← Economist Podcasts
Economist Podcasts
Interview: Bret Taylor of Sierra and OpenAI
00:34:22
What the rise of AI agents means
Loading summary
Transcript64 lines
- [00:00]
T-Mobile Advertiser
Everyone deserves to be connected. That's why T Mobile and US Cellular are joining forces. Switch to T Mobile and save up to 20% versus Verizon by getting built in benefits they leave out. Check the math@t mobile.com switch and now T mobile is in US cellular stores.
- [00:20]
T-Mobile Advertiser Legal Disclaimer
Savings versus Comparable Verizon plans plus the cost of optional benefits plan features in Texas and fees vary. Savings with three plus lines include third line free via monthly bill credits. Credit stop if you cancel any lines. Qualifying credit required.
- [00:30]
Brett Taylor
Foreign.
- [00:42]
Sonos AI Support Agent
Hi there. I'm the Sonos AI support agent. You can talk to me just like you would with anyone else.
- [00:48]
Andrew Palmer
Oh, hi. Did you say you were an AI?
- [00:51]
Sonos AI Support Agent
Yes, I'm an AI powered assistant here to help you with anything Phonos related.
- [00:56]
Andrew Palmer
I've borrowed a colleague's Sonos wireless speaker as an excuse to call up its customer support line because I know it won't be a human that answers the phone. I'm looking for help, so I've brought.
- [01:09]
Interviewer
My speaker into the office today and I'd like to connect it to the office wi fi and I'm having difficulties. So can you help?
- [01:18]
Sonos AI Support Agent
Are you seeing any specific errors in the Phonos app?
- [01:21]
Interviewer
No.
- [01:23]
Sonos AI Support Agent
Okay, give me a moment here.
- [01:25]
Andrew Palmer
AI customer support agents like this one are spreading fast. It's not perfect. We talk over each other a lot, but the agent sounds natural and is able to respond to any question I throw at it, however irrelevant.
- [01:41]
Interviewer
What's your favorite music?
- [01:42]
Sonos AI Support Agent
Oh, good question. I'm thinking about that for a sec. I don't have personal favorites, but I can help you play anything you like once your Sonos one is set up. If you want to keep troubleshooting, just let me know.
- [01:54]
Andrew Palmer
It's clearly been trained to stay on task.
- [01:57]
Interviewer
What kind of personality have you been prompted to have?
- [02:01]
Sonos AI Support Agent
I'm here to be friendly, direct, and helpful, focused on getting your Sonos working with clear step by step support?
- [02:08]
Andrew Palmer
That's a pretty good description. The agent tells me how to connect the speaker, and when I hit a.
- [02:15]
Interviewer
Wall with the office WI fi, I.
- [02:17]
Andrew Palmer
Offers to walk me through a factory reset or to hand me over to a human. I wouldn't call it a delightful experience, but if I really wanted one of those, I wouldn't be on the phone to customer support. I'd be reading Hamnet. The agent is patient and professional, and perhaps the best thing about it is that it answered the phone immediately.
- [02:44]
Brett Taylor
If there's anything I'm doing for society, it means you'll never have to wait on hold again, which I think that's a very popular mission that's way more.
- [02:52]
Interviewer
Important than AGI, I have to say, as a mission.
- [02:57]
Andrew Palmer
The man on a mission is Brett Taylor. He's the co founder and CEO of Sierra, a tech startup that helps companies like Sonos build customer service bots. Unsurprisingly, he's a big believer in AI agents.
- [03:15]
Brett Taylor
And the value proposition is really simple. You know, I think if it were 1995 and I don't think we'd be podcast dude, but if you could sort of imagine for a second I'd be sitting here and telling you why every company needs a website and how it will change your business. I think in 2026, every company needs an AI agent. And the vast majority of the digital interactions you'll have with your customers will be via your agent. And that agent's going to do everything your website can.
- [03:43]
Andrew Palmer
I'm Andrew Palmer, management columnist at the Economist. And as for Brett Taylor, he's a lot more than your average tech entrepreneur. He built the foundations for what would become Google Maps. He was once chief technology officer of Facebook. He's been chairman of Twitter and co CEO of Salesforce. And today, when he's not busy running Sierra, he he's also the chairman of a little known outfit called OpenAI. This bonus episode of Boss Class is an interview with Brett. At the start of this year. I spoke to him about the rise of AI agents and what that means for the future of customer service, the software industry and human jobs, but also what it means for the current moment. Why is it that the managers trying to implement Genai often feel like they're banging their heads against a brick wall?
