No‑BS Guide to Effective AI Prompting
Key Points
- The presenter highlights a widespread gap: most AI tutorials are generic, leaving users with specific, real‑world questions (e.g., comparing financial reports, verifying AI answers, polishing emails) that aren’t adequately addressed.
- The session promises a hands‑on, example‑driven “no‑BS” AI class that walks learners through concrete prompts, explains why they succeed, and supplies detailed write‑ups for future reference.
- A key teaching point is prompt engineering: a minimal one‑sentence prompt yields a cold, overly formal response, while adding relevant context and structure produces a far more useful, natural‑tone output.
- By demonstrating the same deadline‑change email request with a richer prompt—including background, desired tone, and specific constraints—the presenter shows how extra “meat on the bone” dramatically improves the AI’s relevance and actionability.
- The overall takeaway is that effective AI use hinges on supplying clear, context‑rich prompts, and the presenter aims to equip participants with the exact phrasing and examples needed to get reliable, practical results.
Sections
- No‑BS Practical AI Guide - The speaker pledges a hands‑on session that addresses real‑world AI doubts—validating answers, refining rewritten text, comparing financial reports—by demonstrating concrete prompt examples and clear, actionable explanations.
- Implementing Shared Deadline Tracker - The speaker proposes using a lightweight shared tracker and weekly snapshots to log deadline changes, allowing AI-generated nudges and process refinements for more effective real‑world task management.
- Prompt‑Guided Meeting Note Extraction - Demonstrates how a precise prompt directs ChatGPT to generate concise, risk‑focused meeting summaries—listing key decisions, open questions, and upcoming actions—while strictly avoiding generic fluff.
- Personalized Prompt Engineering for Finance - It explains the need to train users to craft tailored prompts—such as driver‑delta or factor‑attribution queries—for financial analysis, avoiding generic, bulky prompt collections.
- Explaining Structured Prompting Simply - A parent requests a child‑level explanation of why a typo‑filled prompt succeeds, illustrating how clear, structured prompts guide the AI to provide relevant, helpful responses.
- Iterative AI Email Refinement - The speaker walks through step-by-step prompts to improve an AI‑drafted email, emphasizing clear subject lines, removal of buzzwords, added warmth, and placeholder details.
- Effective Prompt Strategies Explained - The speaker explains why certain prompts reliably work, demonstrates specific and catch‑all examples, and encourages applying them to various job tasks.
Full Transcript
# No‑BS Guide to Effective AI Prompting **Source:** [https://www.youtube.com/watch?v=esqPTMDvw7w](https://www.youtube.com/watch?v=esqPTMDvw7w) **Duration:** 00:24:01 ## Summary - The presenter highlights a widespread gap: most AI tutorials are generic, leaving users with specific, real‑world questions (e.g., comparing financial reports, verifying AI answers, polishing emails) that aren’t adequately addressed. - The session promises a hands‑on, example‑driven “no‑BS” AI class that walks learners through concrete prompts, explains why they succeed, and supplies detailed write‑ups for future reference. - A key teaching point is prompt engineering: a minimal one‑sentence prompt yields a cold, overly formal response, while adding relevant context and structure produces a far more useful, natural‑tone output. - By demonstrating the same deadline‑change email request with a richer prompt—including background, desired tone, and specific constraints—the presenter shows how extra “meat on the bone” dramatically improves the AI’s relevance and actionability. - The overall takeaway is that effective AI use hinges on supplying clear, context‑rich prompts, and the presenter aims to equip participants with the exact phrasing and examples needed to get reliable, practical results. ## Sections - [00:00:00](https://www.youtube.com/watch?v=esqPTMDvw7w&t=0s) **No‑BS Practical AI Guide** - The speaker pledges a hands‑on session that addresses real‑world AI doubts—validating answers, refining rewritten text, comparing financial reports—by demonstrating concrete prompt examples and clear, actionable explanations. - [00:03:13](https://www.youtube.com/watch?v=esqPTMDvw7w&t=193s) **Implementing Shared Deadline Tracker** - The speaker proposes using a lightweight shared tracker and weekly snapshots to log deadline changes, allowing AI-generated nudges and process refinements for more effective real‑world task management. - [00:06:29](https://www.youtube.com/watch?v=esqPTMDvw7w&t=389s) **Prompt‑Guided Meeting Note Extraction** - Demonstrates how a precise prompt directs ChatGPT to generate