Hey, just quickly from me before we get into it. If you're using AI but still doing too much manually, Neo and I have built something for you. It's called the AI Agent boot Camp, and it's a four week virtual program and you'll walk away with agents already built and working. Spot's limited and all the details are in the show notes. You've probably heard the word agents thrown around a lot lately, and if you've been nodding along while quietly having no idea what it actually means, you're
not alone. The AI companies have done a genuinely terrible job of naming things agents, agentic, GPTs, projects, gems. It's a lot of words for concepts that, once you understand them, are actually pretty straightforward. In this episode, Neo and I
cut through all of that. We cover what an agent actually is and why it's different from agentic AI, which is a distinction that's important to know, and we get into how both individuals and teams can start aren't using them, from automating meeting minutes to building a knowledge agent that fields your team's repetitive questions so that you don't have to. By the end, you'll know exactly what an agent is and have a clear sense of where to start building
one for yourself. Welcome to how IAI with me Doctor Amantha Imba and Neo Applin, head of Inventium AI. Each episode we share one practical way to use AI better at work and in life. No fluff, no tech jargon, just things you can use straight away. Neo, I want to talk about agents today, and I'm sure there's lots of people that know what an agent is, but then there are an awful lot of people that are probably quite confused as to what is an agent? What is
a gentic? Is there a difference? Is that the same thing? How does it relate to my work life? So let's start off with some definitions. What is an agent?
The first thing I'm going to say is the way that these companies have named these things is terrible. There are so many confusing names out there as projects as gpds, there's agents, there's agentic and all those kind of things. So here's how I like to look at it. An agent is generally a thing that we will use. I'm talking now about an agent, a GPT or a project to help you to do something as a reusable expert. In other words, help me to do the thing in
the same way every single time. And what it's not is to do the entire thing. So it's not like an entire workflow. It's just to do one thing. So you might have an agent that maybe checks your work. It might be an agent that potentially you drop in the meeting transcript and will give you the meeting action items and notes and all those kind of things the way that you want your action items and notes to be done.
So it's an agent, okay, And is that different from AGENTICAI.
To go to. Yes, So agentic is where it does the things not in the same way every single time. It's kind of got a goal and it may have some tools and we'll figure out how it's going to reach that goal using the tools, and you leave it to that thing to decide what to do. So, for example, you might have an urgentic thing which has an email tool so it can email in and out and read emails and things like that. It might have file access so it can then access your files and so you
can then give it a goal. Hey, you do this thing, and it might read emails, it might read files, it might figure outs and things, might get attach a file to an email and send it off, so it's like it will decide what to do. Now, with agents, it's more about you needed to be bound to do the same thing the same way every single time, and it's often a smaller thing to achieve in type for example, like a Riunning style guide checkup. You know, it just
does one thing, does it really well? Does it reliably every single time?
And today and for the next few weeks, we are going to be focusing on a gents as opposed to agentic AI. So when it comes to agents, depending on what AI tool you're mostly using, can you took us through like what the equivalents are where they we're in co pilot versus Claude versus Chattipit versus Gemini.
Yeah, Before I do that, I just want to quickly say you do not need to be a geeky rocket scientist AI a kind of person to be able to build an agent AGENTIC Yep. Maybe that's something very different workflows, yep. Maybe, but this is all reasonably easy for just normal regular human beings to be able to do so in the different tools they are called in Copilot's called an agent. That's one I'm going to start there because they've actually
called it that. In Chichipitt it's called a GPT. In Gemini they're called gems, and in Claude generally one ones we're talking about where we're talking about actually projects. Interestingly enough, projects or another kind of term. Chechipt also has projects as a similar kind of thing, and also there are
notebooks in a copilot as well. So these are all different flavors of agents, and the thing that they've all got in common is you can give it an instruction in other words, a prompt, a small or a large prompt. Here's what I want you to do. And you can also give it some files so that it has some knowledge. Maybe it's like a here's a template to use, or it might be here's some knowledge that I need from you.