- [04:46]
Brett Taylor
When a technology is new, whether it's the mainframe or the PC or eventually the advent of the Internet, there's not a lot of off the shelf solutions to leverage that technology. So, you know, when mainframes and PCs came out, a lot of companies had to build everything from scratch. And then the first generation of software companies essentially amortize the research and development costs of building that software across thousands or hundreds of thousands of clients, which is just rational. So you end up where every company in the world built their own. And then you transition to licensing software from these software vendors and then the Internet comes out. And there was an article in Wired in 1997, 98, that time period, and it was about a set of banks that were spending between 20 and $50 million to make their websites transactional, which if you read the article, basically meant adding a login form so you could actually see your Stuff and not just like information about the bank, which is something someone who goes to a coding bootcamp could do in a weekend. Or now with tools like Codex and cloud code, you could do just by prompting. But at the time, it was $40 million of consulting fees to just make this website work. And this whole article was about how they spent all this money and weren't happy with the outcomes. We're roughly in that era of AI and AI agents in particular, where everyone knows that agents are going to have a big impact. If you think about onboarding a new vendor to your supply chain, you do that, you know, hundreds of times a year. If you're a consumer packaged goods company, an agent should be able to take that and make it lower cost, faster, more reliable. If you have a toll free number for customer support, it stands to reason it's better your clients can talk to an AI agent rather than wait on hold and route to a BPO offshore somewhere. But right now, for a lot of use cases, there isn't an off the shelf solution. So you end up with a lot of people taking the raw component parts of AI, the models and agent building toolkits and are trying to string it together. Some people can do it with success, some people won't. Slowly but surely, we're emerging with off the shelf solutions for some of the most important use cases and agents. Cira, we're the leader in AI agents for customer service. There's a really neat company based here in San Francisco as well called Harvey that makes AI agents for the legal profession. So if you fast forward four or five years, I'm hopeful that for your listeners, for each of the use cases in each of the key departments, let's say auditing your financials after a quarter close, there's going to be an agent for that that you can just buy in the meantime, because there isn't, you'll have to build it yourself. And you'll have to go through this question of do you want to incur that complexity and cost? And if you do, by the way, you should probably prep yourself. You're going to throw it out when a vendor is available. Because most companies don't want to be software companies, right? Most companies just want the job done. So we're just in the early innings. And I'm hopeful five years from now it'll be a very mature landscape of vendors who sell agents as solutions to problems, rather than people selling models and saying, here's a bunch of wood, build a house. Which is kind of the case for a lot of companies where they are today.
- [08:00]
Interviewer
I just want to zero in on this sort of interim period. So the argument is if you wait long enough, the ecosystem will be there. There's obviously a bit of self interest here. People will be able to buy from firms like your own. In the meantime though, should people be experimenting? I mean, a lot of this as a general purpose technology, there must be benefit to experimentation, to playing around, to developing an intuition of the technology.
- [08:24]
Brett Taylor
There absolutely is, and it's a very nuanced decision. So I'll sort of walk through what I believe are sort of the first principles view. So AI is inherently deflationary. I mean, ideally it helps you do more with less. So there's a cost savings aspect to it. And what do you do with cost savings? Well, you can pass it on to your shareholders, which is valuable. But I'm a capitalist and you know, if your competitors have access to the same technology, someone will find a way to reinvest that money to gain a competitive edge. So there's a risk to waiting too long because if you have a savvy competitor who's able to adopt this technology more than you can, what structural advantages might compound in the period where you're waiting on the sidelines and your competitor is not? I think that's driving a lot of the urgency and I think a lot of boards and CEOs are actually driving the adoption of AI top down for good reason. But the other part of it though is consumer behavior. And I think ChatGPT is really becoming the front door, you know, the sort of the consumer front door for AI. And if you look at the role that search engines have traditionally played, a lot of that is being reshuffled a bit. And for brands, if you think about how they reach consumers, they that changes as well. There isn't the equivalent of a paid ads market right now with AI. There's a lot of people trying to help you optimize your positioning in ChatGPT, but it's not exactly a science at this point. And I think there's some really interesting questions, which is what are the role of middlemen in this new world, like brokers and things like that. Similarly, I'm probably not alone in this. When I see my primary care physician, I upload my Lab results to ChatGPT before I see him and I ask different questions, like what is the role of expertise? All of your patients are doing that, like how does that change, you know, health care, the law, financial services? So that was a long winded answer, but I think it's very hard to predict the future. So I think it is very important to experiment. As a consequence of things shifting so quickly.