concise, risk‑focused meeting summaries—listing key decisions, open questions, and upcoming actions—while strictly avoiding generic fluff. - [00:11:14](https://www.youtube.com/watch?v=esqPTMDvw7w&t=674s) **Personalized Prompt Engineering for Finance** - It explains the need to train users to craft tailored prompts—such as driver‑delta or factor‑attribution queries—for financial analysis, avoiding generic, bulky prompt collections. - [00:14:24](https://www.youtube.com/watch?v=esqPTMDvw7w&t=864s) **Explaining Structured Prompting Simply** - A parent requests a child‑level explanation of why a typo‑filled prompt succeeds, illustrating how clear, structured prompts guide the AI to provide relevant, helpful responses. - [00:18:04](https://www.youtube.com/watch?v=esqPTMDvw7w&t=1084s) **Iterative AI Email Refinement** - The speaker walks through step-by-step prompts to improve an AI‑drafted email, emphasizing clear subject lines, removal of buzzwords, added warmth, and placeholder details. - [00:22:08](https://www.youtube.com/watch?v=esqPTMDvw7w&t=1328s) **Effective Prompt Strategies Explained** - The speaker explains why certain prompts reliably work, demonstrates specific and catch‑all examples, and encourages applying them to various job tasks. ## Full Transcript
This is the no BS guide to actually
using AI. I get so many questions that
are actually really reasonable and it
tells me that AI is doing a disservice
to all of you. Like the AI can't teach
it. Google can't teach it. Most of the
people out there are spouting generic
nonsense and you're left asking me
really specific questions like Nate, how
do I compare two financial reports? How
do I know which one is right? or Nate,
AI is giving me an answer and I don't
know if I should believe it or not. Or
Nate, the rewritten email doesn't sound
right. How do I make it sound better?
Over and over again, people are asking
these questions. They're right to ask
them. AI is supposed to be able to help
with this stuff, but we in the teaching
community are doing you all a disservice
because we haven't communicated it
clearly enough with enough good
examples. That's what I'm here to do
today. That is what this time is for. We
are going to get on screen. We're going
to look at some specific examples. We're
going to explain why they work. And
there's going to be lots more examples
in the write up. I want you to walk away
feeling like this is the most concrete,
specific AI class that you have ever
been to. Like you got to spend a lot of
time with Nate hanging out talking about
prompts and getting your real questions
answered. So, with that in mind, let's
get to it. All right. Our first example
is a real example I got questions about.
Help me tell my manager to stop changing
my deadlines. Well, this is the first
version. This is what a lot of people
start with, just one sentence. And to be
honest, the answer isn't too bad, right?
Uh the AI comes back. It thinks for 17
seconds and it gives you an email that
you can send. It gives you a live script
you can deliver. It feels a little bit
cold. Like who wants to tell their
manager, I want to deliver predictably.
When deadlines change after we commit,
we incur rework and slip risk. That
sounds like Chad GPT5 talking, not a
person. Uh, and then you have an
escalation ready and it just keeps going
and going and going and what is your
next step and it tries to give you hope.
I will say it gives you a lot for that
one line, but my question is how usable
is it? How usable is it for that one
line? For example, does it actually work
for you to freeze dates 48 hours before
kickoff or did it just make that up? You
get the idea. The more context you give
the AI, the more it's going to be useful
for you. Why don't we see an example
that is exactly the same question, but
with just a little bit more meat on the
bone for the prompt. And let's see how
Chat GPT5 handles this. Okay, the first
thing that we see is that this is a
longer prompt. Let's break it down and
see what we did. Is it scary? Not too
scary. Uh, it's got some labels, but my
manager changes project deadlines every
week. Usually mentions it in passing.
That's already useful. This is what I
need you to do. Set up a simple process
for deadline changes without seeming
difficult or rigid already. This is
differing from the answer chat GPT5 gave
previously. These are my these are my
boundaries. I can't send sound
accusatory. I can't damage the
relationship. This is what success feels
like to me. And then this is the
audience, my manager. This is the tone,
etc. So, this is very specific, right?
Uh here's what you get. You get a very
specific set of options. You either get
the lightweight tracking option. I
really value how quickly you move things
forward. Your speed helps us respond to
shifting priorities is very much the
sandwich approach to conflict, right?
