June 23, 2025 • 9 mins
Want to learn how to architect your prompts like a pro and unlock 10+ hours of your week? Join Inventium’s GenAI Productivity Upgrade. Spots are limited, and the next cohort starts July 14. Find out more and sign up at https://inventium.com.au/genai-cohort/
***
If you’re wrestling with Gen AI prompts - getting outputs that are “just okay” and wasting time going back and forth, you’re probably doing it wrong. Neo Aplin, Inventium’s Gen AI expert, calls this “gunslinging.” It’s a fast-and-loose approach that leads to mediocre results. The smarter way? It’s called “architecting”- a method that helps you co-create with AI for complex tasks like strategy papers, training workshops, and reports.
In this episode, Neo breaks down how to use architecting to get AI working like a true thinking partner and not just a text generator.
We discuss:
- Why “gunslinging” leads to frustration and wasted time
- How to “architect” your AI prompts for better results
- The types of tasks where architecting will supercharge your work
- Tips for using architecting with tools like ChatGPT, Gemini, and Copilot
Key quotes:
“Most people are gunslingers - they shoot from the hip and hope for the best.”
“Architecting is like designing a house before you build it. It makes the whole process faster, smoother, and way more effective.”
“If you want AI to work as a true thinking partner, you need to co-create with it - not just give it a prompt and hope for the best.”
My latest book The Health Habit is out now. You can order a copy here: https://www.amantha.com/the-health-habit/
Connect with me on the socials: Linkedin (https://www.linkedin.com/in/amanthaimber)
Instagram (https://www.
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Speaker 1 (00:00):
Today, I am back with Neo Applan, Inventium's Genai expert
to help unpack a very cool concept that he recently
shared with me. It's about gunslinging versus architecting, and it's
all about how you work with AI. So if you
have ever found yourself wrestling with chat, GPT or one
(00:24):
of the other jenai is to get it just right,
then this episode is for you. Welcome to How I Work,
a show about habits, rituals, and strategies for optimizing your day.
I'm your host, doctor Amantha Imber. Two years ago, I
(00:45):
completely overhauled how I work with Genai and I'm now
saving over forty hours every single week. That is no exaggeration,
and that's exactly why my company, Inventium created the Genai
Productivity Upgrade. It's a twelve week course designed to move
you from AI doubler to productivity machine. No fluff, just
(01:07):
practical strategies that will pay off from week one, saving
you at least ten hours every single week. You'll learn
how to make AI sound exactly like you use AI
as your second brain to excel at your job, and
so much more. Whether you're a complete beginner or already dabbling.
We've got you covered, starting with prompting fundamentals and going
(01:28):
all the way through to advanced automations and agentic AI.
We kick off on July fourteen, and spots are limited.
Visit inventium dot com, dot au, forward slash Jenai hyphen
cohort to secure your place now, there's a link to
that in the show notes, and you've got nothing to
lose because there's a seven day money back guarantee, So
(01:49):
head to the link in the show notes and check
out the program today. So, Neo, you say that most
people are gunslingers when they prompt Jenai, Can you tell
me what you mean by that.
Speaker 2 (02:03):
Yeah, it's a metaphor. It's not a technical term. It's
how some people work with jen Ai. It's effectively, get
a decent enough prompt, shoot from the hip and hope
and pray that it's going to go pretty well. Just
as gun slinging isn't the most accurate way that you
can hit a target, same thing with prompting gun slinging,
where you've got a pretty average prompt, you've shot it
(02:24):
out there, chances are it won't hit the bull's eye
every time. And so what you're finding is you then
have to have a discussion with the AI to improve
the output. I mean a little bit more of this,
a little less so that it can go from a
discussion to feeling very much like a debate and argument
with AI to get what you're really after. So the
first prompt might be fast, but then the cleaning up
(02:45):
is a very long task and can get frustrating after time,
lots of back and forth refining, so it can be
time consuming and inefficient if you're doing anything beyond kind
of basic prompting or basic tasks.
Speaker 1 (02:57):
Okay, so then there is what you call architect What
does that look like instead.
Speaker 2 (03:03):
Well, instead of shooting from the hip, it's much more deliberate,
it's much more collaborative with the AI, and it's more
likely to get you a great result and certainly faster
than gunslinging. And that there's a lot less refinement and
a lot less arguing with AI. So what you do is,
first off, you need to agree with AI and what
your goals are. Now, notice I say to agree, So
(03:24):
you need to say, here's what my goals are, and
you need to make sure that AI understands those goals.
