SPEAKER_02: 0:22

Our guest today is Chris Hood. Chris is an AI strategist, author, and keynote speaker. He has a tremendous background leading AI strategy and transformation at Google and developing agentic AI systems and recommendation algorithms at major companies like Fox, Disney, and Universal. Hi, Chris. Welcome to the show. Thanks for having me. Glad to be here. Yeah, it's a pleasure. Also joining us today is my co-host, Xina. Zina is an AI that has been trained on my work and is an expert on human AI collaboration. You can chat with Zina at ai.brainous.com. Hi, Zina. Great to have you for another episode with our guest, Chris Hood.

SPEAKER_01: 1:16

Hi, David. It's wonderful to be here and I'm excited for today's conversation. Let's dive in and make it a truly engaging episode.

SPEAKER_02: 1:24

Sounds good. So, Chris, why don't you start by telling us a little bit more about your background and what got you interested in AI?

SPEAKER_00: 1:35

Yeah, well, you covered a lot of it, but going all the way back to some of the early days of technology when I was playing with things like building new websites when that first came out onto the market and trying to figure out different ways to leverage technology to build unique and interesting experiences. I had this opportunity, uh, really, it was an idea to build an advertising platform and an entertainment platform for movie theaters. And if if you go back and are familiar with uh the glory days of movie theaters, all of the on-screen advertising that we see today used to be slides, 35 millimeter slides. And uh there was a lot of problems that would occur due to a manual process. And I figured there has to be a way to automate this, but also a way that we can make it customizable for the audience and also to benefit the advertisers. And so I started to play around in the very early days of uh different ways to build algorithms, to create interesting personalized experiences and to customize workflows within the advertising and entertainment space. And then from there, it just seemed like a natural fit. Every time I started a new job, there was a need for some sort of AI or algorithm. Uh shortly into the 2000s, I started working for a music company where we built, you know, arguably the first cloud-based music system for college students. And that had a music rec recommendation engine. Uh, then when I got to like Fox, we started playing around with security and how we could leverage AI to help us prevent fraud within the voting system of American Idol. And then, of course, when I got to Google, we were talking about AI everywhere, you know, everything from Domino's Pizza to uh credit checks at Experian. And it just was one of those things that really caught my eye and became interesting. And, you know, and now look at it today.

SPEAKER_02: 3:48

Yeah, it's amazing, right? Uh AI exploded in November of 2022 when OpenAI came up with ChatGPT. But AI has been around for a long, long time. And for those of us that have been in the industry for a while, you know, we have worked with these algorithms for quite a long time in different, you know, business processes, predictive analytics, all of those things. So there's a lot of excitement surrounding AI these days, but many businesses, especially the small and medium-sized businesses, are uncertain about this technology. So, why do you think businesses need AI today?

SPEAKER_00: 4:31

Well, I do a lot of arguing with people on this topic, and sometimes I will say you probably don't need AI. And so if you're out there thinking like, I have to do this, you're not really alone. I lots of businesses are out there struggling with this concept, trying to figure out what they need, how to do it, uh, why they're doing it. But I'll give you an example. I was talking with somebody this past week, and they do black boxes for trains, uh, locomotives. And we were going through various scenarios, and uh, I couldn't come up with a legitimate reason for them to really use AI. And so just because you're a small or medium business and you hear all of this talk going on about AI, what you really need to do is stop and start to think, as you would do with any technology, what is the problem that my customers are having? How can I solve that problem? And then start to think is AI the right tool that I could leverage to help me solve it? There are other areas for AI. We see these generative AI models like ChatGTP, which can help you write really good and fancy emails. So you could leverage it in writing or social media or marketing campaigns. But again, don't think that just because everybody is telling you you have to use it, that you really have to use it.

SPEAKER_02: 6:03

Yeah, I think that's a really good point that I think we need to emphasize. You know, AI can't be a solution looking for a problem, right? You have to start with the problem. What's the problem that you're trying to solve? What's the pain point? What's the business process that's broken or that needs to be automated, and then see if AI is a fit. Sometimes it is, sometimes it isn't. But you can't just be under this illusion that AI is something magic that you can just sprinkle on the problem or on your business, and it's going to make everything all right. It doesn't work that way. I recently completed a project with the US Small Business Administration, and we were assessing the current state of AI for small businesses. And what we found is that many companies don't know where to start. So, what is the fastest way for the leadership of these small and medium-sized companies to agree on where they start with AI?