But when deadlines shift in
conversations, I can miss the update and
realize later. What do you think about
us logging deadline changes in a single
shared tracker? This is a talk track I
could see actually using. This is
immediately more useful. If you want to
go farther, you actually have the option
to write down a little nudge and use
that as part of the method. And so this
is where Chad GPT is actually suggesting
what if whenever you shift a date, I jot
it down and send a oneliner back. This
is both a script and also a suggestion
for a change in process in one go here.
And then there's also the weekly
snapshot. What if we do a weekly
snapshot where we look at the deadlines
and make sure it's right and then it
comes back with if they push back, how
you handle it, assumptions about their
motivation. So it logs it and then you
can refine it from there. What do you
see here? What I see if you compare it
to the initial version is that this is
actually usable for a realworld
situation. And people who are getting
started with AI will say, well, how did
you get it to do that? What is the magic
in this prompt? Well, to be honest, a
lot of the magic in the prompt is giving
the AI enough about you to be helpful.
So, this detail changes project
deadlines weekly. You see that coming
back up in the options. This detail set
up a simple process. You see each of the
options has a simple process. If you
look through this prompt, you can see
that chat GPT has taken each of the
words you've given it really seriously
and tried to come up with something that
puts it all together. And so what you're
giving the AI in a prompt is not a set
of magic words. It's actually enough
context, enough um information about
what you're doing that the AI can be
helpful. So my manager values
flexibility and speed. You'll notice
these talk tracks mention that back
because that's considered good practice.
This is not magic. This is the AI coming
back and trying to mirror what you give
it. If you give it more, it will give
you back more. Let's check out another
real life example with a real life
question mark. I love this one because
it looks like a long prompt, but it's
actually a very realistic short prompt.
This is the prompt up here. Summarize my
meeting notes. That's it. And then this
just pastes in a bunch of meeting notes.
In this case, to protect people's
privacy, I actually had another AI make
up the meeting notes. So, anyway, here
are the meeting notes. There's a
complete transcript. Uh, and then it
comes back with meeting notes, right?
And again, I don't want to underell it.
There's some value here. It captures the
outcomes in the notes. It captures the
feedback. It captures some action items.
This is not too bad, but it's really,
really easy to do a little bit better
than that and make these notes much more
useful. In particular, if you have ever
been in meetings, you know that one of
the really scary things about meetings
is the idea that when we talk back and
forth, sometimes we slide over project
risk that needs to be written down,
formalized, and talked about or else it
just kind of slides under the radar and
we end up discovering it on launch day.
If you've been a project manager, a
product manager, an engineer, uh, in
marketing, you know that feeling. It's
that clenching in your gut. How do you
avoid that? These meeting notes don't
help with that, but that's one of the
most important things that you could
actually get. These risks are fairly
generic. GA delay strains marketing
timelines. Okay, that's fine. Like,
that's really generic. Let's see how a
better prompt with the same transcript
could change things. Okay, the first
thing we notice is there doesn't seem to
be a prompt here, but don't worry, there
is. This is the meeting transcript. If
we click show full message here and we
scroll down, we eventually get to the
prompt right here at the bottom. pull
out and organize. I want a summary of
the main things that happened. I want
key decisions. I want open questions. I
don't think that that one was very
clearly pulled out before. I want risks.
I want the next seven days. And I and
you define the risks. You see how you
define the risk with likelihood impact
and who's on it. And please skip a
section with nothing in it. Please don't
add fluff. That's critical. And you'll
notice how obsessed chat GPT is with
following this. It immediately comes
back with summary of five main things
that happened. It is trying to tell you
with this word that it has paid
attention to don't add fluff or context
and it's taking it really seriously. It
identifies the onboarding bottleneck,
the performance fix, the GA launch, the
pricing tiers. It it gives you all of
this stuff. Okay, so these are your top
five. It gives you decisions that
happened. It gives you open questions
and it gives you risks that are much
much more interesting.