So here's what I'm trying to achieve. Then you also
work with it on things like best practice or structure
or all those kind of things before it starts writing
anything else. So it's effectively you're working with it as
a planning partner and getting it to challenge your ideas,
(03:46):
getting it to challenge its own ideas, so it knows
the structure, what you're trying to achieve, what best practice is,
before you get it to write the thing. So it's
almost like designing a house before you build it. You
don't want to just build a house first. You want
to design it first, and then when it's already designed,
then you go and get the builders to come on
and to build the thing.
Speaker 1 (04:05):
Okay, so I'm obviously not going to use architecting when
I'm writing a simple email. So I'm wondering what are
the kinds of tasks that architecting is best suited for.
Speaker 2 (04:18):
Anything it's complex or that you need to get a
great result at where good enough isn't isn't enough, isn't
good enough? You need to get something it's excellent. So
things like if you're working on a strategy paper or
training sessions or workshop design or any kind of report
or analysis and all those kind of things, something where
you need to make sure that it's grounding it in
(04:40):
background and science and industry best practices and things like that,
where you want to get a great result, This is
where I would use architecting. So if you need a
structured output or some thinking through it, it's really good
for that. So if you wanted to have something which
is average or it's quick, fine, gunsling, like if I'm
doing emails off gunsling thing is fine. But if I
(05:01):
want to get a document or a structure, or I
want to, as I said, a team workshop. If I
want a great team workshop, then why don't I get
architecting to help me to build something even better. It
works great with all the different ais, I should say,
but in some of them it works better. So copilot
architecting is brilliant. It does such a much better job
(05:21):
than just average copilot gun slinging.
Speaker 1 (05:24):
And if I'm using chat ept, as I know a
lot of listeners do, should I be choosing one of
their logic models for this or any models? Fine?
Speaker 2 (05:33):
Yes, the logic models, and these are the ones that
start in O so three to four, etc. The logic
models are excellent for these kind of things. But they
do a better job when you do architecting, because what
you're still doing is you're working with the GENAI on
what the goals are and things like best practice rather
than letting it think. You're working with the GENAI to
(05:54):
be able to architect this together, and those logic models
do give you a better result. So yeah, do use
the architecting, and those models you over next level the result.
Speaker 1 (06:04):
So NIO, I would love you to walk me through
an example, like, let's just say I don't know you're
designing a team building session for a client off site
or maybe your own team's off site. How would you
use architecting to go through that task?
Speaker 2 (06:23):
I would first start with the context, So here, I'm
planning on building a team off site, and I'd like
to build a structure with you. Tell it what your
goals are. After that, I'd get it to ask itself
what best practice is? Are there ways that I can
achieve this goal even better? Get it to even review
its own work to see whether it can improve it.
(06:45):
What's the science behind team performance? All those kind of
things to get it to think through all the best
practice paths on how to build a great team workshop,
I might work with it on say, structure, how would
I structure these kind of things? What kind of activities
would work. I'm not getting it to build the workshop
or even the final output yet. I'm getting it to
(07:05):
work through best practice, how it aligns with my goals?
Are there better ways to do it? All those kind
of things. Once I'm comfortable it's nailed what I'm trying
to achieve, it understands best practice, it's refined as much
as I think it needs to, then I'll go, Okay,
let's build these things together. Then it will go through
and actually build me a workshop, and it will say
(07:26):
how and Wyatt's built the workshop for that best practice
and how it will deliver to what I'm trying to
achieve with those goals.
Speaker 1 (07:33):
And then I imagine you could break it down even
further to go, okay, can we work on the morning
segment first? And then let's work on the segment that
is just before lunch and so on and so forth,
as opposed to okay, build out the full agenda is
Have I got my thinking right on that?
Speaker 2 (07:48):
Absolutely? Yeah? And this is really good for you. You've
got a big document, say I'd be working on it
with the goals the strategies what you need to do
in the document, and then once you're comfortable with we'll
call it like index or a table of contents, then
you'd build out chapter by chapter, section by section, and
that's much better to do it that way. That way
it will give you a better result and it won't
(08:10):
go off track at all. So yes, structure first and
then section by section is the best way to architect
and best way to get the results.