So it's instructions and a file or files, and that's all you are giving your agent so it can do the thing. So it doesn't have a bunch of tools and it can't just go things by itself. And it's also very responsive like you. It can only do things when someone asks it to do the thing. It doesn't do things at three in the morning. But yeah, so agents, GPTs, projects and gems are generally the names of these things.
Let's talk about how individuals can use them, and then I want to talk about how teams can use agents. And for the purposes of today, we're just going to use the term agents. So what are some of the way that individuals can get value from creating an agent to.
Do the things that you do all the time just to make your life better. So if you are that unfortunately I've done this before, and it sucks to be that person who has to get the meeting transcript and then turn out the minutes and then check the minutes and then email them out to people. If that's something you do every single week or you've got multiple meetings, it's great to build an agent to be able to do that because it then speeds up your time and all you got to do is check what it's done.
So it's like a really helpful small assistant there. You might have something like a voice and style checkert if you'd like. Maybe that's a company one, but maybe that's even just yours, where you might say, hey, i've got some text here, I've got to look after the website.
Maybe you're not a marketing kind of person and you've given a couple of dot points and said, now turn this into Vivee voice and style and sort of then do things like that also good for like bulk emails and things like that, just to make sure it's actually hitting the right beats. So it's something you just do small and often. Other ones might be research assistance. So I've got one which is a research prompt builder. I
think we'll talk about that in another episode. But yeah, when I'm doing researching, I do a lot of research just to make sure I'm keeping up to date on different industries and how AI is going and things like that, and so I've got a research prompt buildup that helps me to build those things up. So the things that you do more than I'm going to say once or twice a week every single week, ask yourself, is this
something that you can put into an agent? Because your job is going to be so different to mine and Amantha's, you'll figure out what you're going to do more often. Maybe that's something you can build into an agent.
Now let's look at teams. How can teams get benefit from agents similar.
Kind of things in order to make their lives better? And so some of them is about the things that you do that you have to do all the time as a team. So maybe meeting minutes is really handy thing. Maybe multiple people are doing meeting minutes. There's that, but maybe there's all things like reports. So there's a way that we produce those types of reports. And sometimes what you want to do is have that same report being kind of built the same way, even though it may
be built by different people. And here's the thing that I might have a different style the way I'll do my report, you'll do your style to the way you do your report. It would be great to have an agent that has like the approved way that it grabs these data in and then crafts it and then puts it into the right headings and things like that. So the things that you and your team do often I think they're really good things to do to build as
an agent. The other thing is the things you wish you wouldn't do, So how can you offload some of those things to AI? So that's another one. And the third is the questions that you often have or that you get as a team. So if you're in HR, I imagine you get an awful lot of questions on how do I change my bank details? When's the next pay run? Those kind of questions. If you're in like a customer service role, you're going to get lots of questions on this thing is broken, how do I fix it?
And then you'll probably know a lot of that in your brain. But wouldn't be better if there was an agent that did a look up of your company procedures or the FAQs and things like that. And of course here's that the other thing, which is why are you answering this questions? Wouldn't be possible to build an agent that answers those questions for those people, so you don't even have to get involved. So it's really useful for
those kind of things. So yeah, if it's often regular you do it the same way as a team, or people are pestering you and your team, then maybe what you can do is create an agent feed at the knowledge with the files and things like that so that people can self service those answers.
So what now and I are going to be doing over the next few weeks is we are going to be digging deeper into agents. So we are going to be unpacking things like, if you're a knowledge worker, what are the must have agents for all knowledge workers. We are going to go into some of the tasks that you should never do manually again, we are going to go into Neo's favorite AG, the one that he uses
pretty much every single day. And we're also going to get into how can you build a knowledge agent that answers every one oh one question like there was just talking about, so that you don't have to So if you want to go deeper into the world of agents, make sure you have hit subscribe or follow, because we will be sharing a lot more info about agents over the coming weeks. How i AI was hosted by me
Amantha Imber and Neo Applan. A big thank you to Martin Imba who does our sound editing, and Jim Rubio for production support, and thank you to John Kilby who composed the theme music.