Closing the loop: From snippet monster to maintainable insights

Описание: Intercom’s Chief AI Officer Fergal Reid sits down with Staff ML Scientist Fedor Parfenov to unpack how the Fin team turned failed conversations into better answers - safely. They trace the journey from Copilot to the new Insights product, tackling content gaps, the “snippet monster,” accumulation and consolidation, and why causal inference beat classic A/B tests for measuring real impact.

Chapters
00:00 Introduction to Insights Product Development
02:57 The Journey from Expedia to Intercom
05:48 Building Copilot: Enhancing Customer Support
08:48 Insights Initiative: Leveraging Conversations for Improvement
12:10 Iterative Development: Overcoming Challenges with Snippets
15:07 Causal Analysis: Measuring Impact Effectively
24:29 Navigating Seasonality in Customer Support
30:04 The Future of Insights and AI Actions
35:41 Building Effective AI Products
43:19 The Evolution of AI Development

Follow the people
  / fergalreid  
  / fedor-parfenov  

https://fin.ai/research/
Insights and blogs from the AI Group building Fin at Intercom

Say hi
  / fin  
https://x.com/Fin_ai

https://www.fin.ai

#AI #CustomerService #MachineLearning #LLM #ArtificialIntelligence #FinAI #Intercom #AIProduct #CausalInference #Chatbot #TechPodcast #AIPodcast #CustomerSupport #GenerativeAI #Analytics