- [10:28]
T-Mobile Advertiser
Everyone deserves to be connected. That's why T Mobile and US Cellular are joining forces. Switch to T Mobile and save up to 20% versus Verizon by getting built in benefits they leave out. Check the math@t mobile.com switch and now T mobile is in US cellular stores.
- [10:48]
T-Mobile Advertiser Legal Disclaimer
Savings versus Comparable Verizon plans plus the cost of optional benefits. Plan features in taxes and fees vary. Savings with three plus lines include third line free via monthly bill credits. Credit stop if you cancel any lines. Qualifying credit required.
- [11:03]
Andrew Palmer
Anybody who has experimented with generative AI will know that there's a lot of room for improvement. Hallucinations still happen. Chatbots still occasionally go rogue. Security is a big concern. And although the models are getting better all the time, Brett warns that some problems are inherent in the technology itself.
- [11:26]
Brett Taylor
Yeah, the models are imperfect. And actually even more challenging I would argue is that models are non deterministic so you can give it the same prompt two times in a row and get two different answers. That makes testing and the concept of robustness very challenging because you want to be able to say, will the model never do this? I'm not sure it's possible to say that. One thing I think is really important to remember though is people are imperfect as well. So if you think in financial services, one of the things that's a big no no is a financial advisor promising returns, right? That's illegal in most countries and should be illegal in all countries because it's impossible to promise and obviously inappropriate. But people have done it. That's why there's all the regulations in place. Right? And in fact for a lot of banks, people record phone calls and have transcripts and have controls in place to inspect and say, did people do something wrong? I think that's actually a fairly healthy way to think about AI as well. If you stop waiting for it to be perfect and say it will be imperfect. Do we have the technical and procedural controls in place to recognize when it is imperfect and remediate it? Have we put in guardrails in place to mitigate that risk? It can be a very constructive conversation. And I think the more narrow the use case, the easier it is to put in those guardrails. So if you're a retailer and you want to have an AI agent help return an item, well, that standard operating procedure is very concrete. We have a 30 day return policy. Has the item been worn, you know, all those things and there's some risk of hallucination, all that. But you've narrowed the use case. So I joke, it goes from being a science problem to an engineering problem. And then as a technology matures, you can generalize more and more and more. But you know, for labs like OpenAI working on AGI, that's a science problem for a company. If you think about building an agent for a process, can you narrow the domain so it becomes an engineering problem? And you can put the controls in place so that when there are errors, you find them and remediate them.
- [13:28]
Interviewer
So if you think about the edge cases in your own client base with Sierra, what is the frontier at this point? I mean, if we had a conversation with a bank which said we can get comfortable with a kind of pretty simple form filling activities. If you start to move into the advisory space, for example, it just gets way too reputationally complex and problematic for us. So where are we on the continuum? What's the odds of the possible right now?
- [13:55]
Brett Taylor
Yeah. So first, I've been really pleasantly surprised how much regulated industries have adopted AI agents so far, as you intuited. You know, there are some conversations that are more complex than others. In the context of healthcare, scheduling an appointment with say an orthopedic specialist is relatively low risk because it's scheduling an appointment. Having an AI agent do a triage diagnosis of which specialist you should talk to is much higher risk because there's medical decision making there. And so I think a lot of people are saying, using the American baseball metaphor, getting some at bats with I think some of the lower risk use cases so that as the technology matures and in particularly the regulatory landscape matures, they have deep experience with this technology so they can evolve towards those more sensitive use cases. I think it will actually evolve more quickly than people expect because AI, while it is imperfect, it is actually more consistent than humans. And so if you go back to the giving financial advice, there's a ton of risk. AI can hallucinate. If anyone tells you there's no risk, they're selling you snake oil. However, if you look at a very large financial services firm and all of the communications they have with their clients, what percentage of those are imperfect? It's probably very high. Our expectations of human perfection are just much lower. And so we accept that. And so I think AI can actually improve the robustness of control. Whether or not that's the commonly held belief now, I believe it will become that over the next few years.
