Focus Sessions schedule

The main goal of this talk is to explore how NLP helped us to design solutions for our customer care. Our problems range from assigning the emails in customer care to the right agent, to transcribe Swiss German voice messages to German for further processing and a chatbot for automatically answering frequent customer questions. In this talk I will dive deeper, how we apply natural language processing to classify various products or processes in mails or intents in chats, how we use that information to automate certain tasks and therefore manage the workload of our agents. Furthermore I will show how to  integrate such a solution in on environment where our agents, can retrain them on demand and react to data drifts

- How to apply NLP in customer care applications

- How to design a managebale software that can react to changes

- How to integrate it into a CI/CD pipeline

With the background of a Master's degree in Computer Science with the focus of modeling
and scaling up AI models I am currently working as a Senior AI Engineer at Swiss Post.

My passion is to focus on delivering business value in customer care by operationalisation of use cases in production. Personally I am a networker and an open-minded, motivated person with the mission of transforming the Swiss Post to an AI driven organisation.

The main goal of this talk is to explore how NLP helped us to design solutions for our customer care. Our problems range from assigning the emails in customer care to the right agent, to transcribe Swiss German voice messages to German for further processing and a chatbot for automatically answering frequent customer questions. In this talk I will dive deeper, how we apply natural language processing to classify various products or processes in mails or intents in chats, how we use that information to automate certain tasks and therefore manage the workload of our agents. Furthermore I will show how to  integrate such a solution in on environment where our agents, can retrain them on demand and react to data drifts

- How to apply NLP in customer care applications

- How to design a managebale software that can react to changes

- How to integrate it into a CI/CD pipeline

During my MSc in Computer Science at ETHZ I discovered my deep fascination for machine learning and it’s capabilities for automation.

This fascination lead me to the Swiss Post where I’m developing, enhancing and implementing the machine learning backend for various applications. Examples include the chatbot or AI generated suggestions for customer support agents.

I particularly enjoy getting requests from support staff to enhance our software and cover more cases since it shows me that not only are we making processes more efficent, we also help people in their day to day lifes.

Diagnosing an issue in a Customer’s home to deploy an engineer can be a complex query.  HomeServe has used conversational AI to diagnose a customer’s issue with only two or three questions, resulting in a more efficient conversation.  HomeServe has been able to automate 15-20% of its deployed claims and service requests in the UK and USA.  Utilizing whispers and screen pops, successful triaging of a customer’s issue has led to over 30 seconds saved in handling time. 

Expanding outside the claims experience, in this talk, we will explore the other conversational bots HomeServe has created to improve the performance of its marketing campaigns through smarter call routing and rich data insight.

- Diagnosing a customer’s issue with only two or three questions

- Reducing handle time through improved call segmentation

- Creating data rich operational insight

Ross has been the lead for HomeServe UK in designing the intent model that sits behind Hana, creating a model that has intents for household claims and customer service interactions.  More recently Ross has moved to the USA team to help improve the existing bot Charlie and launch conservational AI into other channels such as Sales and the Contractor Network.  Data is important and key to success of any automation program, tools like Looker, Power BI have helped Ross bring to the business rich data insight.  Prior to the automation program Ross has experience with more mature contact center telephony technology, designing and maintaining DTMF IVR’, with a background in operation planning and call forecasting.

- Can customer touchpoints be an indication of the success of a virtual agent? 

- Setting realistic goals and defining the purpose of conversational AI in your company 

- How would you know if the conversational AI chatbot is working the way you designed it? And how would you define the ‘success’ of the initiative? 

Catalina Baincescu is Team Lead at CAI Romania & Technical Lead at E.ON Software Development. She is responsible for development of numerous chat and voice assistants internationally at E.ON, starting from simple FAQ bots to complex transactional assistants deployed on different customer-facing channels. Catalina is supporting E.ON business units in dealing with their demand in the most efficient way, discussing and consulting on their systems architecture and how that can be integrated with the platforms that the E.ON group has. Catalina has a degree in Computer Science and has been volunteering to educate children in Romanian school on the basics of computer science field.

Richard is a Senior Research Fellow whose background is in applied research, leading evaluations of national sport and physical activity programmes in the UK, for clients including the Premier League, Rugby Football Union and Department of Health and Social Care. He now applies this knowledge to develop novel, evidence based Conversational AI solutions which support young people and adults to improve their health and wellbeing and leads the Conversational AI Research Cluster at Sheffield Hallam University, working on projects for a range of organisations including the NHS (i.e., DAFNE). He’s also the founder of Phyllis (Phyllis.chat), a chatbot which aims to support adolescents to overcome barriers to physical activity and is a mentor on the Advanced Wellbeing Accelerator Programme (AWRC) which support start-ups (i.e., Therapha) in health and wellbeing.

Product Management IT, Digital Commerce

BMW Group

In this presentation, we will be discussing an early-stage project focused on adding charisma to an online vehicle configurator through the use of conversational AI. The goal of BMW is to close the gap between the online configuration experience and the offline experience at the dealership. This presentation will provide a behind-the-scenes look at the project, including information on the business objectives and technical platform being used. Attendees will gain insight into the challenges and opportunities of implementing conversational AI in the automotive industry and the potential impact on the customer experience.

