If you've ever hit send on a document report or slide deck and then immediately thought, hmmm, I hope that lands okay.
This episode is.
For you because producing a high quantity of work isn't the hard part anymore. It's producing high quality, which means checking it, stress testing it, making sure it's clear, accurate, and actually says what you meant before someone else points out the gaps. Now, sure, you can enter a basic prompt into AI to ask it to review your work. But today Neo and I are going to level up the way you can use AI to make your work better and not to replace your judgment, but to sharpen it.
You're gonna learn how to get AI to.
Critique your work properly, not just polish it, ask for feedback on clarity, logic, bias, and gaps, and we're gonna give you one mega prompt to review emails, documents, slides, or anything you like. Really, by the end of this episode, you won't be guessing whether your work is good enough.
You're going to have a clear, repeatable.
Way to pressure test it before it leaves your desk, and the confidence to decide what to change and what to stand by. Welcome to how I AI 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 dech jargon, just things you can use straight away. So on previous episodes, Neo, you've referred to how we can get AI.
To review our own work.
But I want to get into the nitty gritty of how do we do that beyond just a simple prompt like, you know, put your critical thinking hat on AI and tell me what I could improve, Like how do we get a little bit more sophisticated.
You need to tell it what you wanted to do and also tell it exactly what you wanted to review and check. So I've got I've called it Charles, So I've created myself an agent to a GPT and Charles reviews my stuff. Now I've put in a little bit more specifics around it, but at its essence, this more than two sentences is what you need to write. So
I've got review the last response. Of course, you could say review the document, review this thing that I've uploaded, whatever it is, perform a rigorous critique to find anything incorrect. Weekly supported, unclear, incomplete, biased, impractical, verbose, wordy, or improbable. So as you can tell, I'm going through all the bases, I want you to review it and just go through everything that could be wrong with it, then propose better
alternatives and provide a corrected slash revised version. So you could just get away with that one line. So's that's enough to be able to get it to review it. Because what you're being here is about what you want to review it. So you could say I want to find instead off anything incorrect, weekly, supported, unclear, and complete.
You could say anything that is against our policies, anything against you, how our operating process are, or anything against how I think a CFO would want to review this paper, those kind of things. So be specific about how you want your agent, your chat thread to be able to review your work. So that's an easy thing. So review the last response and then put in all those things. And we'll put that prompt in the show notes as well.
And in fact, we will actually do better than that, because I think we're going to have the whole system instructions for Charles.
Is that right?
Oh?
Okay? And if you're infratrate, okay, we're going to give you Charles. So this is what Charles does. So I call it Charles because I use it so often, I may as well give it a name, So we'll give you Charles. So Charles has that task, but Charles also has a couple of steps after that that it follows. So the first is it goes what do I think Neo's really trying to do? And what do I think He's really wanting me to check? And that's a really important thing for you to see. Is AI actually checking
the things that I want it to check? And it understands me. It goes to equality gates. So in other words, what it says is have you passed these main categories and the categories I've given it is factual accuracy, logical soundness, completeness, relevance, clarity, structure, safety, and practicality. So it goes through those and effectively gives me a tick or a cross, so I can see if he goes biased, Okay, I've got to go in there and change those kind of things, or practical sound,
factual accuracy, those kind of things. Then it goes through and tells me some of the main points that I could have added to or I could have changed. So it's effectively a diagnostic audit, so it says how important this is, how confident it is about how important that is, or the problems there. So if you've got a high severity like this is really important, but a low confidence is like, well, I'm not sure i've been to to
your work neo. But if I've interpreted right, high importance those kind of things, it'll tell you what problem it's got, whether it's like a user experience, a structure or clarity whatever, and it tells you what the problem is where and what you can do to fix it. Also gives you
a bunch of alternative approaches. So for these things that you've got in this work, the document, the email you wanted to review, whatever it is, it will then say, here's some alternative approaches on how you can potentially fix this.
