1 00:00:00,560 --> 00:00:06,000 Speaker 1: Today, I am back with Neo Applan, Inventium's Genai expert 2 00:00:06,400 --> 00:00:11,320 Speaker 1: to help unpack a very cool concept that he recently 3 00:00:11,360 --> 00:00:16,400 Speaker 1: shared with me. It's about gunslinging versus architecting, and it's 4 00:00:16,400 --> 00:00:20,079 Speaker 1: all about how you work with AI. So if you 5 00:00:20,239 --> 00:00:24,800 Speaker 1: have ever found yourself wrestling with chat, GPT or one 6 00:00:24,800 --> 00:00:27,080 Speaker 1: of the other jenai is to get it just right, 7 00:00:27,600 --> 00:00:36,200 Speaker 1: then this episode is for you. Welcome to How I Work, 8 00:00:36,400 --> 00:00:40,560 Speaker 1: a show about habits, rituals, and strategies for optimizing your day. 9 00:00:41,159 --> 00:00:45,400 Speaker 1: I'm your host, doctor Amantha Imber. Two years ago, I 10 00:00:45,520 --> 00:00:49,960 Speaker 1: completely overhauled how I work with Genai and I'm now 11 00:00:50,040 --> 00:00:54,680 Speaker 1: saving over forty hours every single week. That is no exaggeration, 12 00:00:55,480 --> 00:00:59,120 Speaker 1: and that's exactly why my company, Inventium created the Genai 13 00:00:59,280 --> 00:01:03,120 Speaker 1: Productivity Upgrade. It's a twelve week course designed to move 14 00:01:03,200 --> 00:01:07,720 Speaker 1: you from AI doubler to productivity machine. No fluff, just 15 00:01:07,840 --> 00:01:11,040 Speaker 1: practical strategies that will pay off from week one, saving 16 00:01:11,080 --> 00:01:14,559 Speaker 1: you at least ten hours every single week. You'll learn 17 00:01:14,640 --> 00:01:17,760 Speaker 1: how to make AI sound exactly like you use AI 18 00:01:17,920 --> 00:01:21,319 Speaker 1: as your second brain to excel at your job, and 19 00:01:21,640 --> 00:01:25,560 Speaker 1: so much more. Whether you're a complete beginner or already dabbling. 20 00:01:25,640 --> 00:01:28,760 Speaker 1: We've got you covered, starting with prompting fundamentals and going 21 00:01:28,800 --> 00:01:31,959 Speaker 1: all the way through to advanced automations and agentic AI. 22 00:01:32,520 --> 00:01:35,720 Speaker 1: We kick off on July fourteen, and spots are limited. 23 00:01:36,160 --> 00:01:40,080 Speaker 1: Visit inventium dot com, dot au, forward slash Jenai hyphen 24 00:01:40,200 --> 00:01:43,360 Speaker 1: cohort to secure your place now, there's a link to 25 00:01:43,400 --> 00:01:45,760 Speaker 1: that in the show notes, and you've got nothing to 26 00:01:45,800 --> 00:01:49,080 Speaker 1: lose because there's a seven day money back guarantee, So 27 00:01:49,320 --> 00:01:51,640 Speaker 1: head to the link in the show notes and check 28 00:01:51,640 --> 00:01:56,320 Speaker 1: out the program today. So, Neo, you say that most 29 00:01:56,360 --> 00:02:00,760 Speaker 1: people are gunslingers when they prompt Jenai, Can you tell 30 00:02:00,800 --> 00:02:02,000 Speaker 1: me what you mean by that. 31 00:02:03,280 --> 00:02:06,200 Speaker 2: Yeah, it's a metaphor. It's not a technical term. It's 32 00:02:06,320 --> 00:02:09,280 Speaker 2: how some people work with jen Ai. It's effectively, get 33 00:02:09,320 --> 00:02:12,000 Speaker 2: a decent enough prompt, shoot from the hip and hope 34 00:02:12,040 --> 00:02:14,760 Speaker 2: and pray that it's going to go pretty well. Just 35 00:02:14,800 --> 00:02:17,280 Speaker 2: as gun slinging isn't the most accurate way that you 36 00:02:17,360 --> 00:02:21,800 Speaker 2: can hit a target, same thing with prompting gun slinging, 37 00:02:21,840 --> 00:02:24,440 Speaker 2: where you've got a pretty average prompt, you've shot it 38 00:02:24,480 --> 00:02:27,120 Speaker 2: out there, chances are it won't hit the bull's eye 39 00:02:27,320 --> 00:02:29,840 Speaker 2: every time. And so what you're finding is you then 40 00:02:29,919 --> 00:02:32,280 Speaker 2: have to have a discussion with the AI to improve 41 00:02:32,320 --> 00:02:33,800 Speaker 2: the output. I mean a little bit more of this, 42 00:02:33,919 --> 00:02:36,000 Speaker 2: a little less