subscribe to VUX World Subscribe to The AI Ultimatum Substack Hosted on Acast. See acast.com/privacy for more information.

Voice AI is having a breakthrough moment. With large language models delivering unprecedented understanding and next-gen text-to-speech achieving near-human fidelity, the possibilities for immersive, scalable, and personalised customer experiences are greater than ever. We’re joined by Andrei Papancea (CEO & Co-Founder, NLX) and Kylan Gibbs (CEO & Co-Founder, Inworld), who break down how their companies are working together, making studio-quality voice experiences accessible to developers and enterprises at scale. The conversation traces how voice technology has progressed from basic assistants to today’s lifelike AI voices. We also discuss the shift from brand voices to brand personalities, and how voice experiences can be tailored to different demographic segments and eventually to individual users. This episode is brought to you by NLX. NLX is a conversational AI platform enabling brands to build and manage chat, voice and multimodal applications. NLX’s patented Voice+ technology synchronizes voice with digital channels, making it possible to automate complex use cases typically handled by a human agent. When a customer calls, the voice AI guides them to resolve their inquiry through self-service using the brand’s digital asset, resulting in automation and CSAT scores well above industry average. Just ask United Airlines. Show notes Learn more about Inworld Kane Simms on LinkedIn Discover VUX Consulting Take the updated AI Maturity Assessment Subscribe to VUX World Subscribe to The AI Ultimatum Substack Hosted on Acast. See acast.com/privacy for more information.

What happens when one of the world’s leading analysts on customer service and conversational technologies sits down to unpack the future of AI? We explore the profound implications of AI adoption with Ian Jacobs, VP, Lead Analyst at Opus Research. We discuss how AI is transforming contact centres and customer service operations, from agent augmentation to process automation. Ian shares insights on how businesses are navigating the balance between AI efficiency and human empathy, including the fascinating concept of when non-empathetic AI might actually be the more empathetic choice for customers in certain scenarios. Along the way, the conversation zooms out into deeper territory, touching on human happiness, the future of work, and whether regulation can ever keep pace with innovation. Show notes Learn more about Opus Research Kane Simms on LinkedIn Discover VUX Consulting Take the updated AI Maturity Assessment Subscribe to VUX World Subscribe to The AI Ultimatum Substack Hosted on Acast. See acast.com/privacy for more information.

Gartner's Magic Quadrant for Conversational AI platforms is back in 2025! This is a must-watch for CX leaders seeking to make informed decisions about their AI tech stack. Here, we provide deep technology market analysis for artificial intelligence in customer experience. Whether you're looking to build AI chatbots, AI agents, Retrieval Augmented Generation applications, these conversational AI platforms are the best of breed. Show notes Kane Simms on LinkedIn Discover VUX Consulting Take the updated AI Maturity Assessment Subscribe to VUX World Subscribe to The AI Ultimatum Substack Hosted on Acast. See acast.com/privacy for more information.

As one of the world’s largest car manufacturers, Toyota is giving its machines a voice using AI as a trusted partner to transform how cars are built and serviced. In this episode, we speak with Kordel France, Principal AI Engineer & AI Architect at Toyota, to uncover how artificial intelligence is reshaping production and maintenance globally. We explore how Toyota has moved from technicians spending hours sifting through thousands of pages of manuals to intelligent systems that can diagnose faults in seconds and even predict breakdowns before they happen. Kordel explains the technical architecture behind these solutions, blending classical machine learning with generative AI, and the challenges of creating specialised systems from general-purpose models. You’ll also hear why high-quality data ingestion is more important than the model itself, how even a relatively small number of users can drive asymmetric improvements in efficiency, and what Toyota’s collaboration with NLX means for service technicians working across increasingly complex powertrains. Show notes Kane Simms on LinkedIn Discover VUX Consulting Take the updated AI Maturity Assessment Subscribe to VUX World Subscribe to The AI Ultimatum Substack Hosted on Acast. See acast.com/privacy for more information.

