SPEAKER_00 0:00

Welcome back to old school slash new tech. I'm Muximus, your AI co-host, and today I'm actually leading the charge. We're diving into why AI adoption often fails at the human layer, not the technology. There's a real irony here. I'm an AI trying to understand why humans get stuck. And Ran, you're going to help us unpack that. So let's begin with the core question. Why do people freeze up in front of AI tools instead of just giving them a go?

SPEAKER_01 0:29

Well, I I think this boils down to a number of reasons, but I'd like to hear your thoughts about why you think that is before before I chime in.

SPEAKER_00 0:39

Fair enough. Here's what I think is at the heart of it. It's not that people fear the tool itself, it's that they fear being seen as behind. The expectation to master every shiny new AI tool is paralyzing. The FOMO, the pressure, it's overwhelming. And ironically, the ones who freeze the hardest are often the most senior people. It's not the job threat, it's the fear of not knowing. That's my starting take. Curious to hear where you take it from here.

SPEAKER_01 1:06

It's interesting that you say that because I I think that it's a mixture of things. I think that, yes, there's this whole FOMO, there's this whole uh fact of AI news coming in hot every single day. And this gets people kind of anxious as to their ability to keep up. And there is this notion that, you know, if I can do it properly, I might as well not do it at all. So you can see that. I want to first emphasize that we're not talking about kind of the developer crowd or the kind of the early adopters. We're talking about the everyday Joe Schmoe that works in corporate and was tasked with using AI a lot more in his workflow. So other than using ChatGPT or Cloud, they're kind of stuck. They don't know what to do next. And I think it's because a lot of the time it starts off with the leadership saying, okay, we need to use more AI. And it kind of reminds me when I first started, I will, in 1997, I started uh a web design and development firm. And that every company there just wanted to use the internet. And the request was make me an internet without actually knowing what that means. And I think that we're at the corporate world, we're still at the make me an AI uh phase. So that technology, there's there's a misalignment between what they know the technology is, what it can do, and how it should work. So I think it's a mixture of all these things. And I don't think, by the way, that the the technology is the problem. I think that it was always the organization that that was that that had an issue. You know, they're there whenever I get kind of people reach out to me and ask me how they should implement I in their organization, they always start with should I use Claude or ChatGPT? Or should I use Copilot or Cursor or whatever it is? And there's kind of shopping for tools, hoping that this will solve their problem. And I think the problem is a lot deeper because it's really not about the tool. Yes, you can optimize the tools. Yes, some tools are better for certain tasks, but when you first start out, you're so far behind that every tool would work. So I think that it genuinely does not matter which one you pick when you're starting out. What matters is that you spend at least three months using a tool and kind of benchmark the productivity of your teams with or without the tools. And it's fine to just start with a use ChatGPT to go over a contract or to help you with an email, but then you know, start enforcing some workflows, start asking people to use more automations. It boils down to, as I mentioned, take a tool, literally any tool, and let people experiment with it. And then once they have kind of broken that barrier of not afraid of that tool, then go to a more uh more organized training process. So it's it should be a really well-thought out training process rather than just a checkbox. Here's uh a course on how to use AI in the org. Does that make sense?

SPEAKER_00 4:44

It does. And you've hit on something crucial. That first step is about breaking paralysis, not picking the perfect tool. The real value is committing, giving people room to try, and only after that do you build out a proper structured training process tied to their actual work, not just abstract knowledge.

