Showing you my AI chief of staff (OpenClaw practical guide)

0:00Two days ago, Goldman Sachs' chief economist said that AI investment had added, in his words, basically zero to US GDP in 2025. But here's the thing, they're looking at companies across the economy, but they don't look at people like me. A small number of us have already deployed what amounts to a five, maybe a 10 person team working round the clock on our behalf. I'm not special, I'm just early.

0:26Azeem Azhar:The gap between the people who've started and the people who haven't started is widening every week. Is this going to make me worse at certain things? Am I going to think less carefully before delegating because the system is so capable? Am I sharpening my judgment or losing the muscle that that judgment requires?

0:51Welcome to Exponential View, the show where I explore how exponential technologies, in particular AI, are reshaping our future. And it does feel like that future is coming ever closer and becoming more like a discussion of the present. Now, each week, I'll share some of my analyses or speak with a guest to make light of a particular topic. But this week, I want to show you something. What you're seeing on the screen right now is a piece of software. It is a knowledge dashboard that I use to track what I need to do each day. It brings together material from my internal systems, from our CRM system, from our research engine, from X, from my email, from other sources, and it ranks the things that it thinks are important for me.

1:44And given my work, a lot of the things that are important for me are outward facing. They're not necessarily about projects and things that are happening internally. This is a live knowledge dashboard. The thing about this is it's live now, right now, and it runs on a Mac Mini in my studio, just over there. You can't see it. It's in an equipment cabinet. This didn't exist eight days ago. I haven't written a single line of code of it. It was put together by six AI agents overseen by a super agent, or perhaps I should say it was one AI agent overseeing six sub-agents, and they built it overnight over the course of a couple of days with my feedback.

2:27They argued about the database schema at three in the morning. They wrote tests for each other's codes. They deployed it and I woke up and it was running. The first time it was running, it was a bit ugly. It was a bit shonky as any new piece of code, but ultimately it works. And I've iterated a couple of times and it's something that I now use every day. Now that super agent, the primary agent that orchestrated and coordinated all of that is called R-Mini Arnold. Now the R comes from Isaac Asimov's novels. In those novels, robots that were intelligent were given that moniker R for robot, R Daniel Olivo, and it's what we use when we are naming agents of the type that I've just described today with an exponential view.

3:15What about the name Arnold? In the Terminator films, in the second Terminator film, Arnold Schwarzenegger comes back to protect humanity from the even more Terminator-y Terminators. And so our mini Arnold, because my agent is not as big as Mr. Schwarzenegger, is sitting in that Mac mini and doing all of that work. I've been running our mini Arnold or RMA, as I will call it during the course of this conversation, for about a month. And it has really changed the way I work more than any single tool since the web browser. I can't overstate it. You're going to hear me talk about it now for 25 minutes, but it has changed the way I work.

3:58And what is it? Well, Armine Arnold is, for want of any kind of better word, definition, phrase, the academics can argue about this. It is an AI agent. It is the AI agent that does things that are similar to the AI agents that were imagined back in the 80s and the 90s. think about Alan Kay's famous knowledge navigator. And what I've experienced over the last three or four weeks is that a lot of the discussion about AI agents, especially when we think about it in economic terms, perhaps might have missed the point entirely. Two days ago, Goldman Sachs' chief economist, Jan Hatsius, said that AI investment had added, in his words, basically zero to US GDP in 2025.

4:46And earlier in the week, there was the paper from the NBER that suggested that 80 % of American, British and Australian companies were reporting no productivity gains. And that headline is repeated in lots of other places. There was a PC magazine that said the AI agent hype is real, the productivity gains aren't. Now, there are many ways to interpret that number. Of course, not least, it means that 20 % of firms just three years after the chat GPT moment do claim to see productivity benefits. And that concords with our proprietary tracking of US public companies, Gen AI claims. It lines up with what our friend Eric Brynjolfsson at Stanford University is starting to say about the productivity data that is becoming visible.

5:31But here's the thing. Those numbers measure a particular type of real thing. And perhaps they're measuring something that is less important. Maybe they are measuring the wrong thing. They're looking at companies across the economy.

5:45Azeem Azhar:Sometimes they look at individual companies, but they don't look at people like me and they can't capture what is going on there. The revolution isn't merely general intelligence. One of the things I've observed is that when the cost of delegation falls below the execution cost for a growing fraction of what we call knowledge work, when that cost falls by an order of magnitude, you do much more of it. And that's basically the whole story. What RMA has done is it has made it really, really easy for me to just bark orders sometimes into a system in parallel and get lots and lots and lots of work done.