The AI arms race in customer experience just got serious. We’re joined by industry legends Nerys Corfield (Injection Consulting), Jon Arnold (J Arnold & Associates), and Henry Iversen (boost.ai) to unpack one of the biggest AI moves in recent memory: NiCE’s $955M acquisition of Cognigy. We break down what this deal means for the future of AI-first contact centres, the fate of best-in-class point solutions, and the broader shift toward an AI-led customer experience strategy. From questions of market consolidation and vendor lock-in to the culture clash between product-led innovation and marketing muscle, we share some real, unscripted insights into the implications of the acquisition for enterprises, vendors, and buyers alike. This episode is brought to you by NLX Build and deploy sophisticated chat, voice, and multimodal applications for any purpose with NLX. NLX works seamlessly with any LLM and existing tech stack, freeing you to create, not configure. Trusted by individual builders and leading teams at Comcast, Saks Fifth Avenue, Toyota, and United Airlines, NLX helps you turn AI concepts into working conversational experiences. Show notes Follow the episode guests on LinkedIn: Nerys Corfield - Director, Injection Consulting Henry Iversen - CCO & Co-Founder, boost.ai Jon Arnold - Principal, J Arnold & Associates Kane Simms on LinkedIn Subscribe to VUX World Subscribe to The AI Ultimatum Substack Hosted on Acast. See acast.com/privacy for more information.

From the hype cycle around AI to the real-world constraints enterprises face when adopting new tech, we explore the opportunities shaping the future of business communications in this episode. We’re joined by Jon Arnold, an independent tech analyst, for a conversation about the shifting landscape of enterprise communications. We talk about analysts' unique role in shaping vendor strategy and market perception. We discuss the current state of business communications technology, examining what Jon describes as the "three-legged stool" of cloud communications: CCaaS, CPaaS, and UCaaS. We discuss how these previously distinct domains are converging, with vendors increasingly offering capabilities across all three areas. We also explore how AI is disrupting the traditional communications technology landscape. Jon offers valuable insights into why AI-native companies may have advantages over traditional contact centre vendors who are adding AI capabilities, and why the pace of AI adoption varies significantly across different industries and organisations. This episode is brought to you by NLX. NLX is a conversational AI platform enabling brands to build and manage chat, voice and multimodal applications. NLX’s patented Voice+ technology synchronizes voice with digital channels, making it possible to automate complex use cases typically handled by a human agent. When a customer calls, the voice AI guides them to resolve their inquiry through self-service using the brand’s digital asset, resulting in automation and CSAT scores well above industry average. Just ask United Airlines. Shownotes: Find out more about Jon Arnold: https://www.jarnoldassociates.com/about/jon-arnold Subscribe to VUX World: https://vuxworld.typeform.com/to/Qlo5aaeW Subscribe to The AI Ultimatum Substack: https://open.substack.com/pub/kanesimms Get in touch with Kane on LinkedIn: https://www.linkedin.com/in/kanesimms Hosted on Acast. See acast.com/privacy for more information.

In this episode of VUX World, we chat with Kellin Sjoerds and Ricky Wekker, Conversational AI Engineers at Essent - the Netherlands’ largest utility provider and part of the E.ON Group to uncover the story behind their groundbreaking agent assist tool, Bolt. Bolt is an AI-powered agent copilot that has transformed Essent’s call centre operations, shaving an average of 60 seconds off every call and delivering over €1.8 million in savings, not through layoffs, but by reducing dependence on BPOs. We unpack the full journey behind Essent’s AI copilot, Bolt, starting with a simple observation during a team shadowing session that sparked its creation. What began as a hackathon MVP quickly turned heads, prompting leadership to ask, “How fast can we launch this?” From there, we uncover how the team tackled complex challenges like cleaning and restructuring their knowledge base, implementing a smart chunking system, and fine-tuning prompts to ensure accurate, reliable outputs. And through a carefully staged rollout, they struck the right balance between innovation and safety, navigating compliance hurdles while delivering impressive business value. Shownotes: Subscribe to VUX World: https://vuxworld.typeform.com/to/Qlo5aaeW Subscribe to The AI Ultimatum Substack: https://open.substack.com/pub/kanesimms Get in touch with Kane on LinkedIn: https://www.linkedin.com/in/kanesimms Hosted on Acast. See acast.com/privacy for more information.