And this by itself is worth the price of
admission for the prompt because you can
then look at that meeting and you can
say, "Oh, you're right. Marcus and David
are supposed to be watching the
performance fixes, but I'm not clear
that they actually have it after I kind
of think through the meeting. Maybe I
should follow up with them." This pulls
out those things that are intangible in
the meeting and makes them tangible. In
other words, chat GPT is actually adding
value here. And it's not adding value
because it's magic. It's adding value
because it is following the instructions
that you gave it. If we come back here,
all we had to do to get that kind of
magical response was to say, "Please
tell me what could go wrong very
specifically, and then say this is what
I care about. I care about the risk, how
likely it is to happen, the impact, and
who's watching it." These are not magic
words. If you wrote uh the risk, the
probability that it's going to occur, uh
what will happen if it occurs, and the
owner, it would still mostly just work
the same way. The point is, can you
explain in really clear words what you
want? Can you explain what matters to
you? And I think we're hanging out here,
right? This is the chat GPT classroom.
One of the things that people really
miss with AI that they struggle with
with AI
is this idea that you can ask for
something that you want that you haven't
seen before done well and it can still
work. When I was keeping notes manually
and yes I did that for a long long time.
I did not often see risks as clearly
laid out as I just showed you. That was
rare. But now, even if I don't have a
good example beyond saying this is what
I want, I can still get it done. And so,
one of the things that I like to tell
people in Chad GPT class is
have the courage to imagine a better way
to do things and then find the words to
express it. That is one of the biggest
keys to prompting. And I find that
people have these light bulb moments
when that happens. are like, "Oh, I can
just ask for it." Yeah, you can ask for
it. You can ask for it. Let's look at
another example, but we're going to make
it more fun. I love this example because
it's a what do I do when I don't have a
prompt example. I have a situation not
covered in Nate's guide. Right? Here's
the situation. I need to compare two
financial reports. I need to understand
the drivers for financial performance
between them. I need you to give me an
answer in 100 words or less. And the
audience is financial professional. Now,
you might think that's the prompt. That
is the context. And I'm going to explain
how you explain that to the AI. It's
very clear. Here's my context. It's four
different bullets right now. This is
what the you're actually asking the AI
to do using the guides methods. Uh and
then you define them here. Ask do clear
format delta only revisions, which means
revisions that are only about the
difference between situations and
verification. Please make a brief
outline of two approaches to handle this
situation. A full prompt to paste into
AI, including the context, the
instructions, the format, and the
verification step. And then please
explain why this works.
That is what you're asking AI to do.
This is an example of asking chat GPT to
write the prompt for you. Your real
instruction here is write the prompt for
me. And if you were in the business of
teaching AI, you have to be able to
explain this because one of the things
that we learned from that survey of 700
million uh chat GPT users that came out
this week is that we have such a wide
range of use cases for AI that we need
that personalized perspective. You need
to be able to teach people to prompt
like this so that they don't have to
carry around a gigantic sheet of all of
these different prompts. like they need
something that works for more than one
thing. So then chat GPT comes back and
it comes back with two options. You have
what it calls a driver delta. It can
highlight changes in revenue, cost,
margins or cash flows between reports A
and B or it can come back with uh
attributing performance shift to
particular volume, price mix or cost
controls and quantify the impact. You
can choose. And so for example, so
here's the full prompt. It's assuming
key drivers. It's assuming number one
here. Uh
we can say actually
please write the factor attribution
approach
prompt instead and it will come back
with the other prompt. And there you go.
It's a full prompt. It's ready for you
to attach those files and get going. Not
by the way because there's a magic word
up here. The only thing you did up here
was you took what would be a generic
prompt and you made it into something
financial with the words that you used.
This is what is telling Chad GPT it's a
financial prompt. You can put anything
in there. You can change it entirely. As
an example of changing entirely, let's
just do this real quick. We'll do it
live. Okay, here we are. We're going to
delete all of the financial report
stuff. You're going to watch this run
live. Going to delete all of these
things. This is the only thing we have
to delete, right? We deleted all of this
stuff. That's super easy. We're going to
change the situation. I need to talk to
my kids teacher about her homework. My
goal have a constructive conversation
and get strategies to help with reading
chapter books.
Constraints
don't want to
break the relationship with the teacher.
I'm deliberately leaving that typo in.
Actually, I want you to remember you can
leave typos in audience. Uh the teacher.
Um
and so I need a prompt for this, right?
I don't know how to even approach this.
Um please help me figure it out. So I
hit go. So it gives me different
options. You can say frame is wanting to
work together. Share a neutral
observation. Um and then it gives me a
frankly nice prompt. I need to talk to
my child's teacher. Please generate two
conversational scripts using a
collaborative ask and an observation
ask. revise into one recommended
version. I love this. I never came up
with this. Chad JPT did this. And then
it explains to me why it works.
