How Plenums Lab Uses Multiple AI Agents to Debate and Evaluate Ideas (with Evan Khanna)
Testing an idea usually means gathering people to challenge it, which costs time or money. Evan Khanna wanted an instant way to debate his own decisions without hiring anyone or waiting on friends. He built Plenums Lab, where independent AI agents debate a question across different models while an AI moderator and judge weigh the arguments and deliver a decision. In this episode of Lead with AI, Dr. Tamara Nall speaks with Evan about how Plenums Lab grew out of a theory he calls the multi-model approach, why he named the project after a plenum, an assembly of different voices, and how a high school teacher used it to help decide if she should restructure her staff. Evan also explains how he can choose cheaper models for a quick read or stack up to thirty for a deeper debate, why he built ethics guardrails into the system from the start, and where he sees the underlying debate engine heading next, including research into why AI models disagree in the first place. Join the waitlist for Plenums Lab at plenumslab.com. Follow Evan Khanna and Dr. Tamara Nall on LinkedIn, and subscribe to Lead with AI for more conversations with the people building and applying AI. Follow or Subscribe to Lead with AI Podcast on your favorite platforms: Website: LeadwithAIPodcast.com | Apple Podcasts: Lead with AI | Spotify: Lead with AI | YouTube: @LeadwithAIPodcast | Facebook: Lead with AI | Instagram: @LeadwithAIpodcast | TikTok: @LeadwithAIpodcast | Twitter (X): @LeadwithAI Follow Dr. Tamara Nall: LinkedIn: Tamara Nall | Website: TamaraNall.com Follow Evan Khanna (Creator, Owner & Researcher, Plenums Lab): LinkedIn: @Evan-Khanna-Dareshift | Website: EvanKhanna.Dev | Plenums Lab: PlenumsLab.com
About this Podcast:
Testing an idea usually means gathering people to challenge it, which costs time or money. Evan Khanna wanted an instant way to debate his own decisions without hiring anyone or waiting on friends. He built Plenums Lab, where independent AI agents debate a question across different models while an AI moderator and judge weigh the arguments and deliver a decision.
In this episode of Lead with AI, Dr. Tamara Nall speaks with Evan about how Plenums Lab grew out of a theory he calls the multi-model approach, why he named the project after a plenum, an assembly of different voices, and how a high school teacher used it to help decide if she should restructure her staff.
Evan also explains how he can choose cheaper models for a quick read or stack up to thirty for a deeper debate, why he built ethics guardrails into the system from the start, and where he sees the underlying debate engine heading next, including research into why AI models disagree in the first place.
Join the waitlist for Plenums Lab at plenumslab.com. Follow Evan Khanna and Dr. Tamara Nall on LinkedIn, and subscribe to Lead with AI for more conversations with the people building and applying AI.
Follow or Subscribe to Lead with AI Podcast on your favorite platforms:
Website: LeadwithAIPodcast.com | Apple Podcasts: Lead with AI | Spotify: Lead with AI | YouTube: @LeadwithAIPodcast | Facebook: Lead with AI | Instagram: @LeadwithAIpodcast | TikTok: @LeadwithAIpodcast | Twitter (X): @LeadwithAI
Follow Dr. Tamara Nall:
LinkedIn: Tamara Nall | Website: TamaraNall.com

Comments