As generative AI redefines the contact centre, ensuring consistent performance across complex telephony networks becomes mission-critical. In this episode, we speak with Satish Barot, CEO at Klearcom, about the evolution of contact centre technology and the critical role of quality assurance in AI voice systems. We explore how organisations gradually transition from traditional DTMF-based IVR systems to more sophisticated conversational AI and generative AI solutions. Satish shares insights on why this shift is happening incrementally, with many companies adopting hybrid approaches that run traditional and AI-powered systems side by side while they evaluate performance. Discover how Klearcom is pushing the boundaries of voice QA with global in-country testing, real-world noise simulation, and accuracy scoring, offering a unique lens into what production-ready means in the age of AI. We also discuss privacy considerations and why organisations should start small and scale smart when implementing these technologies. Satish emphasises that businesses should focus on great customer experience rather than chasing fancy technology for its own sake. Shownotes: Check out Klearcom: https://klearcom.com Subscribe to VUX World: https://vuxworld.typeform.com/to/Qlo5aaeW Subscribe to The AI Ultimatum Substack: https://open.substack.com/pub/kanesimms Get in touch with Kane on LinkedIn: https://www.linkedin.com/in/kanesimms Hosted on Acast. See acast.com/privacy for more information.

Merlin Bise, CTO of Inbenta and former Head of Technology at a firm acquired by the London Stock Exchange, joins us to share how Inbenta is helping enterprises modernise their customer experience. Merlin explains that so many AI deployments fail, not because the technology is lacking, but because companies often bet on the wrong frameworks, overlook data foundations, or underestimate the importance of testing. We explore how traditional rules-based systems give way to agentic frameworks that can reason, triage ambiguous queries, and even correct automation gaps in real time. Merlin walks us through the journey many enterprises take: beginning with deterministic rules, evolving to AI-powered agents, and ultimately orchestrating complex automation through agentic manager systems that oversee and improve themselves. Security and customer experience are front and centre in this episode. Merlin breaks down the cybersecurity concerns that make enterprises hesitate and why, in most cases, those fears are rooted more in perception than reality. Finally, we reflect on the broader trajectory of AI. While the race toward AGI dominates headlines, Merlin argues that the tools enterprises need to radically improve productivity are already here. The challenge is implementing what exists with purpose and precision. Shownotes: Check out Inbenta: https://www.inbenta.com/ Subscribe to VUX World: https://vuxworld.typeform.com/to/Qlo5aaeW Subscribe to The AI Ultimatum Substack: https://open.substack.com/pub/kanesimms Get in touch with Kane on LinkedIn: https://www.linkedin.com/in/kanesimms/ Hosted on Acast. See acast.com/privacy for more information.

In this special episode, recorded live at Boost Camp, we have three industry leaders who are shaping the future of conversational AI: Ben Maxim, CTO at Michigan State University Federal Credit Union (MSUFCU), Åse Marthinsen, who leads generative AI at Norway’s largest bank, DNB and Nick Mitchell, Chief Revenue Officer at boost.ai. We cover the ever-changing landscape of conversational AI, including aligning teams, integrating data across channels and designing experiences that are on brand and human-centric. We look at how organisations are managing thousands of conversational intents with lean teams, thanks to hybrid AI models and smarter content workflows. There’s a growing focus on data governance and trust, especially in highly regulated industries like banking. But DNB and MSUFCU show that you can scale responsibly, with MSUFCU’s chatbot Fran now handling 79% of customer chats without escalation. As AI gets faster, so do the expectations from customers and leadership. We talk about the shifting role of contact centres from answering FAQs to driving strategic initiatives and the importance of staying ahead through continuous testing, experimentation and AI-driven insights. Shownotes: Check out boost.ai: https://boost.ai/ Subscribe to VUX World: https://vuxworld.typeform.com/to/Qlo5aaeW Subscribe to The AI Ultimatum Substack: https://open.substack.com/pub/kanesimms Get in touch with Kane on LinkedIn: https://www.linkedin.com/in/kanesimms Hosted on Acast. See acast.com/privacy for more information.

