Remember when ChatGPT launched and it was like, wow, that’s crazy—You’re telling me I can talk to a computer? Also
remember how quickly we started to expect more from our AI? Like, why can’t it do things for me? Can it look at my
calendar?
Especially for our business lives, that’s super important. A white-collar employee uses on average over 50 tools a
year.
Now we have these super intelligent chatbots. Of course we want them to accomplish things for us. But how does AI
understand what to do and how to access our tools?
Remember that an AI is basically trying to respond your prompt. In a pure chatbot context, all it has is its
training data.
So if you ask it “Prepare me for my next meeting,” it’s going to give you generic advice based on what it
understands.
Now if we add tools to this AI—in Gumloop you do that by adding them in the UI—you can give it access to business
tools and different data sources.
Now the large language model still works exactly the same way even with tools: It’s still just trying to predict the
next word. The difference now is that it can use these tools.
It looks at your prompt and the tools you’ve given it and tries to do the next right step. It can now decide to use
one of those tools. So if you say prepare me for my next meeting, it can decide that looking at your calendar is the
right next thing to do.
What’s amazing about tool use is that large language models can figure things out. It’ll look at your calendar to
get the next meeting, then jump into your CRM to grab information about attendees or even update information there.
It takes all that information from the tool—all the meetings, or the success message that it’s created a new
contact—adds it to the prompt, and decides what to do next.
Its goal is always the same: predict the right next word but now in doing so it can actually use the tools it has at
its disposal to do that.
Now there’s a lot happening in the background happening to allow large language models to use your tools — but you
don’t have to worry about that!
What’s important to remember is that with tools, you take something that can chat with you to something that can do
things for you.
But here’s the thing—just because it can access your calendar, CRM, and email doesn’t mean it knows what you want it
to do with them. That’s where instructions come in. And when you combine tools with instructions on how you want it
to do things, that’s something that can truly get work done for you — more on that in the next lesson.