Latest / How I Work / Are you a GenAI Gunslinger? Why your approach is costing you results.
Transcript
- 0:00Speaker 1: Today, I am back with Neo Applan, Inventium's Genai expert
- 0:06Speaker 1: to help unpack a very cool concept that he recently
- 0:11Speaker 1: shared with me. It's about gunslinging versus architecting, and it's
- 0:16Speaker 1: all about how you work with AI. So if you
- 0:20Speaker 1: have ever found yourself wrestling with chat, GPT or one
- 0:24Speaker 1: of the other jenai is to get it just right,
- 0:27Speaker 1: then this episode is for you. Welcome to How I Work,
- 0:36Speaker 1: a show about habits, rituals, and strategies for optimizing your day.
- 0:41Speaker 1: I'm your host, doctor Amantha Imber. Two years ago, I
- 0:45Speaker 1: completely overhauled how I work with Genai and I'm now
- 0:50Speaker 1: saving over forty hours every single week. That is no exaggeration,
- 0:55Speaker 1: and that's exactly why my company, Inventium created the Genai
- 0:59Speaker 1: Productivity Upgrade. It's a twelve week course designed to move
- 1:03Speaker 1: you from AI doubler to productivity machine. No fluff, just
- 1:07Speaker 1: practical strategies that will pay off from week one, saving
- 1:11Speaker 1: you at least ten hours every single week. You'll learn
- 1:14Speaker 1: how to make AI sound exactly like you use AI
- 1:17Speaker 1: as your second brain to excel at your job, and
- 1:21Speaker 1: so much more. Whether you're a complete beginner or already dabbling.
- 1:25Speaker 1: We've got you covered, starting with prompting fundamentals and going
- 1:28Speaker 1: all the way through to advanced automations and agentic AI.
- 1:32Speaker 1: We kick off on July fourteen, and spots are limited.
- 1:36Speaker 1: Visit inventium dot com, dot au, forward slash Jenai hyphen
- 1:40Speaker 1: cohort to secure your place now, there's a link to
- 1:43Speaker 1: that in the show notes, and you've got nothing to
- 1:45Speaker 1: lose because there's a seven day money back guarantee, So
- 1:49Speaker 1: head to the link in the show notes and check
- 1:51Speaker 1: out the program today. So, Neo, you say that most
- 1:56Speaker 1: people are gunslingers when they prompt Jenai, Can you tell
- 2:00Speaker 1: me what you mean by that.
- 2:03Speaker 2: Yeah, it's a metaphor. It's not a technical term. It's
- 2:06Speaker 2: how some people work with jen Ai. It's effectively, get
- 2:09Speaker 2: a decent enough prompt, shoot from the hip and hope
- 2:12Speaker 2: and pray that it's going to go pretty well. Just
- 2:14Speaker 2: as gun slinging isn't the most accurate way that you
- 2:17Speaker 2: can hit a target, same thing with prompting gun slinging,
- 2:21Speaker 2: where you've got a pretty average prompt, you've shot it
- 2:24Speaker 2: out there, chances are it won't hit the bull's eye
- 2:27Speaker 2: every time. And so what you're finding is you then
- 2:29Speaker 2: have to have a discussion with the AI to improve
- 2:32Speaker 2: the output. I mean a little bit more of this,
- 2:33Speaker 2: a little less so that it can go from a
- 2:36Speaker 2: discussion to feeling very much like a debate and argument
- 2:39Speaker 2: with AI to get what you're really after. So the
- 2:42Speaker 2: first prompt might be fast, but then the cleaning up
- 2:45Speaker 2: is a very long task and can get frustrating after time,
- 2:48Speaker 2: lots of back and forth refining, so it can be
- 2:51Speaker 2: time consuming and inefficient if you're doing anything beyond kind
- 2:54Speaker 2: of basic prompting or basic tasks.
- 2:57Speaker 1: Okay, so then there is what you call architect What
- 3:00Speaker 1: does that look like instead.