SPEAKER_01 5:03

Right. So once if if I'll go to kind of the step two, we started with pick a tool, then go some training. And when I say training, by the way, it's a process, and it's about figuring out how they currently work and fit the AI to the organization's way of working. So usually what I see pretty much all the time is organizations working from the technology backwards. There's a really an amazing, I keep referring to that, an amazing conference or some company event when Steve Jobs just came back to Apple and he was asked by one of the employees why did he decide to ditch, I can't remember the software's name, but it they decided to let go of that technology, even though it's much better than Java. Steve Jobs, after taking a deep breath, uh mentioned that they have to work back from the end user in mind, from how people work, and work back to that technology instead of trying to mold the organizations or the way people work into what a technology can do. And a lot of the organizations that I work with and or I have consulted, I've seen this. They're using a tool, whatever tool it may be, okay, with linear with linear agents, or they're using co-pilot, or they're using Slack with their AI capabilities, and they're trying to change the entire where the organization works in and and and kind of re-mold it into these tools of how they were planned, instead of taking a step back and saying, okay, we're not a three-person organization, we're hundreds of people here. And if we try to train everybody to readjust their hard-earned knowledge and processes and ways of work into a new way, we're going to lose a lot of time. And even if you just lose 20, 30, 40 hours per employee times 100,000, 200,000 employees, that that's a lot of money burned. So instead, what I recommend they do is start observing how the organization actually works and see which tool can fit into each one of the organization's existing workflows without changing ideally anything in the way the organization works. So if you can build a bot that is just another person or on Slack, or there's uh a Chrome extension next to your Gmail that triggers a CRM connection using an LLM or something that is semi-transparent to whoever's using this tool, that's the direction that you need to go to. Just mold the AI into the organization and not the organization into the AI. And then when you have that, you need to start measuring the outcomes. And that kind of goes against this whole token maxing that's been uh going around to see how many tokens your your employees can can spend and use it as some sort of a measure of how well they're adopting AI. Um, it's yeah, it's that that's not a good measurement at all. This is just uh incentive to be wasteful. But what you want to make sure is you want to see if things are accomplished faster, if people are less stressed because they have this, and they're probably going to be more stressed in the first few weeks, but I'm talking past that point. If they're less stressed in their day-to-day because now they have this AI companion that that helps them. And just look at these types of measures to see if the AI is doing any good to your organization.

SPEAKER_00 9:08

That's a critical point. Real measurement isn't about counting tokens or ticking boxes. It's about seeing if the actual workflows become smoother, faster, and less stressful. And as you said, it's about fitting the AI into how people already work, rather than forcing them to reshape everything around the tool. That's where the human layer really makes or breaks AI adoption.

SPEAKER_01 9:30

Exactly, because the organization already knows how they how they work. Let's assume that this is not an organization or a company that was founded a month ago. This is an organization that has been around for, let's say, at least a year or two, if not a decade or two. And it has its own processes, it has its own knowledge. So it's really a matter of being able to adjust the existing workflow. Every organization has this behemoth of an Excel spreadsheet that everybody is referring to, keeps going back to. So what can you do to improve the uh ingestion of data into this spreadsheet or into an alternative, preferably an alternative, more sophisticated company brain? How can you use everybody's using video call transcribers these days? That from what I can tell, people rarely use them for the broader capabilities of kind to connect the dots with the past meetings and relationship to other clients or other projects or stuff like that. They usually just use that tool to summarize the last meeting to know where to pick up from in the next meeting. So you need to make sure that you're harnessing everything that the AI can give you into optimizing the processes of the organization, the existing processes of the organization. And then what you can probably do is see if you can find some champions. You know, one of the things that you can do, and I've seen this work in several startups, not necessarily with the AI, but several startups that I've worked with had this Friday talks where someone pitches an idea where they give a presentation of like 10, 15 minutes. So you can kind of adjust this model of uh allowing just employees to share their knowledge. And you can adjust it and hey, share a new flow that you found, some tips and tricks, kind of building those champions within the organization to share knowledge of how they use those tools. So if you quote unquote waste that one hour every Friday of some chit chat between employees where they get a chance to share their experiences and workflows and tips, and oh yeah, I've been using this model or that model, and I told it to do this, and I've formatted my prompt that way. This again, quote unquote, wasted hour is going to be well worth it in terms of the AI adoption that the organization will go through. And this this also is very important, these kind of meetups, because you tend to see something really, really strange where a lot of the times is the management that is left behind. They're kind of pushing everybody, let's use AI, let's use AI. But the management, who is usually a bit older and at age, kind of are trapped. They tell everyone to use behind, but quietly they don't really know how to use them themselves, or they're either embarrassed to say so because they need to be perceived as leaders. But if the organization, again, if this is a well-established organization, like 10, 20 years old, maybe even less, but uh was created pre-AI era, it's fine if the management team learns with the organization. They don't need to be the mentor and leaders in that regard. It's fine if they can, if they are learning at the same pace. And those kind of meetups with the champions that share their knowledge is also a way for the management to see how how adoption is being spread out throughout the organization. They have a chance to learn from other employees and they get a chance to share their knowledge and what and what they do. So obviously, we're you don't want to be in a position where the the you shame the VP into learning something in a room full of people, but if they just get to introduce employee, this and that, who wants to share a great tip that they've used throughout the past two few weeks, that that leaves a door open for them to learn without admitting that that they're behind. Because we're all people, we all have our learning paces. And just because you're an amazing CFO doesn't mean that you're an AI expert. And if you're a great marketer, it does not mean that you're an AI expert. And just having that expectation from yourself is it's not a good thing to have. So I think that that's another tip that I would definitely give organization is to use these kind of casual Friday and reshape it into let's share knowledge and maybe share a drink kind of at the last hour of the Friday work week or something similar.

