Multi-LLM, Multi-Agent Strategies to Improve Accuracy

Joe explains using multiple tuned LLMs and agent voting to improve accuracy, and the trade-offs with token costs and logging.

Play episode from 01:10:11

chevron_right

Transcript

chevron_right

Transcript

Episode notes

In this episode, Joe Kim, the new CEO of DRUID AI, unpacks what might be the biggest shift in technology since the internet.

We discuss the evolving landscape of artificial intelligence and its growing impact on businesses. Joe, who has been in his role for 70 days, brings fresh perspectives on how DRUID AI positioned itself as a workflow automation platform years before the market caught up, a bet that's now paying off as companies move beyond AI experimentation into real implementation.

The discussion covers the current state of the AI market, including the challenges of customer adoption, why some customers actively prefer interacting with AI over humans, and the importance of maintaining a balance between generative and agentic AI.

Joe also shares his vision of AI as the next major distribution platform. Just as Amazon has tried to make Alexa the operating system of our lives, OpenAI’s ChatGPT and similar platforms could become the primary gateway to accessing services in the future.