In this podcast with Sarah Haider, Digital Manager for Conversational AI at Salzburg AG, we explore the journey of revolutionising customer interactions with generative AI.
From the early days of NLU-based chatbots to embracing generative AI and retrieval-augmented generation technology, Sarah outlines the challenges and breakthroughs in enhancing Salzburg AG’s digital assistant capabilities.
The conversation highlights the strategic shift to generative AI, tackling complex use cases like public transport queries while maintaining customer satisfaction and reliability. Sarah dives into the importance of data preparation, prompt design, testing, and quality assurance, shedding light on what it takes to make AI solutions scalable and effective in real-world scenarios. This episode is perfect for anyone looking to modernise their chatbot or explore the potential of AI in customer experience. From reducing call centre volume to delivering human-like interactions, Sarah’s approach demonstrates how innovation can elevate both business impact and customer satisfaction.
In this episode
00:00: Introduction to Sarah Haider and Salzburg AG
05:23: Why is AI appealing for the energy industry?
08:32: The history of AI at Salzburg AG
12:00: Measuring success pre-generative AI
16:25: Goals of exploring generative AI
19:50: Starting with Retrieval Augmented Generation (RAG)
24:10: Full RAG implementation process
39:45: Lessons in prompt design
44:45: Quality assurance tactics
48:25: Impact of generative AI
51:20: Other use cases for generative AI
Subscribe to VUX World
Subscribe to The AI Ultimatum Substack