6:26If you think about a big company, they're running pilots, they're building governance frameworks, and they're hiring chief AI officers, a job that exists today and will not exist in five years.

6:37Azeem Azhar:But they have to contend with all the issues of big companies. And that's what turns up in the statistics. A small number of us have already deployed what amounts to a five, maybe a 10 person team working round the clock on our behalf. Now, I'm one of those people and I'm not special. I'm just early. The gap between the people who've started and the people who haven't started is widening every week. And that's not just because the technology is getting better constantly, though it is, but it's because that relationship that you have with the technology compounds. That relationship starts with when you started to use ChatGPT, when you started to move from quick summarizes paragraph of text to more complex multi-term prompting, when you started to use deep research, when you started to think about your prompting strategies in order to get better outputs.

7:32Azeem Azhar:that compounds rapidly. But the other thing that compounds is that the agent, RMA in my case, has worked with me for 30 days and it knows things about me that no brand new tool does. It knows things in certain types of contexts that you don't get if you're using Clawed or ChatGPT with their memory capabilities. Let me just take you through the bits and pieces that make up R mini Arnold. R mini Arnold runs on a Mac mini. It's got 64 gigs of RAM. Look, I bought this Mac mini for the agent. I'm obsessed with buying more RAM than I might possibly need, because it's the one thing that's really complicated with Apple computers to upgrade.

8:15You can always add more storage. You stick an SSD in, but RAM is a sort of one-way street. It's got 64 gigs of RAM. It's connected by wired Ethernet, a 10 gigabit Ethernet directly to my firewall, has a five gigabit internet connection out to the world. And it sits in the equipment

8:31Azeem Azhar:cabinet in this studio, running 24 hours a day, drawing about the same amount of power as a desk lamp. The software that it's running is called OpenClaw. I've written about it a lot on Exponential View. It's open source, it's self-hosted, it runs on my hardware. My data largely stays on my machine. Some of it is in a shared Dropbox in the cloud so I can send things to Armini Arnold. Some of it, in terms of the long-term memory, gets exported out to a vector store that's in the cloud so that it can learn my preferences over more extended periods of time. And the model underneath most of the time is Anthropix Claude Sonnet 4.6 model.

9:17Sometimes I flip up to Opus 4.6, sometimes I go down to the quick and easy Haiku 4.5. And from time to time, RMA might call an open AI perplexity or a Grok model if there's something really particular that I need. But I would say from time to time, not even one in 100 queries that I do. Last week, Sam Altman snagged Peter Steinberger,

9:44Azeem Azhar:the developer behind OpenClaw. He's joined OpenAI. He had been pursued by Mark Zuckerberg, messaging him on WhatsApp. I don't know how Mark got his number, but I guess Mark owns WhatsApp. So maybe he has ways to see if they could support that business. And I know that many, many Silicon Valley VCs were really trying to get hold of OpenClaw, trying to get a hold of Pete to see if they could support that business. So you can draw your own conclusions about what that tells you about how much of a shift in consumer user interactions we've seen from the model of the AI agent that OpenClaw has delivered to us.

10:24So that's a structural story,

10:26Azeem Azhar:and I've written about it on the newsletter. You can go off and see some more details. Let me describe to you what it actually looks like. Like many of us, I wake up early in the morning, by the time I'm downstairs stretching or making coffee, RMA has been running all night. And certainly by about 6 or 6.15 in the morning, a morning brief arrives on my WhatsApp. And that morning brief is similar to things I'm sure you're used to, the calendar for the day, priority emails flagged overnight. But of course, given the work that I do in research and analysis, it includes interesting analysis. The top stories that have come out of PRISM, which is our research backplane that we use at Exponential View that has thousands of things that the team has read and annotated and their own analysis.

11:16Azeem Azhar:It also includes RMA's own analysis of what it thinks might be interesting for me, given the wider context it has of me. And part of that wider context is the information it gets out of Orbit. And Orbit tracks all of my major relationships, work relationships. So it's a flashy CRM and Orbit will be connecting the types of people I might be meeting in the next few days with the research and the stories that are happening today and RMA assembles all of this together and delivers it to me. I'll get a summary of all the tasks that have run overnight and I will run quite complex research and coding tasks overnight.

11:52Azeem Azhar:I'll be told which ones succeeded, which ones failed. There's a whole lot of housekeeping RMA runs as a system and it might have to give me details of things that need my attention. Now, what are these tasks? Well, some can be quite complex. So you may have seen that a few days ago, some substack called Citrini Research wrote an essay that was pretty interesting, a detailed scenario of an economic collapse powered by AI that ran out for two or three years. It was obviously trending on Twitter, it was blowing up on substack. And according to some of the financial press, it also affected the markets and resulted in a real shock to the markets at a time.