so that it can go from a 43 00:02:36,040 --> 00:02:39,200 Speaker 2: discussion to feeling very much like a debate and argument 44 00:02:39,600 --> 00:02:42,320 Speaker 2: with AI to get what you're really after. So the 45 00:02:42,360 --> 00:02:45,239 Speaker 2: first prompt might be fast, but then the cleaning up 46 00:02:45,400 --> 00:02:48,880 Speaker 2: is a very long task and can get frustrating after time, 47 00:02:48,960 --> 00:02:51,280 Speaker 2: lots of back and forth refining, so it can be 48 00:02:51,360 --> 00:02:54,560 Speaker 2: time consuming and inefficient if you're doing anything beyond kind 49 00:02:54,560 --> 00:02:56,560 Speaker 2: of basic prompting or basic tasks. 50 00:02:57,000 --> 00:03:00,760 Speaker 1: Okay, so then there is what you call architect What 51 00:03:00,800 --> 00:03:02,840 Speaker 1: does that look like instead. 52 00:03:03,080 --> 00:03:05,720 Speaker 2: Well, instead of shooting from the hip, it's much more deliberate, 53 00:03:05,800 --> 00:03:09,320 Speaker 2: it's much more collaborative with the AI, and it's more 54 00:03:09,440 --> 00:03:12,760 Speaker 2: likely to get you a great result and certainly faster 55 00:03:13,400 --> 00:03:16,880 Speaker 2: than gunslinging. And that there's a lot less refinement and 56 00:03:16,919 --> 00:03:19,560 Speaker 2: a lot less arguing with AI. So what you do is, 57 00:03:19,760 --> 00:03:22,160 Speaker 2: first off, you need to agree with AI and what 58 00:03:22,200 --> 00:03:24,520 Speaker 2: your goals are. Now, notice I say to agree, So 59 00:03:24,560 --> 00:03:26,800 Speaker 2: you need to say, here's what my goals are, and 60 00:03:26,840 --> 00:03:29,760 Speaker 2: you need to make sure that AI understands those goals. 61 00:03:29,760 --> 00:03:32,880 Speaker 2: So here's what I'm trying to achieve. Then you also 62 00:03:32,919 --> 00:03:36,520 Speaker 2: work with it on things like best practice or structure 63 00:03:36,960 --> 00:03:40,080 Speaker 2: or all those kind of things before it starts writing 64 00:03:40,120 --> 00:03:42,920 Speaker 2: anything else. So it's effectively you're working with it as 65 00:03:42,960 --> 00:03:46,320 Speaker 2: a planning partner and getting it to challenge your ideas, 66 00:03:46,400 --> 00:03:49,120 Speaker 2: getting it to challenge its own ideas, so it knows 67 00:03:49,120 --> 00:03:51,880 Speaker 2: the structure, what you're trying to achieve, what best practice is, 68 00:03:52,280 --> 00:03:54,960 Speaker 2: before you get it to write the thing. So it's 69 00:03:54,960 --> 00:03:57,160 Speaker 2: almost like designing a house before you build it. You 70 00:03:57,160 --> 00:03:59,000 Speaker 2: don't want to just build a house first. You want 71 00:03:59,040 --> 00:04:01,920 Speaker 2: to design it first, and then when it's already designed, 72 00:04:02,120 --> 00:04:03,520 Speaker 2: then you go and get the builders to come on 73 00:04:03,600 --> 00:04:04,400 Speaker 2: and to build the thing. 74 00:04:05,600 --> 00:04:10,000 Speaker 1: Okay, so I'm obviously not going to use architecting when 75 00:04:10,040 --> 00:04:13,480 Speaker 1: I'm writing a simple email. So I'm wondering what are 76 00:04:13,520 --> 00:04:17,719 Speaker 1: the kinds of tasks that architecting is best suited for. 77 00:04:18,680 --> 00:04:21,400 Speaker 2: Anything it's complex or that you need to get a 78 00:04:21,440 --> 00:04:25,320 Speaker 2: great result at where good enough isn't isn't enough, isn't 79 00:04:25,360 --> 00:04:27,400 Speaker 2: good enough? You need to get something it's excellent. So 80 00:04:27,920 --> 00:04:30,560 Speaker 2: things like if you're working on a strategy paper or 81 00:04:30,640 --> 00:04:34,120 Speaker 2: training sessions or workshop design or any kind of report 82 00:04:34,200 --> 00:04:37,520 Speaker 2: or analysis and all those kind of things, something where 83 00:04:37,800 --> 00:04:40,320 Speaker 2: you need to make sure that it's grounding it in 84 00:04:40,640 --> 00:04:44,240 Speaker 2: background and science and industry best practices and things like that, 85 