3DN’s first in a series of educational webinars designed to help businesses navigate the right pathway for AI. This session explores the philosophy behind 3DN’s approach to AI, demonstrates a real-world case study with Agar Chemicals using knowledge graphs for product recommendations, and shares a practical tip for extracting your personal writing style using AI.
Transcript:
[00:00:00] Firstly, thank you for coming today. We developed a series of webinars that we’re going to be running every few weeks, purely as education to help our customers and potential customers figure out the right pathway for AI in their business. Before we get into things, though, I’m just going to start off something here. I’m using a tool called Claude, it’s an alternative to ChatGPT. And I’m going to ask, you know, what’s the best product to clean antifreeze off a workshop floor? And we’ll come back to that soon.
Demonstrates how language models can analyze images using computer vision to identify objects, count people, and extract details.
Transcript:
When we think about language models a lot of the time, we think about how it’s dealing with text, but something that’s really useful with language models is also dealing with images. Both chat GPT and Clawed and other language models use a tool called computer vision, which enables it to interpret an image in some form. So in this case, I found an image on the Wander and we’re going to use computer vision to do an analysis of the image. So I’ve asked Clawed in this case to describe the key elements in the image, identify any text that appears, explain the relationships between objects and unusual, on notable aspects, and to specifically be aware of objects and their attributes, text and labels, spatial relationships and context clues. In this case, the analysis is quite detailed. It’s told us that it can see market stalls with green and teal awning labeled are a market. It’s identified that there’s vendors and shoppers and visitors and there’s historic architecture visible in the background. And then the market is under some metal beams. It’s identified relationships between crowds of people navigating the stalls, the historic buildings, the trees and the greenery and the merchandise that’s displayed up to. Now in this case, this isn’t amazingly useful information unless our job was analyzing images, but it may be useful because it allows us to get more detail about a specific aspect of the image. In this case, I’ve asked can you count the number of people in the image and it’s identified approximately 15 to 20 people and told me why it’s hard to do that. I’ve then pressed it for an exact count and you can see what it’s done is it’s identified 16 distinctly visible people in the image. In isolation, analyzing a single image on its own, not amazingly useful, but you can see the power available when it comes to analyzing dozens or hundreds of these sort of images. In this case, we looked at a photograph, but it could be a screenshot of a website to a diagram from a textbook, really anything that you wanted to analyze that has an image.
Demonstrates the web crawler that automatically extracts and processes website content into the knowledge base.
Transcript:
We built 3D and respond to transform custom inquiries into exceptional experiences. We do this by streamlining, prioritizing and resolving requests across all of your channels. This empowers your team to deliver faster, more personalized support, builds, lasting relationships. And today, I want to show you how we deal with the knowledge base in 3D and respond. One of the critical parts of 3D and respond, because it adds all of that organizational knowledge to the response. There’s two ways that you can add information to the knowledge base. And today we’re going to talk about only one of those two ways and that is doing a web crawl. With 3D and respond, we include a powerful web crawling system. And this automatically builds your knowledge base from your existing website content. And here’s how it works. You simply provide a starting URL like maybe your homepage or your events page. And the system just starts exploring the crawler follows links on your website, identifies relevant content pages while avoiding things that are irrelevant, like duplicated content or navigation systems. As the crawler visits each page, it extracts all the meaningful information out, like the actual information your customers would need. While removing headers and footers and other elements. The extracted content isn’t just stored as is though. We break it down into smaller, focused chunks that are perfect for AI based questions and answers. Each piece of content is then converted into a special mathematical representation. That captures its meaning, not just the key words. And this is what allows the system to understand customer questions and find the most relevant information. This automated system eliminates the need to manually copy and paste content into your knowledge base. Your existing website investment becomes immediately useful for customer support, ensuring consistency between your public information and your support responses.
A demonstration of how AI agents can fundamentally shift how associations serve their members — handling complex constitutional queries and delivering instant, accurate member services 24/7.
Transcript:
[00:00:00] Every minute your team spends on routine queries is a minute they’re not delivering real value to your members. Right now, your members are paying for digital friction with their time and money.
[00:00:11] Let me show you what changing that looks like. These two agents represent a fundamental shift in how associations serve their members.