12:29Azeem Azhar:So I was really curious about digging into the authors and the team behind Cetrini and behind that essay. And so I asked Armini Arnold to do some research. Who are those authors? What's their heritage? Where have they come from? How serious are they? How robust was the work that they had done? And now I know RMA set up a team of investigators to go off and comb through this. I think at one point there were five sub-agents working on this task and doing web searches and drilling down and trying to see what they could learn. And I've got back quite an interesting report, which if I have time, I may put some of in the newsletter on Sunday.

13:09Azeem Azhar:But that wasn't the only thing that was happening overnight. So another set of agents were refactoring the code of my CRM system. What does that mean? It means that this is a system that I designed and I've built over the course of a few weeks. And of course, I'm interested in shipping features. I'm much less interested in thinking about the elegance and the sort of structural integrity of the code. That's true for any code. It's the accumulation of tech debt. I told RMA that what I wanted to do was assemble a team of security researchers, quality analysts, documenters to walk across the code base of the CRM and fix what was broken, reporting back to an architect who had confirmed that everything still worked.

13:54Azeem Azhar:It was a major piece of work. Several thousand lines of code were touched overnight. I also have a different team that works every single night for me of agents. These ones are running OpenAI's GPT codecs. And what they do is they walk across all of my other GitHub repos, making small improvements, finding tiny bugs and shutting them down. And finally, RMA has a team of security agents, some of which are inside the firewall, some of which are outside the firewall, which effectively find and patch security vulnerabilities across the system. And typically, they don't find much. But normally, once every three or four days, something does crop up.

14:30So this is like having a

14:31Azeem Azhar:chief of staff who can draw upon a number of specialist teams, essentially constantly overnight. And if you think about what I just described there, how much of that was me initiating work? Well, two of the pieces, the piece about checking the CRM code and doing the research and the digging around the Citrini essay were de novo tasks for the day. But the rest are things that are just scheduled and run day after day. Now, what is the interface for all of this? The interface is WhatsApp. The reason is that's the interface that I use for so much else. Why not just use WhatsApp? It's the same app that I use to message my wife and my family and my friends and my kids and the people I work with.

15:12Azeem Azhar:There's no special dashboard required. I have built that dashboard that I shared with you earlier because it was really useful given the breadth of things that I'm working on to have a dashboard like that. I mean, you just don't really want to be flagging research stories on and off through WhatsApp. But you don't need that dashboard. And in fact, I only check in on that a couple of times a day. What I do hundreds of times a day is use WhatsApp effectively to delegate and check and verify work that my agent and its team of agents are working on. So today I open WhatsApp and I talk to it. The agent comes back.

15:53Azeem Azhar:It picks up where we left off previously. It knows my priorities. It knows who to contact and why. And I'm going to show you what that looks like. So here you can see what my WhatsApp looks like. I have a tag actually for all of the various RMA agents. So this is the thing that's quite strange. It's not a single conversation. It is eight conversations. In fact, there's slightly more than that. Each different bit of context I have for long running tasks with RMA, I create a communication lane for. So R. Mini Arnold, right at the top, it's one of my favorites, is the general chuck it at it and figure it out.

16:35Azeem Azhar:R. M. A. I. G. B. is the channel for my new book. The sub-agent there has all of the chapters. It knows the chapter structure. It knows the argument. It knows all of Chantal's latest findings. It has access to Prism so that it can look things up for me. The channel on orbit is the CRM. It knows about my contacts and other details, but it also has access to the GitHub repo. So when I see a bug quickly during the day, I can tell it to fire off and fix it. RMA EV research are all the things that relate to the research that we're doing within Exponential View, whether it's for the newsletter or it's for something else.

17:18It's the same AI, but with eight specialized instances all running in parallel, all with their own memory, all with their own tasks, all with their own context.

17:28Azeem Azhar:Now, the script says they don't talk to each other and each one knows deeply about its domain and not much about the others. The truth is they do sometimes get confused. And sometimes I will be in the EV research channel and I'll get a response from one of the other channel lanes showing up. This is early software. There are going to be these types of issues and teething trouble. So if we then think about what that means, I mean, it's a really, really kind of remarkable situation because, of course, I've got this master orchestrator, Armony Arnold, but I have these eight contexts, which it should technically adhere to.