00:04:44,480 --> 00:04:46,839 Speaker 2: where you want to get a great result, This is 86 00:04:46,880 --> 00:04:49,520 Speaker 2: where I would use architecting. So if you need a 87 00:04:49,560 --> 00:04:53,000 Speaker 2: structured output or some thinking through it, it's really good 88 00:04:53,080 --> 00:04:55,479 Speaker 2: for that. So if you wanted to have something which 89 00:04:55,560 --> 00:04:58,400 Speaker 2: is average or it's quick, fine, gunsling, like if I'm 90 00:04:58,400 --> 00:05:01,160 Speaker 2: doing emails off gunsling thing is fine. But if I 91 00:05:01,200 --> 00:05:03,080 Speaker 2: want to get a document or a structure, or I 92 00:05:03,160 --> 00:05:05,880 Speaker 2: want to, as I said, a team workshop. If I 93 00:05:05,920 --> 00:05:08,599 Speaker 2: want a great team workshop, then why don't I get 94 00:05:08,680 --> 00:05:11,800 Speaker 2: architecting to help me to build something even better. It 95 00:05:11,800 --> 00:05:14,240 Speaker 2: works great with all the different ais, I should say, 96 00:05:14,760 --> 00:05:17,919 Speaker 2: but in some of them it works better. So copilot 97 00:05:18,080 --> 00:05:21,120 Speaker 2: architecting is brilliant. It does such a much better job 98 00:05:21,400 --> 00:05:23,760 Speaker 2: than just average copilot gun slinging. 99 00:05:24,760 --> 00:05:27,040 Speaker 1: And if I'm using chat ept, as I know a 100 00:05:27,080 --> 00:05:29,279 Speaker 1: lot of listeners do, should I be choosing one of 101 00:05:29,320 --> 00:05:32,799 Speaker 1: their logic models for this or any models? Fine? 102 00:05:33,160 --> 00:05:35,200 Speaker 2: Yes, the logic models, and these are the ones that 103 00:05:35,279 --> 00:05:39,120 Speaker 2: start in O so three to four, etc. The logic 104 00:05:39,160 --> 00:05:41,800 Speaker 2: models are excellent for these kind of things. But they 105 00:05:41,839 --> 00:05:46,000 Speaker 2: do a better job when you do architecting, because what 106 00:05:46,040 --> 00:05:48,479 Speaker 2: you're still doing is you're working with the GENAI on 107 00:05:48,560 --> 00:05:51,200 Speaker 2: what the goals are and things like best practice rather 108 00:05:51,200 --> 00:05:54,560 Speaker 2: than letting it think. You're working with the GENAI to 109 00:05:54,600 --> 00:05:57,680 Speaker 2: be able to architect this together, and those logic models 110 00:05:57,680 --> 00:06:00,720 Speaker 2: do give you a better result. So yeah, do use 111 00:06:00,760 --> 00:06:03,719 Speaker 2: the architecting, and those models you over next level the result. 112 00:06:04,560 --> 00:06:07,239 Speaker 1: So NIO, I would love you to walk me through 113 00:06:07,800 --> 00:06:10,720 Speaker 1: an example, like, let's just say I don't know you're 114 00:06:10,760 --> 00:06:16,440 Speaker 1: designing a team building session for a client off site 115 00:06:16,560 --> 00:06:19,080 Speaker 1: or maybe your own team's off site. How would you 116 00:06:19,200 --> 00:06:22,320 Speaker 1: use architecting to go through that task? 117 00:06:23,480 --> 00:06:25,800 Speaker 2: I would first start with the context, So here, I'm 118 00:06:25,839 --> 00:06:28,360 Speaker 2: planning on building a team off site, and I'd like 119 00:06:28,400 --> 00:06:31,120 Speaker 2: to build a structure with you. Tell it what your 120 00:06:31,160 --> 00:06:35,280 Speaker 2: goals are. After that, I'd get it to ask itself 121 00:06:35,520 --> 00:06:39,120 Speaker 2: what best practice is? Are there ways that I can 122 00:06:39,160 --> 00:06:42,839 Speaker 2: achieve this goal even better? Get it to even review 123 00:06:42,880 --> 00:06:44,800 Speaker 2: its own work to see whether it can improve it. 124 00:06:45,440 --> 00:06:48,240 Speaker 2: What's the science behind team performance? All those kind of 125 00:06:48,240 --> 00:06:51,360 Speaker 2: things to get it to think through all the best 126 00:06:51,360 --> 00:06:54,279 Speaker 2: practice paths on how to build a great team workshop, 127 00:06:54,600 --> 00:06:56,440 Speaker 2: I might work with it on say, structure, how would 128 00:06:56,440 --> 00:06:58,760 Speaker 2: I structure these kind of things? What kind of activities 129 00:06:58,800 --> 00:07:02,120 Speaker 2: would work. I'm not getting it to build the workshop 130 00:07:02,640 --> 00:07:05,800 Speaker 2: or even the final output yet. I'm getting it to 131 00:07:05,880 --> 00:07:08,880 Speaker 2: work through best practice, how it aligns with my goals? 