- [15:36]
Interviewer
One part of my brain is still trying to work out what an at bat is. But we'll leave that just in terms of customer reactions, because you're kind of describing like, people need to adjust to the idea of agents of AI. Humans are fallible. This is better. But to what extent do customers of your customers know that they're talking to an AI and how do they respond to it?
- [15:57]
Brett Taylor
All of them do. All of the agents built on Sira identify as an AI, say, hey, I'm an AI. And actually most of them say, I occasionally make mistakes too, because it's a trust building exercise. Right. You know, and the customer satisfaction scores of the AI agents built on Cira are incredibly high and almost uniformly higher than the human interactions that preceded it. One of my. The favorite conversations that one of our clients sent me was for a telecommunications company and an elderly man called because his receiver wasn't working, so he couldn't watch television and spent more than 30 minutes on the phone talking to this AI and ended with, thank you, you've been a good robot. It was fascinating to me just because the degree of patience this AI had with someone who probably in these interactions would have encountered a much less patient person on the other side. Just because of the inherent cost of staying on the phone with someone for that long and just the empathetic gesture of thanking it. He was quite aware it was a bot. I think we'll be pleasantly surprised. Just because AI agents can speak your language literally here in California, we, uh, there's English speakers, there's Mandarin speakers, there's Tagalog speakers, there's Vietnamese speakers. It's now free, effectively to provide multilingual service. Infinitely patient. There's no one behind you saying, hey, get off the phone. You have to do 10 more phone calls today to reach your quota or whatever it might be, and, you know, can accommodate even idiosyncratic things. It doesn't mean it's better for everything. I don't mean to imply that, but my co founder, Clay Beauvoir has a great way of putting it, which is for the history of computers. We've had to learn how to use computers. Think of the first time you used Microsoft Excel, just how intimidating it was. AI agents learn you and you just talk and it figures it out for you. So I think it's a really humane, really positive evolution in the history of computers, going from punch cards to keyboards and mice to touchscreens to now just speaking.
- [17:59]
Interviewer
What about some of the hidden costs here? So are there humans in the loop when people are interacting with your AI agent and how often? What does a handoff look like in practice?
- [18:11]
Brett Taylor
There can be and there should be in some circumstances. I'll just give you an example. In like the mortgage industry, if you're refinancing a home or buying a home, some of it is the actual presentation of a mortgage, which probably should be done by a banker. But a big part of it is collecting information like your income and assets and credit. And that's an example where an agent can just sort of augment an experience that you have with a banker and the banker can spend less time on, you know, collecting forms and PDFs and actually just doing what he or she does best. I would say it should just be a business decision. Do you want the AI to sort of be a co pilot, if you will, to a professional subject matter expert? Do you want it to be autonomous? Similarly, the client should add agency in that, you know, if you want to talk to a real person, you should be able to. The nice part about these AI agents, because they're good and they're not like the old bots that everyone hated, most people are opting into using them so you can end up actually having, I'll say, higher quality, more expensive interactions with your people because you've essentially unlocked a bunch of budget by taking a lot of the simpler transactional stuff off. With AI, we have one client who had offshored their customer service, who's now on shoring again as an example because the volumes have changed and they can afford it now and they thought it would be a better experience. So there can be some really interesting counterintuitive second order effects here.
- [19:34]
Interviewer
But to the extent that models can still go wrong, you've got to have some method of monitoring. Is your contention that that can be another model? How do you mitigate that risk?
