The AI Workflows Behind Every's Consulting Team

Natalia Quintero joined Every as head of consulting with a mandate to bring AI into the workflows of executives at hedge funds, private equity firms, and tech companies. She is also a recent Codex convert—someone who spent months resisting the tool before Dan Shipper’s daily pestering finally got her to try it. Natalia encountered Codex as a non-technical builder who had learned to navigate file systems and folder structures in Claude Code through sheer effort. She’s now used Codex to do everything from automate her CRM setup to build a portal to manage her father’s medical care. Dan talked with Natalia for AI & I about what it looks like to go from non-technical to building software with Codex, why Every still uses software-as-a-service products from Attio and Asana instead of vibe coding their own tools, and where she thinks AI agents like Every’s internal Claudie employee require human managers. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Timestamps: 00:01:05 Introduction 00:02:35 How Natalia manages Claudie, the consulting team's AI project manager 00:04:55 Why the consulting team still pays for SaaS products 00:11:47 Codex as a game changer 00:14:55 Building personalized learning guides and illustrated explainers with AI 00:21:40 Inside Natalia's AI-powered email triage system 00:26:44 The shift from knowledge work as sculpting to knowledge work as gardening 00:28:57 Using Codex to one-shot a custom CRM 00:33:16 Using Codex to build an app that coordinates her father's medical care Links to resources mentioned in the episode: Natalia Quintero on X: https://x.com/NataliaZarina Asana (project management): https://asana.com Every Consulting: https://every.to/consulting Go to attio.com/every and get 15% off your first year.

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Dan Shipper?

  You go and teach executives and other people at big companies how to use AI. And so I think what you're doing is a good window into how great operators and executives are starting to use this stuff.

• 0:10Speaker 01

  What Codex helped me do was basically create kind of like an operating system. My email knows what's going on more than I do. I'm just so bullish on all of the administrative tasks that will suddenly kind of like be taken care of. Because now we have this sort of like super alien tool that can support on those things.

• 0:27Dan Shipper?

  Knowledge work now is turning into something like gardening, where when you're gardening, you're creating the conditions for the growth to happen, but you're not like making the plant with your hands.

• 0:52Dan Shipper?

  Every is the only subscription you need to stay at the edge of AI. If you care about being on top of the latest models and using the latest tools, you have to subscribe to Every to separate out the signal from the noise. Go to every.to/subscribe today. Natalia, welcome to the show.

• 1:05Speaker 01

  Thanks, Dan. Good to be back.

• 1:07Dan Shipper?

  So for people who missed your last episode, you are our head of consulting at Every.

• 1:13Speaker 01

  That's right.

• 1:13Dan Shipper?

  You are also the manager of Claudi, consulting's AI agent employee, which was, who was the star of our last episode together. And I wanted to bring you on because I feel like every couple of months, things shift so radically. And for me, you're one of the like bellwethers of how things are changing. Because you're an early adopter yourself and you go and teach executives and other people at big companies how to use AI. And so I think what you're doing is a good window into how like really great operators and executives are starting to use this stuff.

• 1:53Dan Shipper?

  So the last time we chatted, Claudie, which is the the internal AI employee agent that we built to basically help to run the consulting business, uh, to, you know, send out sales proposals and manage the CRM and all that kind of stuff. Claudie was like this nascent thing that the test, who's our senior AI engineer was like, sort of,

• 2:17Dan Shipper?

  uh, what's, what's the word for it? He was, uh, he was sort of like Wizard of Oz-ing it in the background, like making it work, uh, minute by minute. And I, but I feel like now Claudie is like actually working, like the, the model releases over the last couple of months have, have dramatically changed how much it's able to do. So give us an update on Claudie. How are things going there?

• 2:37Speaker 01

  You know, it's, it's funny with the speed of AI. Claudie, it feels like Claudie is like just not novel. You know, it's, Claudie is an agent that does work for us every day and Claudie has its own LinkedIn and Twitter feed and, you know, manages our dashboards and, um, you know, has a trust battery now that's new. Uh, so, you know, it's running on a loop to sort of like self-evaluate performance and to improve itself, given the feedback that we give it. And Claudie's thriving, I guess.

• 3:14Dan Shipper?

  Well, one of the things that that's interesting is you, you hired Claudie to do operations stuff. But you're also now hiring an operations person. So what have you learned about the uses and limits of these sorts of internal agents for stuff that you might want to hire a human for?

• 3:29Speaker 01

  Yeah, you know, it's really interesting. I think, you know, I, as, as we've all uh, been using AI more, I think the, the thing that we keep coming back to is that AI is really good at executing against a standard operating procedure and Claudie is exceptional at that. Uh, but Claudie still needs two things. One is it needs constant oversight and management to make sure that it's doing those things really well, actually. Uh, so you know, the sort of question of like taste and, you know, reaching for excellence still requires direction and sort of managerial support, uh, which, you know, can be quite tedious and time consuming. So there's still quite a bit of time involved there. Uh, and, and two is

• 4:13Speaker 01

  When you are working with people, you know, as much as I love working with Claudi, I I want to interface with people, right? And I find that

• 4:21Dan Shipper?

  I can't really relate, but I I see I see why someone might feel that way.

