{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Unprompted","title":"Designing Hybrid Conversational AI: Why Hybrid Beats Fully Generative | With Rebecca Evanhoe","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/066a6858\"></iframe>","width":"100%","height":180,"duration":3548,"description":"Designing Hybrid Conversational AI\nIn this episode of the CDI Expert Series: Unprompted, we sit down with Rebecca Evanhoe to explore what it really takes to design and scale conversational AI in production. Drawing on her work building voice AI for thousands of restaurants at Slang.ai, Rebecca shares a grounded, experience-driven perspective on hybrid systems, evaluation, and why strong conversation design principles matter more than ever in the age of LLMs.\nWe delve into the practical realities of deploying conversational AI at scale, moving past the hype to emphasize that hybrid architectures, combining deterministic logic with carefully scoped LLM tasks, are essential for voice-based and high-stakes environments. A major focus is on rigorous evaluation, where Rebecca outlines the process of designing experiments, defining clear success criteria, and combining human and automated testing to build confidence and mitigate hallucinations, rather than trusting LLMs out of the box.\n \nThis episode also covers:\nWhy hybrid conversational systems outperform fully generative approaches\nHow to evaluate LLMs for real-world conversational use cases\nDesigning voice AI that respects turn-taking, timing, and social norms\nUsing LLMs as components rather than full conversation drivers\nThe growing importance of evaluation as a core design skill\nWhat conversation designers should focus on as AI tooling evolves\nBalancing automation, hospitality, and brand experience in voice interfaces\nThis episode offers a practical, no-nonsense look at what it takes to design conversational AI that actually works. So after listening, the question becomes: how do you design conversational AI systems that are not just powerful but reliable, testable, and ready for the real world?\nContact Us\nThanks for tuning in to Unprompted, for more practical lessons, and behind-the-scenes stories, exclusive events, and candid insights, visit our website or follow us on your favorite social platform.\nFollow us on...","thumbnail_url":"https://img.transistorcdn.com/-iQg5hMdBJ8PK4wI_rIzkGYVHTLjksUyCb3FxXpUxMI/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS8yOTg2/ZWU1YjkwYTcwMWNm/NGQwZTFhNTA0Njg5/MmQ0NS5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}