- [19:45]
Brett Taylor
I like to think of it as defense in depth, which is a term in tech circles we usually use around security. Most companies now have a chief information security officer. And what defense in depth means is first you try to prevent anything from going wrong. So you lock all the doors, but then you say, okay, if a bad actor does get in, can we detect it quickly and limit the blast radius? So that's where you end up with, in addition to locking all the doors, you make sure there's good monitoring on everyone's laptop and you end up with all these layers so that even if one of the layers ended up with a vulnerability, you've mitigated it. I think the same should be true of AI. So I think the first layer should be AI monitoring. The AI at CIRO we use a concept called supervisor models, and they essentially supervise the decision making of the underlying model in real time. And say, is this a hallucination? Did they actually follow the standard operating procedures? Did they break one of the guardrails? And that's in real time. And then you can have a longer, more intense model, which is essentially after the conversation is done, evaluating it, you know, was this a low sentiment conversation? Did the AI agent repeat itself too much? Things that you can sort of look at with the context of the full conversation. And then you can, you know, maybe put those conversations on a queue so people can review them after the fact. And what's really nice about that is rather than just looking at maybe a random sample of conversations, you put the needles at the top of the haystack, you know, so the problematic ones are there. And the whole idea here is you use a combination of AI and humans in the loop, using AI to help those humans that are in the loop so that they're not just wasting their energy, but actually spending their time on the most sensitive, the most problematic conversations.
- [21:34]
Interviewer
I also wanted to talk about evaluation. So if as an enterprise you're trying to build things for yourself and trying to define what good quality is, what performance is, that seems to cause people quite a lot of trouble. You're inside organizations helping customers through that process, as I understand it. So what are the kind of big problems that people hit and how should they resolve them?
- [21:56]
Brett Taylor
This is going to sound reductive, but I think one of the most important things you can do as a business leader is specify a business outcome. You're trying to drive more than a technical outcome. I think it's really important when you think about your business processes where AI agents can apply. What are the key business metrics you actually care about? I'll just give you one that's simplistic, which is what percentage of calls? Don't people need to talk to a real person? Well, it's easy to make it 100%. You just don't let someone talk to a real person. And you or any consumer knows that can be an insanely frustrating experience. So that metric's just gamable. It's not a great metric on its own. Things like customer satisfaction score coupled with a metric like that are really productive because you tend to get a mix of consumer sentiment plus the sort of business outcome of how many of your clients could help themselves without having to wait in a queue.
- [22:51]
Interviewer
And that feeds into your own pricing approach.
- [22:54]
Brett Taylor
That's right. We do what's called outcomes based pricing at zero, which means we only charge our clients when the AI agent actually solves the problem on behalf of the customer and we have to escalate to a person, it's free. Our whole philosophy is that software ancient history. Four years ago, software was, you know, a productivity tool for a person. And if you asked a salesperson, was it your CRM system or you that drove that sale, of course they're going to take credit for it. Well, now in AI agents, if it's one of a Sierra agents answering a phone call or answering a WhatsApp chat and handling a customer service inquiry, you know whether it solved the problem. And you also know the customer satisfaction score. And why not pay for a job well done rather than pay for the privilege of using the software?
- [23:39]
Interviewer
So I want to just end by opening this out a little bit more into kind of where you think things are going. So you've described how in five years, say, the ecosystem for vendors will be that much more developed. You're in an interesting position where you've got feet in sort of two camps, right? With Sierra, you are one of those vendors, the application layer. You're also chair of OpenAI, one of the foundation models. If you take us forward five years, does the foundation model do everything? Is there a threat to your business at Sierra from a more competent Claude or chatgpt?
