#4 Harley Davis: Combining LLMs with OR and Business Rules for Mission Critical Applications
Manage episode 485449604 series 3662212
In this podcast episode, Michael Watson & Vijay Mehrotra interviews Harley Davis, Founder and CEO of Athena Decision Systems. They discuss the rise of generative AI and its integration with business rules, emphasizing the importance of reliable decision-making in mission-critical applications. Harley explains the limitations of LLMs, referring to them as 'stochastic parrots,' and highlights the challenges of scaling these technologies while ensuring privacy and compliance. The conversation also covers the role of RAG in enhancing LLM performance and shares real-world use cases where AI can improve administrative processes.
Chapters
0:00 - Introduction & Preview
1:19 - Meet Harley Davis & Athena Decision Systems
4:30 - Business Rules in Mission-Critical Applications
9:23 - Understanding LLMs and Their Limitations
12:05 - Integrating LLMs with Business Rules
14:12 - Challenges in Scaling LLMs and Privacy Concerns
17:34 - The Role of RAG in Enhancing LLM Performance
20:15 - Deploying LLMs in Real-World Applications
24:24 - Improving Administrative Processes with AI
27:10 - Final Thoughts and Recommendations
Follow the show
Apple: https://podcasts.apple.com/in/podcast/the-decision-intelligence-lab/id1811085064
Spotify: https://open.spotify.com/show/0lFoAVKqJHTYSZNpeN61ou?si=0ae973aab0174b3b
Connect with guest
Harley Davis: https://www.linkedin.com/in/harleydavis/
Athena Decision Systems: https://athenadecisions.com/
Connect with hosts
Prof. Vijay Mehrotra (University of San Francisco): https://www.linkedin.com/in/vijay-mehrotra-ba9498/
Prof. Michael Watson (Northwestern University): https://www.linkedin.com/in/michael-watson-07600a1
About the podcast
The Decision Intelligence Lab podcast delivers real-world insights for data professionals, business leaders, and anyone seeking to leverage data & AI for smarter decision-making & successful business outcomes. For business inquiries, email at [email protected]
5 episodes