Um,
please run the prompt. And then, and you
notice it worked with a typo. And then,
please explain to me like I'm 12 why it
works. Okay. This is giving me words I
wouldn't have been able to find. I
really appreciate how much effort you've
put into helping my child build her
reading skills, especially if it's an
emotional thing. As a parent, these
kinds of scripts are helpful. gives me a
recommendation. Uh, it gives me a sense
of why it thinks it works and it gives
me a sense of the why. Right? If you if
you say you're the expert, what should I
practice? The coach feels respected. It
gives me a metaphor with soccer that
works. Uh, I'm going to go one step
further here to close out our example.
Uh, can you explain uh like I'm 12,
again, I'm leaving the typo, why this
prompting approach works well. Um, how
does prompting like this help you as the
AI help me better? I love this. Think of
me as a fast, eager helper. I sometimes
get carried away. If you say, "Help me
talk to my kids teacher," I might give
you something polite but random because
I don't know what's most important. But
when you use structured prompting,
you're telling me what question you want
me to answer, what action you want me to
take. You're giving me constraints, and
that ultimately helps me help you.
Fantastic. Yes, chat. GPT can help you
prompt. Let's look at one more example.
This one is almost never covered in
classes, and I think that's
disappointing. Most of the time, people
will give you a single prompt like I've
been showing you, and then they'll be
like, "Go and be well. You have your
prompt." You know, you have Nate's
master prompt. You're off you go. Well,
what if you aren't that person? What if
you're having a conversation? How do you
have a conversation that progressively
reveals the information you need? So,
for example, again, a real question. You
get to a more human sounding email. And
so, here's an initial situation.
Already, this is fine, right? I run a
design agency. A client's been with us
for 3 years. They want to rush the
project. I need to turn them down nicely
without ruining the relationship. Please
keep it short. Uh, please don't use bud
buzzwords. Uh, and if they can
understand that that we can't help now,
but they'll reach out later, that's
great. It comes back. This is okay.
It's kind of it still feels wordy. I
feel like I would not send this because
it feels like a wall of text to a
client. Uh, and so I want to give the I
want to give the the AI a little bit
more context to help me. Okay, so this
is a CMO. I worked with them for years.
You need you need to know that, right? I
need friendly but professional tone like
I'm talking to a colleague. Um, and
someone else they could work with is
something that I want to include here
because you just realize that right as
you're reading the draft. So comes back.
Uh, it's a little better. I'm grateful
you reached out. We've really valued
working together. There is a
recommendation in here. Uh, it still
feels a bit like a wall of text. Um, and
so I just want some advice. And so I I
just ask that, right? Actually, you know
what? Before writing anything, please
give me two different ways I could
handle the decline. Ask me a question
about the situation that might help you
to write better. And this is a great
example in a multi-turn conversation
where you can actually throw the ball
back to chat GPT and you can ask it to
ask you, right? you can ask it to give
you tips and that will be really
helpful. So it comes back, it says you
can protect the relationship with a
really clear referral or you can
position it very much as a timing issue
and emphasize future work more. And so
it's taking from what you've told it and
saying which do you want me to emphasize
and then it's asking do you want the
referral to be the heart of the message
or something that's lighter that you
might try in the meantime and that's a
really nuanced question that we haven't
given a perspective on. And so I looked
at that and I'm like, I think I want a
clear referral. You could have picked
either one, but I went with option one.
All I say is go with one. It drafts it
out. This is already better. It's two
paragraphs. It's more scannable rather
than risk a rushed outcome. It's still a
little cold. Uh and I feel like I'm
worried that the buzzwords are still in
there. So I'm saying skip the buzzwords.