18:04Azeem Azhar:And it's like having those eight simultaneous relationships, but it's with the same entity. There is some shared context. I haven't figured out exactly how to do this perfectly. I'm still trying to figure it out. I've experimented with other things. I experimented with using Telegram for this, but I don't really like Telegram as an app. I experimented using Slack for it, but I just again found I don't spend as much time in Slack as I do in WhatsApp. I had actually build me a small app that was a persistent web app where I could keep track of all of these channels. None of those worked for me. Those approaches might work for you.

18:40Azeem Azhar:everyone is different. The asymmetry in all of this I find most interesting is not AI and humans, it's actually individuals and institutions. Because I'm currently running these capabilities that I doubt any Fortune 500 company has deployed at this level. So let me tell you about the type of impact that this system has had for me. And in that, it'll address questions like, how much does it cost? Or is it worth it? A quick note, if you want to support us in bringing more of these conversations to the world, please consider subscribing to the show. I'll give you three small vignettes. I had a wonderful meeting with a major sovereign wealth fund a couple of days ago.

19:19It was a big meeting. They're impressive, super, super smart. And I had to rush straight from having a filling at the wonderful dentist just down the road from me up in Hampstead in London. And it was going to be a really, really hectic morning. RMA had figured out a brief for me and said, you've got this dentist thing, and then you've got to run straight to this meeting. Here's a brief. I recognised the name and prepared me for it. The briefing was pretty thorough.

19:47Azeem Azhar:Of course, it had all the obvious things you'd expect because it's gone to the CRM and it's pulled those details. But it also has access to all of my granola transcripts and any other conversations I've had that are relevant. And it has access to PRISM. And so PRISM contains lots of research, as well as our house views, knowledge of how the team in Exponential View thinks, uses frameworks, thinks critically. And it knows a lot about the person I was meeting. So the context I was given was really quite remarkable. And I've used CRMs that prepare you like this previously. And I've used AI systems over the last year or two that try to prepare you like this seriously.

20:25Azeem Azhar:But they sort of lack that context and that nuance that I have through RMA. And I will explain in a few minutes why I have so much context and nuance there. What I got was something that described the investment posture around compute, data centers, chips, their wins, the open questions, all anchored in a really broad set of news and analysis that I might have missed. So I walked into that meeting differently. I wasn't scrambling to look somebody up in perplexity while I was running out of the tube. I actually had some real context. It's the kind of thing that a great chief of staff with plenty of time would have prepared if I had one and had had the time.

21:05Azeem Azhar:The thing that surprised me, because I hadn't told RMA to do this, was that after the meeting, I moved off to the next thing, which, as it happened, was to go to the Apple store to get my laptop screen repaired. It updated the CRM with the fact that I'd had the interaction. It didn't have much details, but I did have a WhatsApp saying anything you want to add as notes from this interaction. And, you know, that, again, was just an open loop that I would have had to remember and had to surface. And it also reminded me that I've met a peer to that person previously, and whether it's worth reconnecting with them as well.

21:41Azeem Azhar:Pre-meeting briefing, that's fine. That's reasonable inference. The quality of that briefing, better than things I've seen before. The post-meeting logging in a quite a non-invasive way. And I would just say something about that non-invasiveness, which is if I have a Zoom meeting where I've run granola, I don't get that flag. I guess it sees it's got the granola transcripts and it can populate the CRM that way. Now, here's the thing. I actually don't really know how that happened and how it worked. I don't know if it'll happen reliably week and week, day after day. I mean, these LLMs are jagged, as we know, wobbly in some cases.

22:15Azeem Azhar:But this isn't the case of the AI doing my homework. This is an agent that understands the shape of that professional relationship and all the effort I've put in to ensure that there is enough context around it. And it knows that a meeting doesn't end when you leave the room. So I found that pretty interesting, quite special, again, compared to things I've used previously. Here's a second example. And I love this example because it's about how this episode was made. So 24 hours ago, I needed a script for this show. I knew roughly what I wanted to say. I had the thesis. It's the delegation cost argument.

22:56Azeem Azhar:I had a few stories. I know the audience. What I didn't have was time. And, you know, as regular listeners know, I work with Chantal normally on the scripts. So I thought I've had a pretty busy Thursday. It's going to take me four or five hours. I was frankly exhausted by the time I got home. So I went to WhatsApp and I gave RMA a brief. And I said, look, I'm doing this live sub stack. It's kind of about you. It's tomorrow. Here's the thesis. Here's the tone. Here's roughly what I want to cover. And I want it written in my voice, the voice I've been cultivating over 30 years of my professional experience.