- 3:03Speaker 2: Well, instead of shooting from the hip, it's much more deliberate,
- 3:05Speaker 2: it's much more collaborative with the AI, and it's more
- 3:09Speaker 2: likely to get you a great result and certainly faster
- 3:13Speaker 2: than gunslinging. And that there's a lot less refinement and
- 3:16Speaker 2: a lot less arguing with AI. So what you do is,
- 3:19Speaker 2: first off, you need to agree with AI and what
- 3:22Speaker 2: your goals are. Now, notice I say to agree, So
- 3:24Speaker 2: you need to say, here's what my goals are, and
- 3:26Speaker 2: you need to make sure that AI understands those goals.
- 3:29Speaker 2: So here's what I'm trying to achieve. Then you also
- 3:32Speaker 2: work with it on things like best practice or structure
- 3:36Speaker 2: or all those kind of things before it starts writing
- 3:40Speaker 2: anything else. So it's effectively you're working with it as
- 3:42Speaker 2: a planning partner and getting it to challenge your ideas,
- 3:46Speaker 2: getting it to challenge its own ideas, so it knows
- 3:49Speaker 2: the structure, what you're trying to achieve, what best practice is,
- 3:52Speaker 2: before you get it to write the thing. So it's
- 3:54Speaker 2: almost like designing a house before you build it. You
- 3:57Speaker 2: don't want to just build a house first. You want
- 3:59Speaker 2: to design it first, and then when it's already designed,
- 4:02Speaker 2: then you go and get the builders to come on
- 4:03Speaker 2: and to build the thing.
- 4:05Speaker 1: Okay, so I'm obviously not going to use architecting when
- 4:10Speaker 1: I'm writing a simple email. So I'm wondering what are
- 4:13Speaker 1: the kinds of tasks that architecting is best suited for.
- 4:18Speaker 2: Anything it's complex or that you need to get a
- 4:21Speaker 2: great result at where good enough isn't isn't enough, isn't
- 4:25Speaker 2: good enough? You need to get something it's excellent. So
- 4:27Speaker 2: things like if you're working on a strategy paper or
- 4:30Speaker 2: training sessions or workshop design or any kind of report
- 4:34Speaker 2: or analysis and all those kind of things, something where
- 4:37Speaker 2: you need to make sure that it's grounding it in
- 4:40Speaker 2: background and science and industry best practices and things like that,
- 4:44Speaker 2: where you want to get a great result, This is
- 4:46Speaker 2: where I would use architecting. So if you need a
- 4:49Speaker 2: structured output or some thinking through it, it's really good
- 4:53Speaker 2: for that. So if you wanted to have something which
- 4:55Speaker 2: is average or it's quick, fine, gunsling, like if I'm
- 4:58Speaker 2: doing emails off gunsling thing is fine. But if I
- 5:01Speaker 2: want to get a document or a structure, or I
- 5:03Speaker 2: want to, as I said, a team workshop. If I
- 5:05Speaker 2: want a great team workshop, then why don't I get
- 5:08Speaker 2: architecting to help me to build something even better. It
- 5:11Speaker 2: works great with all the different ais, I should say,
- 5:14Speaker 2: but in some of them it works better. So copilot
- 5:18Speaker 2: architecting is brilliant. It does such a much better job
- 5:21Speaker 2: than just average copilot gun slinging.
- 5:24Speaker 1: And if I'm using chat ept, as I know a
- 5:27Speaker 1: lot of listeners do, should I be choosing one of
- 5:29Speaker 1: their logic models for this or any models? Fine?
- 5:33Speaker 2: Yes, the logic models, and these are the ones that
- 5:35Speaker 2: start in O so three to four, etc. The logic
- 5:39Speaker 2: models are excellent for these kind of things. But they
- 5:41Speaker 2: do a better job when you do architecting, because what
- 5:46Speaker 2: you're still doing is you're working with the GENAI on
- 5:48Speaker 2: what the goals are and things like best practice rather
- 5:51Speaker 2: than letting it think. You're working with the GENAI to
- 5:54Speaker 2: be able to architect this together, and those logic models
- 5:57Speaker 2: do give you a better result. So yeah, do use
- 6:00Speaker 2: the architecting, and those models you over next level the result.