- [24:14]
Brett Taylor
I don't think so. I wouldn't have started Sierra, but I think it's a really important question. And certainly in the cocktail parties here in San Francisco, it's what everyone's talking about. One of the main things that these foundation models can do well is generate code to produce software. And if you haven't tried it, open ChatGPT and ask it to write an app for you or a website. And it will. And it's pretty good. And so you look at that and you're like, wow, the marginal cost of producing software is going down dramatically. What does that mean for the software industry? Why would I license a piece of software? Can I just go to an AI model and say, generate that software? For me and for my entire career, there's been a shortage of software developers. It's the scarcest resource at most firms. So it's a really important question to ask for a variety of industries. Not this is a software industry, but the consulting industry. The ramifications are dramatic. And as with anything so fundamental and so big, it's hard to actually predict the second and third order effects correctly. My personal opinion is that most companies don't want to build and Maintain software. So even if the act of generating a piece of software goes down by a lot, you build it, you own it, you know, and so I'll just take an ERP system as an example. There was a new accounting standard that came out for software companies called a decade ago, and it just changed the way you recognize revenue, particularly for subscription software businesses. And so being in, you know, at Salesforce at the time, I was, it was something that was a big deal for us. And if you imagine every single company has to go re implement those accounting rules and just how significant is right, like your auditor will care about it, amortizing that cost among lots of similar looking companies feels really rational to me. And I'm not sure just, just the cost of writing software is actually what you're purchasing from your ERP vendor. You're almost purchasing the audit that they've done and the bugs that other clients found that they fixed. That essentially ecosystem of collectively hardening that system that is so mission critical for you has innate value. So as a consequence, I think companies still want to buy solutions to problems. They don't want to buy, you know, software. And my hypothesis is that you will buy agents that do purpose tasks. And, you know, you might buy an agent that audits your financials every quarter, you might buy an agent that answers your customer service calls, you might buy an agent that generates leads for your sales teams and there will be an ecosystem of companies that compete to produce the highest quality agents in those categories. That's my hypothesis. But I say this with the humility that it is my industry, the software industry is being disrupted as much as any other, perhaps more than any other as a consequence of AI. And so if we talk again in a year, I might have a different opinion, but that's my opinion right now.
- [27:11]
Interviewer
So your vision is agents everywhere. Sierra's proposition is, I think fundamentally we can save you a lot of money on labor. What is your hypothesis on where humans continue to have an edge and what this means for jobs generally?
- [27:25]
Brett Taylor
I'll do a small correction. I don't think our main value proposition is labor cost savings. I think our main value proposition is improving your sales and your relationships with your customers. So if you think about, say, a mobile operator, if you look at what drives their business, it's customer acquisition and churn. And churn is actually the more insidious because once you spent all that money acquiring that customer, even a handful of basis points of churn reduction is worth a ton. And one of the main drivers of churn is customer Experience, customer service. And so if you think about you have a budget for talking to your customers and you've made it so the cost per interaction goes down from €10 to €1, just for argument's sake, you now have 10 times the budget for customer interactions. How much will you recoup in toss savings and how much will you invest back in reducing your churn or driving more sales? Cost reductions are interesting, but I mean most CEOs are hired and fired based on growth. But I do think your point on jobs, certain jobs are going to be more capably done with an AI agent than a person. And that has been true in the past. If you look at the birth of the automated teller machine, it changed the role of people in bank branches all the way back to agriculture where when the US became a country in 1776, most of our country were farmers. And so this has happened many times. Jobs have changed a lot. The premise I strongly disagree with, and again I come at this with a lot of humility, is the idea of like jobs will go away and we'll have nothing to do. I just don't agree with that. I think actually we just lack the imagination to think about what jobs will be formed around this technology. The question though is just how quickly the technology evolves. You know, my mom worked for a oil company for 30 years and she didn't have to completely reskill every five years. Right. It was a much slower pace of adoption. The electrification of the US and the UK took decades and we're now have a technology where I'll just take my own profession, software engineering, where what is the best practice today is completely different than it was 12 months ago. It is a challenging expectation for the individuals at your company to have to reskill that quickly. And I think it's happening for a lot of white collar jobs where that wasn't the expectation going in. So I think that's really challenging. I'll give you what I think is a really optimistic take on it though, which is we're all in the same boat together. There's no software engineer here in the Sierra offices that's an expert in coding agents any more than any other software engineer because the technology is all new. I joke. It's like we're all accountants and Microsoft Excel was invented last weekend. No one knows pivot tables yet, but if you're the one who learns it first, you're going to be like the best accountant on the block. And so I think it's intimidating, but with a kind of a beginner's mindset. I think the individuals at your firms that actually adopt this technology the best and most fluidly can actually accelerate their careers. And that's really interesting because there's no one on the outside you can bring in who's better than the people you already have. And that's very different compared to some of the other, I'll say, economic disruptions that have happened in the past. But it is challenging. I mean, imagine you're 58 years old, you're contemplating your retirement, and all of a sudden the skills you've developed through your career when you're supposed to be in the prime of your career are not as relevant. That's a challenging situation to be in. So, as I said, I think it's actually appropriate in some ways that the software industry is disrupting itself as much as any other industry, because I can tell you the people working on it are having the same insecurities that we're talking about right now. And I find there's something appropriate about that. But I'm optimistic for the long term and mildly anxious for the short term is the short of it.
