How LLMs are Revolutionizing Bot Creation

Hello, Trailblazers of the AI Space,

Over the next few weeks, I will share my experiences and insights into the new way to build Conversational AI Agents.

We will cover all of the most essential topics, including LLMs, Knowledge Bases, Prompt Engineering & Tuning, utilizing NLP and NLU, Model Fine-Tuning, and even touch on Pre-Training a Large Language Model. That last one doesn't apply to you unless you have about $30 Million you want to spend.

And now this...

Do you remember the good ole days when building a bot felt like a never-ending cycle of setting flows and interpreting user inputs through NLU frameworks??

Well... they are gone! But before we skip to the present, let's walk down memory lane so we can see where we were and where we are going!

Before LLMs

Not too long ago, we were all immersed in creating intricate flows, anticipating every possible user input, and crafting responses accordingly. It was a time of structure, precision, and rigidity—a time when creativity felt bound.

Those days are gone.

They are becoming a distant memory, thanks to the introduction of Large Language Models (LLMs).

After LLMs

Today, the world of Conversational AI has been flipped upside down. The work is less about the exhaustive setting of flows and more about understanding the potent dynamics of prompt chaining and harnessing the power of well-structured knowledge bases.

However, the real change is in thinking.

Designers now need to think about what information is and how it is interpreted into something meaningful.?

Understanding this dynamic will lead to organizing and retrieving information more accurately and efficiently and to creating better conversational agents.?

So in summary, it boils down to:

1. Organizing and Retrieving Information and generating Meaning

2. Flows: Very strategic Flows using NLP and NLU

The New Conversational Design Stack

The new CUX Design Stack will include a whole new section on Knowledge.?

LLMs will tap into the Knowledge and be able to answer most questions, and then NLUs will follow up with the next logical step for the business.?

For example, a user might ask about a product warranty, which triggers the Knowledge Base.

The LLM answers the user's questions using the knowledge base and the user responds with enthusiasm. Then, the NLU is triggered to take the user down the happy path and close the sale.

In the example, the design stack includes:

• Knowledge Base: Training the LLM on specific information
• Prompt Design / Engineering / Tuning: prompts, instruction, roles given the LLM
• NLU Flows: Very strategic Flows using NLP and NLU

Knowledge Bases and the Future of Conversational UX

We've also prepared a video to visualize how exactly LLMs are revolutionizing bot creation, guiding you through the nuances of prompt chaining and the indispensable role of knowledge bases.

We invite you to join us on this exciting journey as we uncover the layers that make this technology a game-changer in the bot creation space.

Resources

Guide to the New Conversational Design Stack & Presentation