Skip to content
Join 7,000+ leaders following Alastair's work on LinkedIn.

RAG is the "killer app" of AI

Last updated 15 April 2026 Published 18 September 2024

RAG is the "killer app" of AI.

Or, at least, it's the killer app of AI for 2024 AI Agents will be the killer app of AI in 2025 and beyond. Watch this space...

Back to RAG - it's not a specific app. It's a technique we use with AI that's simple but incredible effective: we combine a language model with your own documents and data.

Here's how it works: you have a repository of your own data - your documents, records, or files. RAG enables the language model to access and read these documents, meaning it can generate responses that are specifically tailored to your data.

In technical terms, RAG stands for Retrieval Augmented Generation, and models like ChatGPT, Claude, or Gemini can get to "know" your business and your team's data, allowing the model to provide answers that are accurate, context-driven, and based on your unique information.

This puts the AI model on steroids - instead of writing generic responses, it uses your data to give you specific answers that make sense for your unique situation.

This means you get answers that are up-to-date, relevant, and specific to your business/team/organisation.

⚠️ This is important because AI is only as good as the data it's based on. We've all heard the phrase "Garbage In, Garbage Out".

RAG helps us make sure what we put in is relevant and useful to the context of what we want to get out, i.e. NOT garbage.

So, how do you implement RAG? There are many options, some very simple, and some a lot more complex (and expensive). It depends on factors like:

What's your budget?
- High: Go self-hosted
- Moderate: Consider third-party options
- Low: ChatGPT is your friend

How sensitive is your data?
- Very: Self-hosting is the safest
- Moderate: A trusted vendor works
- Low: Cloud-based is fine

What's your AI expertise?
- Advanced: Go self-hosted
- Intermediate: Third-party solutions
- Beginner: ChatGPT & similar options

You can't just switch on RAG and expect instant results:

🗂️ Use up-to-date, clean, and well-organised data.
🔄 Check compatibility with your current systems.
👩‍💻 Train staff to use RAG effectively.
🔒 Ensure you follow data privacy laws.
⚙️ Regularly update and fine-tune your setup.

Would you like help setting up RAG for your business? Comment "RAG" below and I'll DM you some resources to help you get started.

Related Articles

Building an AI Knowledge Base That Actually Works

Labs Learning - April 2026 This is Part 2 of a two-part series on building AI knowledge bases. Read Part 1: Your AI Knowledge Base Is Only as Good as What You Feed It In the last post, I talked about the data quality problem: how 87% of my AI knowledge base turned out to […]

Your AI Knowledge Base Is Only as Good as What You Feed It

Labs Learning - April 2026 This is Part 1 of a two-part series on building AI knowledge bases. Read Part 2: Building an AI Knowledge Base That Actually Works There's a type of AI system that's becoming increasingly popular in businesses of all sizes. It's called RAG - retrieval-augmented generation - and the basic idea […]

Building a Live Speech to Text AI

One thing you may not know about me is that when I run workshops or live demos for organisations, I always give the organiser explicit permission - twice - to interrupt me. Here's why: I have ADHD. I have it...

What the Hell Is "Data"?

One thing that really frustrates me about AI consultants - and software engineers - is when they say things like: "You need to know your data" "You need to have clean data" "You need to know where your data...

Is your business AI ready?

  • Get honest, practical AI advice
  • Find out where AI saves the most time
  • No hard sell - just an honest conversation
Alastair McDermott

25 mins · Free · No obligation

Book a Focus Call