132 00:07:08,920 --> 00:07:11,720 Speaker 2: Are there better ways to do it? All those kind 133 00:07:11,720 --> 00:07:14,840 Speaker 2: of things. Once I'm comfortable it's nailed what I'm trying 134 00:07:14,840 --> 00:07:18,360 Speaker 2: to achieve, it understands best practice, it's refined as much 135 00:07:18,360 --> 00:07:21,120 Speaker 2: as I think it needs to, then I'll go, Okay, 136 00:07:21,240 --> 00:07:24,040 Speaker 2: let's build these things together. Then it will go through 137 00:07:24,120 --> 00:07:26,200 Speaker 2: and actually build me a workshop, and it will say 138 00:07:26,440 --> 00:07:29,440 Speaker 2: how and Wyatt's built the workshop for that best practice 139 00:07:29,720 --> 00:07:31,760 Speaker 2: and how it will deliver to what I'm trying to 140 00:07:31,800 --> 00:07:33,200 Speaker 2: achieve with those goals. 141 00:07:33,640 --> 00:07:35,800 Speaker 1: And then I imagine you could break it down even 142 00:07:35,920 --> 00:07:38,920 Speaker 1: further to go, okay, can we work on the morning 143 00:07:38,960 --> 00:07:41,520 Speaker 1: segment first? And then let's work on the segment that 144 00:07:41,960 --> 00:07:44,240 Speaker 1: is just before lunch and so on and so forth, 145 00:07:44,240 --> 00:07:46,920 Speaker 1: as opposed to okay, build out the full agenda is 146 00:07:47,560 --> 00:07:48,760 Speaker 1: Have I got my thinking right on that? 147 00:07:48,800 --> 00:07:50,760 Speaker 2: Absolutely? Yeah? And this is really good for you. You've 148 00:07:50,800 --> 00:07:53,680 Speaker 2: got a big document, say I'd be working on it 149 00:07:53,720 --> 00:07:56,760 Speaker 2: with the goals the strategies what you need to do 150 00:07:56,800 --> 00:07:59,560 Speaker 2: in the document, and then once you're comfortable with we'll 151 00:07:59,600 --> 00:08:02,360 Speaker 2: call it like index or a table of contents, then 152 00:08:02,440 --> 00:08:05,640 Speaker 2: you'd build out chapter by chapter, section by section, and 153 00:08:05,680 --> 00:08:07,920 Speaker 2: that's much better to do it that way. That way 154 00:08:08,040 --> 00:08:10,040 Speaker 2: it will give you a better result and it won't 155 00:08:10,040 --> 00:08:12,520 Speaker 2: go off track at all. So yes, structure first and 156 00:08:12,560 --> 00:08:15,520 Speaker 2: then section by section is the best way to architect 157 00:08:15,880 --> 00:08:17,240 Speaker 2: and best way to get the results. 158 00:08:17,960 --> 00:08:20,680 Speaker 1: Neo, thank you so much for coming on again. I 159 00:08:20,760 --> 00:08:24,600 Speaker 1: know that we have recently in our own GENAI workshops 160 00:08:24,600 --> 00:08:29,200 Speaker 1: been talking about these terms architecting and gunslinging, and I 161 00:08:29,240 --> 00:08:32,400 Speaker 1: feel like there is that aha moment when people start 162 00:08:32,440 --> 00:08:34,960 Speaker 1: to actually put this into action. So if this is 163 00:08:35,040 --> 00:08:40,360 Speaker 1: resonated with you, I strongly recommend give architecting a go 164 00:08:40,600 --> 00:08:43,440 Speaker 1: today when you are working with the AI to work 165 00:08:43,480 --> 00:08:47,199 Speaker 1: on a complex task. If you like today's Joe, make 166 00:08:47,240 --> 00:08:50,000 Speaker 1: sure you hit follow on your podcast app to be 167 00:08:50,040 --> 00:08:53,920 Speaker 1: alerted when new episodes drop. How I Work was recorded 168 00:08:53,960 --> 00:08:56,599 Speaker 1: on the traditional land of the Warrangery people, part of 169 00:08:56,640 --> 00:08:59,280 Speaker 1: the Cooler Nation. A big thank you to Martin Nimber 170 00:08:59,440 --> 00:09:00,600 Speaker 1: for doing this sound mix