- What does is a charismatic vehicle selection journey look like?

- How do online and offline assistance differ?

- How to implement this as scale?

Gerrit Seebeck is a highly experienced professional with over 7 years at BMW and over 10 years in the field of digital media, IT product management and analytics. He has a unique perspective on the intersection of data and business, and is dedicated to maximizing the value of technology for his company. Currently Gerrit is leading a project at BMW to enhance the vehicle selection process by adding conversational AI assistance, an innovation that will bring dealership-level guidance to the online buying experience. Gerrit is also a dedicated mentor and lecturer in his field, sharing his knowledge and experience with the next generation of professionals . (Written by ChatGPT)

Live across 15 markets, and with chat and voice capability spread across 7 channels, averaging over 300 million conversations per year, TOBi is Vodafone’s flagship digital agent. While its name and brand is similar across Vodafone, Tobi capabilities, implementation, behaviour and look and feel varies in the different Vodafone local markets.

As TOBi scales and matures, it is now more important than ever to align TOBi’s experience and design across all markets, so that the experience and dialogue is consistent, expert, and meets the needs of our customers wherever they are in the world.

From the creation of an Experience Framework to the establishment of a central repository of visual components, in this presentation we will go through the work we are doing to address this challenge at Vodafone.

- Addressing the challenges at Vodafone 

- How TOBi differs across Vodafone local markets 

- Creating a consistent experience and dialogue to meet the needs of customers 

Beatriz Lopez Mencia is a User Experience Manager in Vodafone Group. At Vodafone she manages the design of a wide variety of global digital consumer products, from the My Vodafone App to the Digital Assistant TOBi.

Trained as a Telecommunications Engineer and with a PhD in Human Computer Interaction, she has more than 10 years of experience working in the User Experience industry. Previously, Beatriz worked 7 years in Research and Innovation at the Polytechnic University of Madrid. Her research career was focused on Speech Technologies, Voice Interaction Design and Embodied Conversational Agents.

With passion both for technology and user experience, Beatriz advocates for a more human, relevant and inclusive technology industry.

Live across 15 markets, and with chat and voice capability spread across 7 channels, averaging over 300 million conversations per year, TOBi is Vodafone’s flagship digital agent. While its name and brand is similar across Vodafone, Tobi capabilities, implementation, behaviour and look and feel varies in the different Vodafone local markets.

As TOBi scales and matures, it is now more important than ever to align TOBi’s experience and design across all markets, so that the experience and dialogue is consistent, expert, and meets the needs of our customers wherever they are in the world.

From the creation of an Experience Framework to the establishment of a central repository of visual components, in this presentation we will go through the work we are doing to address this challenge at Vodafone.

- Addressing the challenges at Vodafone 

- How TOBi differs across Vodafone local markets 

- Creating a consistent experience and dialogue to meet the needs of customers 

Jordan Anglin is a Customer Experience & Engagement Lead in Vodafone Group. At Vodafone he manages Group wide initiatives to help improve consistency of the Customer experience TOBi delivers to across our markets. This includes sharing & alignment of best practices, Launching Global engagement plans in partnership with Vodafone Brand teams and conducting Consumer Research/Benchmarking studies in partnership with UX Research Team to understand the impact/impression of TOBi on our customers. Most recently Jordan has taking on additional focus on the Centralised Chat UI with Components which can be reused across markets and building of Quality Dashboard/Standards. Jordan passion comes from Supporting & driving a community to continue to share knowledge drive collaboration and overall improvement in TOBi’s Customer experience.

- Exploring the benefits of customer service automation 

- Helping your team deliver personalised customer support, while eliminating redundant, complex processes 

- Automated customer service doesn’t replace the need to build relationships with customers; instead, it makes it easier to forge trusting, mutually beneficial relationships 

- How the BA.com chatbot came to be, and what it resulted in 

- Realising that chatbot was hated by customers – but why? 

- How we decided to turn around the chatbot, what we did and finally, achieving the promises of chatbots 

Aivis is a technically adept, agile, and enthusiastic professional with deep experience in delivering digital transformation projects to a diverse set of clients. He is inclusive, open-minded, project manager with an interest in data analytics, process optimization, digitization, and human-centered design. Aivis' core skillset includes a strong analytic mindset, conceptual and quantitative thinking, as well as exceptional interpersonal skills that foster trust and relationships.

Aivis approaches problems using people, processes and platforms approach. He tries to understand how various components interact, and how they affect the end-user. As such, his proposed solutions and approaches are centered around the human experience, thus reducing potential change management issues.

He is passionate about transportation industry, specifically aviation and active transportation (cycling, bike-share, etc).

- When customer service is automated, the level of personalisation must remain high

- By learning language-specific nuances, you can understand the voice of your customer which is the key to understanding your customer

- Conversational AI promotes humanity, commitment and openness