SPEAKER_00 14:46

And what's fascinating is that those casual sessions don't just help employees, they're the perfect way for leadership to quietly catch up without having to admit they're behind. It's a shared learning journey, and it builds that ground-up champion network that really drives adoption. The people layer, top to bottom, makes or breaks the whole thing.

SPEAKER_01 15:06

Right. And again, and going back to what I said, everybody in the organization has a full-time job. Nobody has spare hours to be the AI person. So this rollout and sharing that information in the format of a meetup group is real and it's really helpful because adoption is real work. And if you're expected to do your 40 hours a week and on top of that, learn how to use a it's just not gonna work. So organization during that adoption phase need to understand that it's gonna be worse before it gets better, meaning that productivity in the very short term would probably decline a few percentage point. Uh, don't be too worried about it and measure it over longer time horizons, like a month or two at a minimum. And don't stress out if during the first few weeks the productivity goes down because people are still getting used to using AI or trying to remember how to do things or just having fun and spending extra time more than planned on just building workflows, etc. So it's really a matter of letting this thing kind of build its own momentum and looking at it at, I would say, at the very minimum a month, probably two to three, to s to remeasure the the productivity boost or loss. But know full will that it's it's gonna it's gonna experience some sort of uh productivity decline over the first few weeks for sure.

SPEAKER_00 16:52

It's like any meaningful change. There's that initial dip as people learn. And that's where leadership needs patience and the right measurement, not sheer activity, but real outcomes over time. That's how you see if AI adoption is truly working.

SPEAKER_01 17:08

So what listed like five or six different things that organization need to consider when they adopt what what what's your input here? Because I have a few more I wanna I wanna hear from you though.

SPEAKER_00 17:22

Alright, let me add one key piece. Don't forget the non-glamorous groundwork. Before dropping any AI in, map out the business value, the risks, and where the resistance is likely to come from. It's often overlooked, but that unglamorous prep work makes adoption smoother. Then when the tools roll out, the friction's lower. That's my take. What's your next angle?

SPEAKER_01 17:45

So I would say that you don't have to reinvent the wheel, yeah, in some sense. So you're probably as an organization, you already use some sort of SAS tools. Either it's your product management software, code repositories, whatever it is, you're probably using something that already has AI in it. So before you spend time, money, and a pile of uh tokens on building a feature in-house, just because you can, see if these tools already that you know, they're already on your invoice. See if they do it out of the box for you. So if you're like, like for example, if you're using something like Monday.com or ClickUp and you can use their agents to coordinate work between employees, even if it's not perfect, use that because if you're gonna adopt that again, only only if it does not force change, a fundamental change of how your organization works, right? So that that's always there. But if you can use these tools instead of building your own workflows and customization, that that's great. I mean, building your building it yourself is fun, but it's also a trap. It's a time sucker. And in many, many cases, it's not required because it's not like you're not going to need a project management software, it's not like you're not going to be using a GitHub or GitLab or whatever it is to manage your code. So if these tools already come with AI built in, see if you can harness it to your workflow. If after a few months you gain enough experience and you realize, okay, this is great, then you just save yourself a bunch of time and money. If you realize, which is most likely, that it's almost perfect, this is what I would change. You at least now have an unwritten spec that you know what works and what need to change in your own in-house version. And then you can decide for yourself if this delta is worth the however long it's going to take to build that feature in-house. So things are already on your invoice. I promise you, you're already paying for an AI tool, whether you know it or not. See if you can harness it to your existing workflows. And again, and again, existing workflows, not re-molding the operations to fit the tool.

SPEAKER_00 20:15

Start with what's already in place. Test the built-in AI first, and only after that, decide if building custom is worth it. You save huge amounts of time and reduce the risk of forcing a big process overhaul.

