Mikhail Burstev, Founder of Deep Pavlov, talks AI orchestration and LLMs

Picture of Kane Simms
Kane Simms

More ways to listen and watch

About this episode

Mikhail Burstev joins us as he shares AI orchestration and LLMS with us on the VUX World Podcast

Presented by Tidio

Grow your online store with the #1 customer success tool for eCommerce. Engage with your customers and website visitors in real-time. Provide personalized product recommendations. Use AI-powered chatbot workflows to move prospects through your sales funnel. And so much more.

Save 20% on your subscription with the promo code VUX.

Find out more about Tidio (use the link https://www.tidio.com/partners/vux/)

Mikhail Burstev is a seasoned AI practitioner and scientist. Founder of one of the most popular chatbot frameworks, Deep Pavlov, Mikhail has been knee deep into the AI space for many years. He joins me to share his thoughts on AI orchestration and Large Language Models.

In this episode

00:00 Introduction
03:20 Welcome Mikhail
08:30 The primary goal of Deep Pavlov
12:05 Switching between agents
14:50 Main considerations
20:00 Requests going to the correct agents
23:11 Features that each agents fulfils
27:57 Recognising conversations
31:46 What things go wrong
35:40 LLMs performance
38:23 Missing some obvious information
42:13 Where LLMs and LNP models perform best
45:23 Handing back to orchestrators
52:57 Using personal assistants
57:30 Outro

Share

Weekly newsletter

The latest in AI-powered customer experience. Make better strategic decisions with the help of our weekly newsletter.

Host

Kane Simms

A strategic AI advisor who, for the past decade, has helped business leaders and product owners transform customer experience using conversational and generative AI.

Share

✓   Link copied

Weekly newsletter

The latest in AI-powered customer experience. Make better strategic decisions with the help of our weekly newsletter.

Top articles and podcasts

Related content

Cobus Greyling: why intents, graphs and conversation design have come full circle
Cobus Greyling on where enterprise AI is really heading: data, security, forward-deployed engineers and conversation design.
From answers to actions: building better government AI
Pete Kowalczyk on knowledge graphs, goal detection and moving AI from answering questions to taking action.
What’s really breaking your AI agents?
Discover where conversational AI projects actually break: contradictory source data, manual process and weak testing.
How Simplyhealth scaled voice AI to resolve 30% of calls
Paul Atkins, Head of Business Optimisation at Simplyhealth, breaks down how they scaled voice AI to resolve almost a third of calls, and what it took to get there.