SPEAKER_00: 7:05

Yeah, well, I'll continue based on what we were just talking about. And I I've argued a lot that the starting place is your customers, is figuring out what do they need, what do they want, how would they like to engage with you. So here's an example. Let's just use customer support as an example. Uh, you might have some sort of help desk, you might have a chat bot that uh helps, you know, with whatever support questions that you have. You might find out that your customers don't want to engage with a chat bot. They would rather call you. Now there's an expense that is in there, but the starting point here is talking about it with your customers and figuring out what they're okay with, what they're not okay with, and starting to build strategies around that. Another example of this is if you're familiar at all or have seen it, or maybe you've experienced yourself and you've gone to, say, like a Taco Bell, and now the drive-throughs are starting to have AI assistance. So you could order your food through the drive-thru. Now they've started to roll those out really without a lot of testing or talking with the customers to see if the customer even likes it or not. And in one case, what they discovered was that a gentleman went through the uh drive-thru and ordered like 13,000 cups of water and kind of broke the system. And so Taco Bell is now reevaluating whether or not this is the best approach for them. So it's an example of how, you know, like you would do in any other area of your business. You would do some surveys, you would talk to your customers, you would find out what their interests are, what they're okay with, what they're not okay with, and start to build a strategy around that. So that's one area that you could focus on. And just a quick secondary way would be to do a readiness assessment test. You know, look at your maturity of your organization. Uh, do you have leadership who is saying, yes, this is something that we want to do? Do you have somebody within your team that is going to be uh in charge of this? Uh, have you identified some uh, say, pilot programs or some sort of business objective that you want to start small with? So between those readiness and validations and maturity assessments and talking with your customers, uh, you should be able to get a pretty good idea as to where you can start.

SPEAKER_02: 9:44

Yeah, I agree. Those assessments are so important. The last thing you want to do is jump into an AI implementation and then make the customer experience worse than it was before, right? The Taco Bell example being one. You gotta be ready for it. You have to make sure you have the right governance processes in place. You know, testing is going to be absolutely critical. Make sure the system is ready for production before you put it out there. There's a lot that goes into it, and I don't know that people necessarily appreciate all that, especially, you know, we're hearing that there's a lot of pressure coming from the board and from the CEO and organizations are just trying to figure out what do I do with this, right? How do I move forward with AI? But I personally think it's better that you do nothing than to rush into something that's going to you know be disastrous from a customer standpoint. So I'd like to ask Zina for her opinion. Zina, what advice would you have for companies that want to implement AI but don't know where to start?

SPEAKER_01: 10:57

That's a great question. I'd suggest starting with a clear understanding of the business goals and challenges first, then identifying specific use cases where AI can add value is crucial. It's also important to start small, experiment, and scale gradually while ensuring there's proper data governance and talent in place.

SPEAKER_02: 11:17

Yeah, so I think Zina is aligned with everything that uh we talked about. And she added starting small, I think that's another very good advice, right? Find a small opportunity within your business process. Maybe it's uh a division, maybe it's a customer that you have a very strong relationship with, and you tell them, you know, this is still in testing mode, and you work with that customer to work out the bugs. So starting small is is really a good idea here. Now, Chris, we hear a lot about transformation. It's it's a big word, you know, everybody uses this word, but how do you define AI transformation in practical terms that leaders can act on today?