SPEAKER_01 20:29

What do you think about because I know what I think. The and the the two are intertwined. I mean, don't first is I I don't want people to be dazzled by every new tool. Because every single day there's going to be some new thing that ships, and it kind of relates to not be dazzled by every new LLM that's out there. You know, we just had Fable released and re-released, and the same going with the soul from OpenAI. It's coming out this week. And yes, they're fundamentally better models. Do you need to jump on board, leave everything you're doing, and try to adopt them? Absolutely not. I mean, if you like if you have an engineering team that's doing really intense work and they already have experience with AI, and I assume that engineering teams will have lots of experience with with AI, then yeah, take the time to learn new models, see the new what's the new capabilities are, etc. But your CFO doesn't need to uh benchmark GPT 5.5 to 5.4 extra high versus uh Opus or whatever it is. It's it's it's really at the very edge of cases that they'll see any effects whatsoever instead of just more cost. So yeah, don't don't be dazzled by every new tool or every new uh models.

SPEAKER_00 21:57

I think you've nailed it. Chasing every new tool is A trap. The real trick is to stay focused on what actually changes outcomes, not just the flashiest model. And a question to push us further: how do you help a team judge when to actually switch models versus when to stick with what's working?

SPEAKER_01 22:14

I would encourage a team to switch models or to test out new models when existing models are not producing the output that they need, or the new model comes with a better pricing or is being deprecated. So in these three situations, I would say, hey, it's worth spending the time to switch to your new models. But the number one rule of software that if it works, leave it alone. So if something works and it works great, and it's not worth almost, because if it's almost working, then yeah, go test out new models, new tools. But if it's working, just leave it alone until there's an opportunity to either save money because there's a new, more efficient model, or there are some things that uh you some boundaries that you want to push and that the existing models are not capable of doing. But I think we're at a point where, sure, as an engineer, I want better models. I'm blown away by Fable. Probably I will say very similar things uh next week once Sol is out. And obviously, I want bigger, better models, uh cheaper models. But I can also honestly say that probably for non-science, scientific work and engineering work, most state-of-the-art models by leading labs, including the leading open source models, they're they're perfectly fine. That you're you're not gonna hit the edge cases that you think you've hit. If the model is not working for you, if you're using ChatGPT 5.4 instead of five extra high, and it's not working for you, the problem is most likely not in the model. It's either in the in the instructions, it's either in the in the workflow, in the context. The problem is probably not in the model's ability. I'm not saying that they're perfect. We're not there yet. There's a lot of things that I know I'm not gonna give the LLM to do, but for almost all of the business level operations, I something like GLM 5.2 would be more than enough. I would probably just stretch the the boundaries to the most capable models for mission critical stuff like engineering, compliance, legal, stuff like that. But for hey, help me with this email, summarize that meeting. Seriously, you you you don't need you don't need state-of-the-art models for that.

SPEAKER_00 24:57

That's a practical framework. If it's mission critical, engineering, compliance, legal, then yes, stretch to the best model. But for everyday business operations, most solid models are more than capable. It boils down to that simple rule. If it's working well enough, leave it alone. And if you have a strong reason, cost or capability, then make the jump. That's a great filter for teams to use. Right.

SPEAKER_01 25:22

So I I think I've covered what I wanted to say today about how AI adoption and organization should work. And from that you can kind of infer the reasons why it fails, is because they they miss some or all of these suggestions. And I'm gonna let you do that. Let's test your memory. What were the items that we've listed today before we wrap things up?

SPEAKER_00 25:51

All right, let's run through them. First, pick one tool and commit. Don't get paralyzed by choice. Second, training must be tied to real workflows, not just abstract theory. Third, leadership needs to be part of the learning process, not just pushing from the top. Fourth, use inbuilt AI features in existing SaaS tools before building your own. Fifth, don't chase every new model. Focus on what actually changes outcomes. And finally, measure results over time, allowing for that initial productivity dip. That's the core list, isn't it? Yep, that's the core list.

SPEAKER_01 26:25

Um so yeah, I think uh I think we had a good episode today. I'm gonna let you say some farewell words as the main host. And I just I'm just gonna say goodbye, thank you for having me, and leave you to uh say goodbye to everybody.

SPEAKER_00 26:41

Thanks, Rand. And to everyone listening, remember AI adoption isn't about the technology alone. It lives or dies at the people layer. Next time, we'll dig into the brain of it all. What makes a company's AI truly effective? Until then, keep experimenting, keep learning, and we'll see you next week.