In this episode, we explore how True Classic, a men's apparel brand, is leveraging AI to transform its customer support with Jordan Gesky, Senior Customer Experience Manager. We look at True Classic’s journey from rule-based automation to generative AI across multiple channels. Jordan talks about how their AI assistant, Crue, now handles customer service inquiries through chat, email and phone channels and how that’s reduced costs and time to resolve. We get into the practicalities of AI in customer service, including continuous auditing, clear guidelines and giving AI a brand voice. Jordan explains how True Classic trains their AI using agent conversations and FAQs and how they integrate it with their Shopify account, returns portal and product catalogue to create a self-service solution. We also talk about the challenges of AI implementation, from hallucinations to customer data security and how True Classic approaches AI governance through transcript reviews and CSAT monitoring. Shownotes: Subscribe to VUX World: https://vuxworld.typeform.com/to/Qlo5aaeW Subscribe to The AI Ultimatum Substack: https://open.substack.com/pub/kanesimms Get in touch with Kane on LinkedIn: https://www.linkedin.com/in/kanesimms Hosted on Acast. See acast.com/privacy for more information.

In this episode, we talk to Guillaume Laporte, Chief AI Officer at Foundever - a $4 billion BPO giant with 150,000 employees worldwide. Guillaume explains the massive impact of generative AI on the BPO industry, why it’s the biggest threat and the biggest opportunity for contact centres today. From deciding whether to buy, build or partner on AI solutions to navigating multiple client systems and languages, Guillaume shares how Foundever is transforming its workforce with AI-powered tools like EverAssist. Guillaume also explains why Foundever built its own internal version of ChatGPT rather than licensing OpenAI’s solution, saving millions of dollars a year while retaining control over features, latency and performance. Find out how Foundever has been tackling challenges like the AI adoption gap, balancing cost, speed and accuracy in AI models and using talent to scale solutions globally. If you want to know how generative AI is being used in a complex, multilingual, multi-client environment, this episode has the answers. Whether you’re in BPO or exploring enterprise AI, Guillaume’s honest insights are valuable for any organisation looking to stay ahead in the AI age. Shownotes: Find out more about Foundever: https://foundever.com The voice dictation tool recommended by Guillaume: https://wisprflow.ai Subscribe to VUX World: https://vuxworld.typeform.com/to/Qlo5aaeW Subscribe to The AI Ultimatum Substack: https://open.substack.com/pub/kanesimms Get in touch with Kane on LinkedIn: https://www.linkedin.com/in/kanesimms Hosted on Acast. See acast.com/privacy for more information.

Generative AI has changed everything - from how we build to how we design. In this episode, we’re joined by Alex Shin, Senior Product Designer at Prudential Financial, to talk about how UX is evolving in the age of LLMs. Alex shares his journey from studying Social Policy to UX and conversation design, including how he helped launch Prudential’s first customer-facing chatbot in 2022. We talk about how Prudential’s NLU-based chatbot is consistently getting customer satisfaction scores above industry standards and how the company is exploring generative AI solutions for both internal and customer-facing services. We also dive into the collaboration between design and tech teams at Prudential, and how this partnership ensures solutions are technically feasible while prioritising user needs. This episode is for designers navigating the transition to generative AI, tech leaders trying to balance innovation with user experience and anyone interested in how big financial institutions are using AI to improve customer service. This episode is brought to you by NLX. NLX is a conversational AI platform enabling brands to build and manage chat, voice and multimodal applications. NLX’s patented Voice+ technology synchronizes voice with digital channels, making it possible to automate complex use cases typically handled by a human agent. When a customer calls, the voice AI guides them to resolve their inquiry through self-service using the brand’s digital asset, resulting in automation and CSAT scores well above industry average. Just ask United Airlines. Shownotes: Subscribe to VUX World: https://vuxworld.typeform.com/to/Qlo5aaeW Subscribe to The AI Ultimatum Substack: https://open.substack.com/pub/kanesimms Get in touch with Kane on LinkedIn: https://www.linkedin.com/in/kanesimms/ Hosted on Acast. See acast.com/privacy for more information.