Speaker 1 (08:17):
Neo, thank you so much for coming on again. I
know that we have recently in our own GENAI workshops
been talking about these terms architecting and gunslinging, and I
feel like there is that aha moment when people start
to actually put this into action. So if this is
resonated with you, I strongly recommend give architecting a go
(08:40):
today when you are working with the AI to work
on a complex task. If you like today's Joe, make
sure you hit follow on your podcast app to be
alerted when new episodes drop. How I Work was recorded
on the traditional land of the Warrangery people, part of
the Cooler Nation. A big thank you to Martin Nimber
for doing this sound mix
Today, I am back with Neo Applan, Inventium's Genai expert
to help unpack a very cool concept that he recently
shared with me. It's about gunslinging versus architecting, and it's
all about how you work with AI. So if you
have ever found yourself wrestling with chat, GPT or one
(00:24):
of the other jenai is to get it just right,
then this episode is for you. Welcome to How I Work,
a show about habits, rituals, and strategies for optimizing your day.
I'm your host, doctor Amantha Imber. Two years ago, I
(00:45):
completely overhauled how I work with Genai and I'm now
saving over forty hours every single week. That is no exaggeration,
and that's exactly why my company, Inventium created the Genai
Productivity Upgrade. It's a twelve week course designed to move
you from AI doubler to productivity machine. No fluff, just
(01:07):
practical strategies that will pay off from week one, saving
you at least ten hours every single week. You'll learn
how to make AI sound exactly like you use AI
as your second brain to excel at your job, and
so much more. Whether you're a complete beginner or already dabbling.
We've got you covered, starting with prompting fundamentals and going
(01:28):
all the way through to advanced automations and agentic AI.
We kick off on July fourteen, and spots are limited.
Visit inventium dot com, dot au, forward slash Jenai hyphen
cohort to secure your place now, there's a link to
that in the show notes, and you've got nothing to
lose because there's a seven day money back guarantee, So
(01:49):
head to the link in the show notes and check
out the program today. So, Neo, you say that most
people are gunslingers when they prompt Jenai, Can you tell
me what you mean by that.
Speaker 2 (02:03):
Yeah, it's a metaphor. It's not a technical term. It's
how some people work with jen Ai. It's effectively, get
a decent enough prompt, shoot from the hip and hope
and pray that it's going to go pretty well. Just
as gun slinging isn't the most accurate way that you
can hit a target, same thing with prompting gun slinging,
where you've got a pretty average prompt, you've shot it
(02:24):
out there, chances are it won't hit the bull's eye
every time. And so what you're finding is you then
have to have a discussion with the AI to improve
the output. I mean a little bit more of this,
a little less so that it can go from a
discussion to feeling very much like a debate and argument
with AI to get what you're really after. So the
first prompt might be fast, but then the cleaning up
(02:45):
is a very long task and can get frustrating after time,
lots of back and forth refining, so it can be
time consuming and inefficient if you're doing anything beyond kind
of basic prompting or basic tasks.
Speaker 1 (02:57):
Okay, so then there is what you call architect What
does that look like instead.
Speaker 2 (03:03):
Well, instead of shooting from the hip, it's much more deliberate,
it's much more collaborative with the AI, and it's more
likely to get you a great result and certainly faster
than gunslinging. And that there's a lot less refinement and
a lot less arguing with AI. So what you do is,
first off, you need to agree with AI and what
your goals are. Now, notice I say to agree, So
(03:24):
you need to say, here's what my goals are, and
you need to make sure that AI understands those goals.
So here's what I'm trying to achieve. Then you also
work with it on things like best practice or structure
or all those kind of things before it starts writing
anything else. So it's effectively you're working with it as
a planning partner and getting it to challenge your ideas,
(03:46):
getting it to challenge its own ideas, so it knows
the structure, what you're trying to achieve, what best practice is,
before you get it to write the thing. So it's
almost like designing a house before you build it. You
don't want to just build a house first. You want
to design it first, and then when it's already designed,
then you go and get the builders to come on
and to build the thing.
Speaker 1 (04:05):
Okay, so I'm obviously not going to use architecting when
I'm writing a simple email. So I'm wondering what are
the kinds of tasks that architecting is best suited for.
