Let’s RAG and roll: the role of content in LLM applications

Picture of Kane Simms
Kane Simms

More ways to listen and watch

About this episode

In this episode, we dive deep into the critical role content plays in the success of AI systems like RAG.

Generative AI is often marketed as a magical tool—just upload your data and let the model do the heavy lifting. But the reality is far from simple. Retrieval-Augmented Generation (RAG) doesn’t work without thoughtful preparation, clear strategy, and, most importantly, quality content.

Join us as we speak with seasoned content strategists and AI industry experts who have been on the frontlines of managing and optimizing knowledge bases for AI use cases. We’ll explore why the future of AI isn’t about replacing writers—it’s about empowering content designers, technical writers, and knowledge architects to create structured, optimized, and actionable information that AI can truly work with.

If you’ve ever wondered why your AI project underdelivered or how to transform legacy content into a powerful AI resource, this episode is for you.

In this episode

00:00 Introduction
01:39 Larrys, Maaike and Timo’s work background
05:38 Talking to data
10:22 Core problems
13:50 Content transformation
21:49 Technology companies perspective
33:07 Bringing together customer needs and content
41:10 The RAG bot
45:35 Tagging and meta data
51:00 New approach
53:15 Leveraging content advice
55:54 Outro

Subscribe to https://vux.ai/subscribe for weekly updates on how to implement AI effectively in your organisation.

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.