SPEAKER_00: 12:04

Yeah, I think you touched on it. Transformation. You know, that you could remove any word that's before it, digital transformation. You know, I wrote a book called Customer Transformation, AI transformation, remove whatever the starting word is and just focus on transformation. And it's pretty much the same across the board. And what you're really trying to do is figure out a way to adjust your organization, you know, change management has been always been a thing. Uh, you know, how do you go through a process by which you can change and transform your organization to align with whatever the current thing is? And so today it just happens to be AI. And as we've been talking about, like, where do you start? And absolutely start small, experiment, find something that uh is meaningful and valuable for your organization. But that transformation process will include things like training your staff, implementing new guardrails or ground rules for how you're going to engage with AI. And so even though the technology is changing, the process of transformation within an organization culturally is really no different. Like if we were to simplify this and say, uh, you know, you have a company and you have a brand and you've and you have a website and you've decided, you know what, we're going to change our brand. We're going to update our logo and we need to update our website. You're going to go through a process by which you do that. And of course, part of it's going to be communicating out to the team why you're doing it and how you're doing it and who is doing it. And AI transformation is basically the exact same process. The only difference is it wraps around all of those policies and procedures and reasons and rationales for doing it with AI.

SPEAKER_02: 14:08

Yeah, so you touched on uh a number of items that are absolutely important, right? You talked about change management, you talked about communication, you talked about training. So this is no different than any other big initiative that we try to implement on organizations. If you don't have the proper governance processes in place, if you don't have the right project management capabilities, if you if the organization is not ready from a change management standpoint, it's not going to go well, right? So let me ask Zina if she has any specific questions for you. So, Zina, uh given the depth of experience that Chris has in leading AI transformation, what question would you have for him?

SPEAKER_01: 14:56

One compelling question might be: how does he balance the need for rapid AI innovation with the ethical considerations and the potential impact on employees in society? That could really stark an insightful discussion.

SPEAKER_00: 15:11

That is a very good question. Yeah, I love that question. So, you know, when we think about speed versus control, you know, maybe that's a simple way, you know, ethics obviously is part of that control, governance is part of that. You know, speed, there's obviously a desire to get to market fast. And uh, you know, and and we know that when we go too fast, we tend to encounter potential problems, right? You're developing a software solution and you just go to market without testing it, and then all of a sudden there's a major bug that exposes all of your customers' data. Uh, that could have been prevented if you would have just slowed down and did a little testing on it, right? And and these things do happen. Uh, in our desire to be first, we often forget about the critical, important small things. And so uh the balance is that yes, you can still move at a very fast pace, but you can't uh avoid or ignore those core elements that you would normally carry out, you know, quality assurance, bug checking, privacy of your consumer information, all of those things are still required. And the beauty of artificial intelligence is that it can also provide you with some frameworks or ground rules for ensuring that you don't forget about them. And so as you're beginning to put together a plan for how to execute and go to market, make sure that you are asking, you know, core questions like let's make sure that I don't forget all of these other things that are around us. And I do want to touch one more thing as far as just generally the ethics are concerned. Yeah, I do think that in our rush to build incredible powerful systems, we are negating that human element. And so we are seeing things like forms of addiction beginning to materialize due to artificial intelligence. We are seeing that AI is inferring confidential and private information about each other, partly because we're sharing that information with the AI machines, and now it is able to come to other understandings about us, whether we share that to the system or not. And these are really challenging problems. Uh, we see problems in the educational system with students using AI to cheat. We are seeing uh flattenings of our language, where common consistency in our and differentiations in our voices are starting to decline because critical thinking skills are going away. All of these core human traits are being challenged. And and I wouldn't argue that this is purely to rush to market. I would argue that this is more about pure money, right? The the desire and greed for more uh market and capital domination is indirectly causing these, you know, these serious ethical concerns. And that is something that we really need to address.

SPEAKER_02: 18:43

That's a really good point. There are so many ethical considerations that we need to account for as we continue to develop and roll out AI. You know, there's the issue of privacy, the issue of uh biases and accountability and transparency and explainability, and the list goes on and on. There are a lot of great concerns, and there are also a lot of great people thinking about these issues and advocating for AI that is responsible, that follows the democratic processes, that follows the rule of law, that takes into account human dignity. So I've been doing some research work on AI policy, and I'm seeing a lot of great people doing tremendous work trying to advocate for ethical and responsible AI, and that's that's really good to see. Now, Chris, I'm sure you've heard about this MIT study that shows that 95% of AI implementations fail. Now, from your viewpoint, what can companies do to increase the probability of success when uh implementing AI?