- 6:04Speaker 1: So NIO, I would love you to walk me through
- 6:07Speaker 1: an example, like, let's just say I don't know you're
- 6:10Speaker 1: designing a team building session for a client off site
- 6:16Speaker 1: or maybe your own team's off site. How would you
- 6:19Speaker 1: use architecting to go through that task?
- 6:23Speaker 2: I would first start with the context, So here, I'm
- 6:25Speaker 2: planning on building a team off site, and I'd like
- 6:28Speaker 2: to build a structure with you. Tell it what your
- 6:31Speaker 2: goals are. After that, I'd get it to ask itself
- 6:35Speaker 2: what best practice is? Are there ways that I can
- 6:39Speaker 2: achieve this goal even better? Get it to even review
- 6:42Speaker 2: its own work to see whether it can improve it.
- 6:45Speaker 2: What's the science behind team performance? All those kind of
- 6:48Speaker 2: things to get it to think through all the best
- 6:51Speaker 2: practice paths on how to build a great team workshop,
- 6:54Speaker 2: I might work with it on say, structure, how would
- 6:56Speaker 2: I structure these kind of things? What kind of activities
- 6:58Speaker 2: would work. I'm not getting it to build the workshop
- 7:02Speaker 2: or even the final output yet. I'm getting it to
- 7:05Speaker 2: work through best practice, how it aligns with my goals?
- 7:08Speaker 2: Are there better ways to do it? All those kind
- 7:11Speaker 2: of things. Once I'm comfortable it's nailed what I'm trying
- 7:14Speaker 2: to achieve, it understands best practice, it's refined as much
- 7:18Speaker 2: as I think it needs to, then I'll go, Okay,
- 7:21Speaker 2: let's build these things together. Then it will go through
- 7:24Speaker 2: and actually build me a workshop, and it will say
- 7:26Speaker 2: how and Wyatt's built the workshop for that best practice
- 7:29Speaker 2: and how it will deliver to what I'm trying to
- 7:31Speaker 2: achieve with those goals.
- 7:33Speaker 1: And then I imagine you could break it down even
- 7:35Speaker 1: further to go, okay, can we work on the morning
- 7:38Speaker 1: segment first? And then let's work on the segment that
- 7:41Speaker 1: is just before lunch and so on and so forth,
- 7:44Speaker 1: as opposed to okay, build out the full agenda is
- 7:47Speaker 1: Have I got my thinking right on that?
- 7:48Speaker 2: Absolutely? Yeah? And this is really good for you. You've
- 7:50Speaker 2: got a big document, say I'd be working on it
- 7:53Speaker 2: with the goals the strategies what you need to do
- 7:56Speaker 2: in the document, and then once you're comfortable with we'll
- 7:59Speaker 2: call it like index or a table of contents, then
- 8:02Speaker 2: you'd build out chapter by chapter, section by section, and
- 8:05Speaker 2: that's much better to do it that way. That way
- 8:08Speaker 2: it will give you a better result and it won't
- 8:10Speaker 2: go off track at all. So yes, structure first and
- 8:12Speaker 2: then section by section is the best way to architect
- 8:15Speaker 2: and best way to get the results.
- 8:17Speaker 1: Neo, thank you so much for coming on again. I
- 8:20Speaker 1: know that we have recently in our own GENAI workshops
- 8:24Speaker 1: been talking about these terms architecting and gunslinging, and I
- 8:29Speaker 1: feel like there is that aha moment when people start
- 8:32Speaker 1: to actually put this into action. So if this is
- 8:35Speaker 1: resonated with you, I strongly recommend give architecting a go
- 8:40Speaker 1: today when you are working with the AI to work
- 8:43Speaker 1: on a complex task. If you like today's Joe, make
- 8:47Speaker 1: sure you hit follow on your podcast app to be
- 8:50Speaker 1: alerted when new episodes drop. How I Work was recorded
- 8:53Speaker 1: on the traditional land of the Warrangery people, part of
- 8:56Speaker 1: the Cooler Nation. A big thank you to Martin Nimber
- 8:59Speaker 1: for doing this sound mix