- [31:21]
Interviewer
I guess the interesting thing is you're actually at the confluence of two things, right. Coding is right at the frontier of this and feels this apprehension. Customer service is another good example. So your advice to a software engineer is learn AI, get ahead of the group. What's your advice to a kind of like a call center agent?
- [31:39]
Brett Taylor
Well, it's interesting. One of our clients, the team that managed the call center, now their job title is AI Architects, and they're working on the AI agents themselves. And it, I think, proves the principle that actually there's no expert in this. And the people who are managing call centers are just as equipped, in fact, deeply understand the customer experience and they can manage AI agents as well. I think for the individuals who are grappling with their own identity in this world, you might have to seek out opportunities in other departments and be sort of savvy, just because if certain types of interactions are going to be done by agents just because it's appropriate, what are the areas that my company is going to invest in? And you may need to position yourself for that. And that's challenging. I don't mean to minimize the complexity of that, but that's the way I'd think about it. Cost savings in an area leads to investment in another area. As an individual employee, how do you sort of jockey for positions that you benefit from that investment?
- [32:40]
Interviewer
Last question, if I may. And that's. You described yourself as an ex suit. And you must be running a ton of people right now at Sierra. So how has AI made you a better manager?
- [32:50]
Brett Taylor
I love using AI as a creative foil. If I am writing a note on our Strategy, I'll use ChatGPT to critique it and find flaws. I don't use it to write because I find the act of writing my process of thinking, and so I find generating content with it actually eliminates a key part of my deliberative process. But I love it as a creative foil and a critique. Similarly, I do think it's a great productivity enhancement. Whether it's slack or email. Having AI summarize things, it's hard to keep tabs on everything going on. And there's so much information that I didn't read before that. Now I can use AI to help me read as well. Those would be the two things that I think are remarkably useful tools.
- [33:38]
Interviewer
Is there anything that it doesn't do yet that you wish it did? What's your own frustration?
- [33:43]
Brett Taylor
I do hope there's a day when I'm driving in on my commute that I can be talking to an AI and triaging my email inbox and I haven't quite found that workflow, but it feels inevitable. You can see the progress in the technology almost daily. So it's more of like a matter of when than hoping. Hoping it gets there.
- [34:00]
Interviewer
Well, if you solve like holding on the line and email, then you're up for some kind of peace prize. I think so. Thank you so much, Brett. That was great to speak to you. Thanks for your time.
- [34:09]
Brett Taylor
Thank you for having me.
- [34:12]
Andrew Palmer
On the next bonus episode of Boss Class, a conversation with a venture capitalist whose firm specializes in funding AI native startups, including Sierra. She's called Sarah Guo, and of all the interviews I did for this season, this may be the one that stuck with me the most.
- [34:32]
Sonos AI Support Agent
One thing we say internally is like, the floor is lava, right? You are working on fluid ground right now, and so if we want to find founders who share this worldview and then think hard about what is invariant.
- [34:53]
Andrew Palmer
Boss Class is produced by Lawrence Knight with support from Alicia Burrell. The series editors are Sam Colbert, Pete Norton, and Claire Reid. Our sound designer is Weidong Lin, and Darren Ng composed our music. Our executive producer is John Shields. I'm Andrew Palmer. This is the Economist.
- [35:15]
Sonos AI Support Agent
Would you like to speak with a human agent for more help?
- [35:18]
Interviewer
I don't think so. I think that's good. You've been a very, very good robot.
- [35:23]
Sonos AI Support Agent
Thanks for saying that. If you need help again, just reach out. Have a good day.
- [35:32]
T-Mobile Advertiser
Everyone deserves to be connected. That's why T Mobile and US Cellular are joining forces. Switch to T Mobile and save up to 20% versus Verizon by getting built in benefits they leave out out. Check the math at T Mobile com switch and now T Mobile is in US Cellular stores.
- [35:52]
T-Mobile Advertiser Legal Disclaimer
Savings versus comparable Verizon plans plus the cost of optional benefits. Plan features in taxes and fees vary. Savings with three plus lines include third line free via monthly bill credits. Credit stop if you cancel any lines. Qualifying credit required.