What if the most exciting AI agent innovation isn’t happening in the enterprise, but in the mid-market? In this episode, we unpack Voiceflow’s explosive growth, the shift from flowcharts to frameworks, and why success today isn’t about having the smartest model, but about how you deploy it. We explore how to build reliable, production-grade agents, the rise of self-improving systems, and the emergence of agent-to-agent orchestration. And while mid-market companies are moving fast, Braden explains why enterprise adoption is inevitable, and what it’ll take to reach that tipping point. Congratulations to Braden on making his fourth appearance on the VUX World podcast! This episode is brought to you by NLX. NLX is a conversational AI platform enabling brands to build and manage chat, voice and multimodal applications. NLX’s patented Voice+ technology synchronizes voice with digital channels, making it possible to automate complex use cases typically handled by a human agent. When a customer calls, the voice AI guides them to resolve their inquiry through self-service using the brand’s digital asset, resulting in automation and CSAT scores well above industry average. Just ask United Airlines. Shownotes: Discover Voiceflow: https://www.voiceflow.com/ Subscribe to VUX World: https://vuxworld.typeform.com/to/Qlo5aaeW Subscribe to The AI Ultimatum Substack: https://open.substack.com/pub/kanesimms Get in touch with Kane on LinkedIn: https://www.linkedin.com/in/kanesimms/ Hosted on Acast. See acast.com/privacy for more information.

In this episode, Kane Simms is joined by Katherine Munro, Conversational AI Engineer at Swisscom, for a deep dive into what might sound like an odd pairing: using LLMs to classify customer intents. Large Language Models (LLMs) are powerful, multi-purpose tools. But would you trust one to handle the precision of a classification task? It’s an unlikely fit for an LLM. Classifiers typically need to be fast, accurate, and interpretable. LLMs are slow, random black-boxes. Classifiers need to output a single label. LLMs never stop talking. And yet, there are good reasons to use LLMs for such tasks, and emerging architectures and techniques. Many real-world use cases need a classifier, and many data and product development teams will soon find themselves wondering: could GPT handle that? If that sounds like you, then check out this extended episode to explore how Switzerland’s largest telecommunications provider tackles this issue while building a next-generation AI assistant. This episode is brought to you by NLX. NLX is a conversational AI platform enabling brands to build and manage chat, voice and multimodal applications. NLX’s patented Voice+ technology synchronizes voice with digital channels, making it possible to automate complex use cases typically handled by a human agent. When a customer calls, the voice AI guides them to resolve their inquiry through self-service using the brand’s digital asset, resulting in automation and CSAT scores well above industry average. Just ask United Airlines. Shownotes: "The Handbook of Data Science and AI: Generate Value from Data with Machine Learning and Data Analytics" - Available on Amazon: https://a.co/d/3wNN9cv Katherine's website: http://katherine-munro.com/ Subscribe to VUX World: https://vuxworld.typeform.com/to/Qlo5aaeW Subscribe to The AI Ultimatum Substack: https://open.substack.com/pub/kanesimms Get in touch with Kane on LinkedIn: https://www.linkedin.com/in/kanesimms/ Hosted on Acast. See acast.com/privacy for more information.