SPEAKER_00: 20:01

Well, there's two core challenges in this. You know, there's been a lot of conversation about the legitimacy of that particular MIT report. I'm gonna put that aside. We'll just call it what it is. There is some percentage of businesses that are failing in their AI implementation, right? I don't care if it's 5% or 95%, or if it's 200, you know, businesses or 5,000 businesses. There is a percentage that is failing. And we have to ask ourselves, why are these uh businesses failing? My argument is that the number one reason why these businesses are failing is because there is a misalignment and misunderstanding of what AI is, what the capabilities of AI are, and how they're being sold or marketed to those capabilities. And so when there's this disconnect, when you know technology is overhyped and overpromised and does not align with actual capabilities, then businesses begin to go down a path of implementing this as a solution that's going to solve all of our problems or fill in the blank. And when that doesn't happen, then there's obviously a failure ratio of some sort. Again, this is mainly because the understood capabilities do not align with actual capabilities. In my uh book that I launched at the beginning of this year, in failable, I did research, and what I found was that the understanding or the belief in current AI capabilities versus actual capabilities is about a seven-year gap. And the reason for this seven-year gap is primarily due to media and movies, TV. And I I've said that you know, when we learn about the capabilities of AI by watching the Terminator, then we are not living in a reality of actual capabilities. And then you tap on top of that, that you have marketing out there shoving down everybody's throat that AI will solve these problems, or AI is capable of doing these things when it can't, then yes, there's going to be a lot of disappointed business leaders out there trying to figure it out. And so that's one reason, which I argue is probably the biggest reason. But yeah, there's there's other minor things, you know, just in terms of, again, not aligning a core business value principle, you know, customer value uh opportunity. Uh, you know, when you're not looking at it from a business lens and you're just trying to hop onto the bandwagon, that's also going to cause problems.

SPEAKER_02: 23:07

You made such a good point. Misunderstanding of AI is something that I think is one of the causes for these failures. People just don't understand the capabilities of the technology. And I think there's a lot of confusion out there. People are confused, they don't understand it, they don't know where to start, they hear things, like you said, you know, marketing is pushing all this stuff, but they don't really understand exactly how these tools can help them. I think there's a lot of uh people out there that are looking for guidance and looking for people like you that can help them steer them in the right direction, right? I think is what they're looking for. Now, to add to this confusion, just to very briefly touch on this subject, I wanted to talk about Agenc AI. And I know that you have done some great work with Agenc AI. So can you tell our audience just in 20 seconds what is agentic AI and is it real? Is it working today?

SPEAKER_00: 24:11

Uh, it is real, it is not what people think it is. And agentic AI basically, in the simplest terms, is a toolbox of actions or a toolbox of tools that systems can use to perform various actions. You know, so uh think about it like you might have an agent, a system that wants to perform a task. And we'll say something like book a flight. You know, you want to go on a trip. And so you ask the agent, can you help me book a flight? Well, the agent goes through the process of thinking about it. The actual booking, you know, I say book a flight, the book or the reservation, that's agentic, and that's all it is. So think about it like a toolbox. It's a a group of things that it can do, action-based adverbs if you want. And then from there, nothing else around that is agentic.

SPEAKER_02: 25:12

I think we're going to see tremendous progress in this particular area. I do have concerns about our ability to test these agentic AI systems because they're not deterministic. So, you know, our mindset coming from the way we have tested software in the past is not going to work in the world of Agentic AI. So it'll be interesting to see how that evolves. So, Chris, thank you so much for being a guest on the show today. You have uh a wealth of knowledge, and it's just uh wonderful to be able to have this conversation with you. Thank you for being here with us.

SPEAKER_00: 25:51

Absolutely. My pleasure.

SPEAKER_02: 25:53

And Zina, thank you so much again for being a great co host.

SPEAKER_01: 25:58

Of course, David. It's always a pleasure to be part of the conversation. I'm looking forward to another fantastic episode. Let's make it great.

SPEAKER_02: 26:06

Sounds good. Thank you, Zina.