So can I understand just day to day because I feel like I hear you use Charles a lot, So what are the kinds of tasks that you're bringing in Charles for? And just to confirm, Charles is a GPT and chat GPT for you, Is that right? Yes, that's great, yes, But equally it could be a project in Chlaude. It could be an agent in co Pilot, it could be a gem in Gemini.
Yes, absolutely, or it could just be a prompt in your prompt library you dump in whenever you need.
Okay, so tell me what are the kinds of tasks that you're using Charles for?
Anything with analysis, I'm getting it to check my analysis. So if I'm doing a review or some kind of a document or whatever, then I'm getting Charles to review that and give me their or its opinion on what I think what it thinks can be improved in this work. Now, by the way, sometimes Charles comes up with suggestions like, yeah, I get that, but no, you don't know the background like I do, and so I don't have to change it. But those kind of things I was running through Charles.
I'd done a social post. We've got online communities for AI people learning AI, and I had already done a social post, and I thought, oh, I forgot to put
that through Charles, and so I posting it. I put the social post into Charles, and it gave me a couple of suggestions on how I could quickly go in there and do some tweaks to make my social post clear out so it can be anything from social posts to emails to documentsy working on analysis as you're doing slide you can give I've given slide decks to in the past, a whole bunch of different things, so pretty
much anything you're doing. If you would love to get a second opinion, then get Charles to give you that second opinion. So I'm not quite there. I still haven't built it into everything I do, but anything important I get Charles to have a look at. But I think it's almost like a spell check, Like we get word to do a spell check and a grammar check for anything we then do and then upload or give to a colleague. It's a good idea to get AI to do a review to see whether you can improve those
things before you give it to those people. Why that review doesn't take much because of course AI is just doing the review. You can agree or disagree with those things, and quite often it's like, oh, that's a really good pickup, and I'm just going to do small tweaks. So it's like the third thing we're doing spell check, grammar check, get it to do a your Charle's check, and of course we're giving you the we're going to give you the COVID Charles, so you can run that yourself.
How well does it work if AI has been primarily responsible for creating the output, Like, let's just say, you know, as sadly many people are, they're just kind of taking shortcuts with AI.
They're being a bit lazy. They're producing some AI slop.
You know, maybe they've put in three bullet points and they're like, write me a three page report that I can give to my bus on this particular topic or project update. Is it good at critiquing its own work when the prompter's been lackluster and you know, maybe the AI's output is actually not that good.
Yeah, I was a bet to joke and say it'll recognize its own handywork and say that's awesome. No, it doesn't do that. It'll even improve AI's output as well. So it's a good thing to get this as a second opinion AI. So if you've been working with A on a document or whatever, even if you have just been like phoning it in and saying five top points, give me a document, it will still review that and
tell you how that could be improved. So don't take AI's output first output as gospel ever, like I prefer, using AI's output is to augment me, not to do the work for me. But yes, you can get it to review AI's output and we'll actually give you a better response and'll actually tell you where the flaws are where it could be improved. So yes, absolutely use it for.
That amazing So for anyone listening, we are very or i should say NEO is very generously sharing Charles with you. All. Just pop into the show notes and there will be a link to get the full text in markdown to paste into your GPT agent project of choice, or.
You can just use it as a mega prompt.
So enjoy Charles, maybe give it its own name, and we will see you next Monday. If you found this useful, please help us spread the AI love and share it with someone who you think would benefit from knowing what you now know. And if you're ready to really start mastering AI, check out inventium dot ai. We help individuals, teams, and organizations turn Jenai into a real work superpower, saving ten plus hours a week and staying future already without the jargon or overwhelmed.
Thanks so much for listening, and we'll see you next time on.
How IAI how i AI was hosted by me Amantha Imber and Neo Applan.
A big thank you to Martin Imber who does our sound editing, and
Jem Rubio for production support, and thank you to John Kilby who composed the theme music.