Knowbl on building an LLM-first AI platform

Picture of Kane Simms
Kane Simms

More ways to listen and watch

About this episode

Matt Taylor joins us as he shares his insights into how Knowbl is building an LLM-first AI platform.

Matt Taylor, CEO, Knowbl, joins me to discuss the realities of building a conversational AI platform on top of LLMs from the ground up.

In this episode

00:00 Introduction and presenting VUX World at the EU Chatbot Summit, We have a 30% DISCOUNT for you too: VUXEU23 to attend: https://theeuropeanchatbot.com/
02:50 Welcome Matt Taylor
05:09 The impact of ChatGPT
08:09 Challenges with traditional NLU systems
14:30 Challenges of traditional CAI systems
20:57 What does Knowbl do?
28:27 How accurate is an LLM at entity extraction
31:30 Ingesting content
35:10 Generating vs presenting content
41:12 Managing context
45:48 Feeding the LLM
47:30 Room for qualitative research?
52:26 A wish for future of LLMs
55:39 Knowbls approach to LLMs
1:01:44 Quickfire questions
1:05:04 Outro

Visit : https://knowbl.com/

Join VUX World at the EU Chatbot Summit where we’ll be hosting a full day of enterprise AI best practice content, with the likes of Vodafone, Love Holidays, LNER and many more. We have a 30% DISCOUNT for you too: VUXEU23 to attend: https://theeuropeanchatbot.com/

Find out more about https://kore.ai/ and book a demo here

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.