I need to have the subject line really
clear and I need to have the email
itself. And I that's that's all I want
us to sort of focus on. I don't want it
to be I don't want it to be anything but
what I need to check and read. And I
feel like right now when I look at it,
it's better, but there's still something
missing. And so I'm basically trying to
get the AI to give me some clarity,
especially around the subject line. So
now we have this a quick note on the
Rush project. Uh on timing for this
project as a backup. Uh this is already
better. It dumps the buzz. Dumping the
buzzwords was really good, right? I'm
glad you thought of us. We've loved
working with you. That feels really
natural. the M dash might be a little
bit of a giveaway depending on who you
believe about chat GPT writing but still
it's it's not bad uh and then I ask it
this look at what you wrote and I want
you to tell me is it specific enough are
we naming dates and steps now I haven't
given it dates and steps but I want
placeholders does it sound warm enough
please list five things you changed to
improve it you see how I'm basically
leading the AI through an edit
conversation I'm not just leaving it
alone I'm not saying this is good enough
people might have taken these and said,
"Ah, I don't know. I don't know. I don't
know." Uh, and you might be saying to
yourself, "This is a lot of edits for an
email." But think about it. This is a
client that may be a six-f figureure
client for this for this small firm.
They don't want to lose them. They just
need to delay things a bit. It
absolutely is worth a 5minute
conversation with Chad GPT to get to a
better email. Okay. Is it specific
enough? Chad GPT admits not quite. Does
it sound warm enough? It's clipped. I
agree. Here's some things I could do to
include it or in not include it, improve
it. Here's a revised version. We valued
your trust for this rush request. I need
to be honest. We can't give it the focus
it deserves. I recommend this is very
readable. It looks like it's almost
there. Uh for this final version, tell
me what assumptions are you making? How
confident are you that this keeps the
relationship strong? And what's one
thing I should double check? You can
actually ask them to double check it.
Make sure the referral you name is
reliable as the double check
recommendation. I agree that sounds like
an important. So there you go. What we
have here is something that is now ready
to paste in that is quite strong. It may
not be perfect but it is strong enough
that it is 90 95% there for a delicate
email to a highv value six or seven
figure client. We did not start there.
You do not have to start with perfect
with AI to get it where you want to go.
And I want to go back through and note
we're sort of following stream of
thought and all we're doing is taking
enough time to add the words so the AI
knows how to key off of us so that it
can be as helpful as possible. List
exactly five small things you change to
improve it is just a little bit more
precise than tell me what you'd fix.
Those are the kinds of small differences
that aren't magic. They just help the AI
help us. I hope that this has been a uh
helpful multi-turn conversation to look
through. I know we don't do a ton of
these and I think it's really important
to look at them because they show how we
can follow our own train of thought and
still get somewhere really useful with
an AI. So, I want to close by going back
to some of the things that people have
been asking me initially and reframing
them as larger questions that I see all
over the internet that I see in my inbox
and how we're answering them. So, how do
I get better responses out of AI? That's
one of the underlying questions. All I'm
saying is give the AI enough context to
help you. When I gave you those answers,
I on purpose used the same kinds of
labels in every single one. The
situation, what I need, my constraints,
what success looks like. You can name
those different things. But those are
some basic categories of meaning,
categories of words that if you give
that to AI, it can go farther for you.
What prompts actually work? That's
another one that I get a lot. These
prompts work. I gave you real scenarios.
They actually work. And they don't work
because I wrote them. They don't work
because they're magic. They work. And I
hope you can see this because they give
the AI the information it needs. I also
hear a lot, I need examples for my
specific job. Whether that's boss
conversations, emails, meeting notes,
whatever. I gave you some of those
specific examples, but inevitably you're
going to think of some that I didn't
cover because this is only going to be
so long. That is what those larger
catchall prompts are for. And that's why
I deliberately illustrated one of my
examples, the financial analysis one
with a catch-all prompt. You are
empowered to go take that kind of a
prompt and put it to use for your
situation. And that is why I spent so
much time showing you the actual
prompts. It's not because I wanted to
bore you. It's because I wanted you to
understand how they work and I wanted
you to see them really play out side by
side so you could see I'm not just
trying to make stuff up. I'm not just
trying to tell you more words are
better. I'm trying to give you clarity.
I'm trying to give you the ability to
get help from the AI. So if you take
anything away from this class on AI,
please take away a sense that it is not
that hard to get to can use AI in many
of my tasks every day. The prompts that
I have just laid out for you covers so
many different real work situations. All
you have to do is slightly change the
situation and what you need from the AI
and your goal in situation and the
context you give it and you're going to
be off to the races. You can use an AI
to get a better answer. You can shape
what you get from chat GPT so it is more
useful and we've seen so many examples
of how to do that. Over to you. Best of
luck and enjoy chat GPT. It is really an
amazing tool and I hope that this has
helped you use it better.