Speaker 2 (04:18):
Anything it's complex or that you need to get a
great result at where good enough isn't isn't enough, isn't
good enough? You need to get something it's excellent. So
things like if you're working on a strategy paper or
training sessions or workshop design or any kind of report
or analysis and all those kind of things, something where
you need to make sure that it's grounding it in
(04:40):
background and science and industry best practices and things like that,
where you want to get a great result, This is
where I would use architecting. So if you need a
structured output or some thinking through it, it's really good
for that. So if you wanted to have something which
is average or it's quick, fine, gunsling, like if I'm
doing emails off gunsling thing is fine. But if I
(05:01):
want to get a document or a structure, or I
want to, as I said, a team workshop. If I
want a great team workshop, then why don't I get
architecting to help me to build something even better. It
works great with all the different ais, I should say,
but in some of them it works better. So copilot
architecting is brilliant. It does such a much better job
(05:21):
than just average copilot gun slinging.
Speaker 1 (05:24):
And if I'm using chat ept, as I know a
lot of listeners do, should I be choosing one of
their logic models for this or any models? Fine?
Speaker 2 (05:33):
Yes, the logic models, and these are the ones that
start in O so three to four, etc. The logic
models are excellent for these kind of things. But they
do a better job when you do architecting, because what
you're still doing is you're working with the GENAI on
what the goals are and things like best practice rather
than letting it think. You're working with the GENAI to
(05:54):
be able to architect this together, and those logic models
do give you a better result. So yeah, do use
the architecting, and those models you over next level the result.
Speaker 1 (06:04):
So NIO, I would love you to walk me through
an example, like, let's just say I don't know you're
designing a team building session for a client off site
or maybe your own team's off site. How would you
use architecting to go through that task?
Speaker 2 (06:23):
I would first start with the context, So here, I'm
planning on building a team off site, and I'd like
to build a structure with you. Tell it what your
goals are. After that, I'd get it to ask itself
what best practice is? Are there ways that I can
achieve this goal even better? Get it to even review
its own work to see whether it can improve it.
(06:45):
What's the science behind team performance? All those kind of
things to get it to think through all the best
practice paths on how to build a great team workshop,
I might work with it on say, structure, how would
I structure these kind of things? What kind of activities
would work. I'm not getting it to build the workshop
or even the final output yet. I'm getting it to
(07:05):
work through best practice, how it aligns with my goals?
Are there better ways to do it? All those kind
of things. Once I'm comfortable it's nailed what I'm trying
to achieve, it understands best practice, it's refined as much
as I think it needs to, then I'll go, Okay,
let's build these things together. Then it will go through
and actually build me a workshop, and it will say
(07:26):
how and Wyatt's built the workshop for that best practice
and how it will deliver to what I'm trying to
achieve with those goals.
Speaker 1 (07:33):
And then I imagine you could break it down even
further to go, okay, can we work on the morning
segment first? And then let's work on the segment that
is just before lunch and so on and so forth,
as opposed to okay, build out the full agenda is
Have I got my thinking right on that?
Speaker 2 (07:48):
Absolutely? Yeah? And this is really good for you. You've
got a big document, say I'd be working on it
with the goals the strategies what you need to do
in the document, and then once you're comfortable with we'll
call it like index or a table of contents, then
you'd build out chapter by chapter, section by section, and
that's much better to do it that way. That way
it will give you a better result and it won't
(08:10):
go off track at all. So yes, structure first and
then section by section is the best way to architect
and best way to get the results.
Speaker 1 (08:17):
Neo, thank you so much for coming on again. I
know that we have recently in our own GENAI workshops
been talking about these terms architecting and gunslinging, and I
feel like there is that aha moment when people start
to actually put this into action. So if this is
resonated with you, I strongly recommend give architecting a go
(08:40):
today when you are working with the AI to work
on a complex task. If you like today's Joe, make
sure you hit follow on your podcast app to be
alerted when new episodes drop. How I Work was recorded
on the traditional land of the Warrangery people, part of
the Cooler Nation. A big thank you to Martin Nimber
for doing this sound mix
Popular Podcasts
United States of Kennedy
United States of Kennedy is a podcast about our cultural fascination with the Kennedy dynasty. Every week, hosts Lyra Smith and George Civeris go into one aspect of the Kennedy story.
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com