• 4:28Speaker 01

  And the reality is that, you know, while we do have all of these rich dashboards and all of this data that Claudi is populating, we need we need someone to surface what is interesting about that data, what the signals are and to help lead those conversations. And so actually, I suspect that we will continue to expand the team to build on the data and information that Claudi surfaces so that we can actually do interesting things with it.

• 4:54Dan Shipper?

  One of the big things that you went through recently, which I think is super relevant to anyone inside of a big org or anyone running a software company is you actually bought a CRM. And previously it was all Claudi glued together with Google Sheets. And I think there's this whole narrative running around. I think honestly, SaaS stocks are back. So maybe the narrative is a little bit less present than it used to be, but it's still on people's minds is like, are you just going to vibe code all SaaS? You know, like Fable currently is banned, but I'm sure it'll be back. Maybe it's even back by the time this episode comes out. But like if Fable can just one shot a CMS, like, why would you use one?

• 5:33Dan Shipper?

  But you you have the ability to make your own CMS and we have enough resources internally for us to vibe code one. But you decided not to.

• 5:42Speaker 01

  Yeah.

• 5:42Dan Shipper?

  Or you decided to move off the the sort of homemade one onto a professional one. So why would you do that?

• 5:47Speaker 01

  Yeah. So despite my hopes and aspirations that I could do all of the things

• 5:55Speaker 01

  and, you know, become an engineer and maintain all of these engineering products that I

• 6:00Dan Shipper?

  This one I can relate to this one.

• 6:04Speaker 01

  It turns out there are actually private and public companies whose entire business it is to do these things really well. And sometimes these like very specific things really well. So, um, you know, we, you know, I vibe coded a CRM tool that allowed us to manage our sort of like sales pipeline for a while.

• 6:26Dan Shipper?

  And it was managing in Google Sheets. So it was like Claude, Claudie was the, was the glue between what was going on in Slack and the meetings and Google Sheets.

• 6:33Speaker 01

  Yeah, exactly. So basically Claudie what had access to was able to read my email, was able to read our meeting note takers notes, uh, was able to digest kind of like an inbound, uh, leads that came and then you track this all in a Google Sheet. And, and then, you know, eventually that became a, a database that we were managing. And these things just require maintenance, right? In order for the data quality to be good enough that you can do interesting things with it, you need to, you know, like almost like Claudie, you need to be on top of the, the quality of the data. And so, uh, it turns out this is Atio's entire business.

• 7:11Speaker 01

  And so, you know, I think one of the challenges with AI, uh, I certainly have is that in, you know, in the era of AI, you can build anything. I think I even said this in the last podcast. Uh, the question is, should you build, uh, and maintain, uh, whatever you, you actually build? And I think in this, in this case, and probably in other use cases, we also rolled out Asana for our project management system. Um, I think we're able to do the scale of the work that we are able to do because of Atio, because of Asana, um, and because of Claudie managing all of that information is much greater than if we didn't have those tools. Um, but now we, we just have less burden on the team to maintain that.

• 7:50Dan Shipper?

  Can you give me like a, like a concrete example? Cause in my head, I'm like, well, CMS is just, it's just like customer records and then, and that's just a spreadsheet. So you should just be able to like have Claudie do everything. So can you give me like a deeper dive into what specific kinds of things came up that were harder than you expected?

• 8:08Speaker 01

  Yeah, so you know, uh, so yeah, totally. Like if you, uh, let's talk about maybe like a traditional sort of like sales pipeline lead, right? So there's the, they come in as an inbound, you have these sales logic rules where like certain things need to happen in order for them to move further down the pipeline until they are a converted client. And sometimes those things happen very quickly. Sometimes they happen over a longer period of time. With my human brain, I think I can kind of track what's going on over like a two to three month period. And then any conversations that are taking place outside of that. And af- after a certain amount of volume, I just can't quite track. Um, with, with, uh, with a tool like, like, you know, Atio.

• 8:51Speaker 01

  It is, it has access to all of the things that Claudia had access to, but it has really robust logic. So that it can, um, basically, you know, track the, the movement of a deal over the course of the pipeline. And it can kind of flag it to me in different ways in a way that I would have had to supervise Claudia to do. Um, and, and was not, um, it, it, Claudia was just like not inherently set up for it. It could do that if I spent more time, you know, training it to do that. Um, but it's, it's ultimately like, you know, sort of like a, a reward pay, payoff thing.

• 9:24Dan Shipper?

  I think one of the things that's unintuitive about software is real software is a compilation. It's like a logical machine that com- that compiles thousands and thousands of little logical rules to, that, that you wouldn't expect you would need beforehand. And, uh, and, and the whole job of the company and the engineers is to like, gather all the rules that are needed and then put it into the system. And when something breaks, like change the rules.

• 9:50Speaker 01

  Yeah.

• 9:51Dan Shipper?

  And AI is very good at, um, w- working around that kind of deterministic system and writing it, but. It's not going to one-shot all the rules that you're going to need.

• 10:02Speaker 01

  Yeah, needless to say, I've become a really big fan of PRDs.

• 10:07Dan Shipper?

  Yeah.

• 10:09Speaker 01

  And actually scoping what I'm building, which I, you know, I think I've improved in both scoping and building higher quality things and also making that decision earlier of whether it's going to be worth it for us to just invest in a tool versus for us to build it out.

• 10:23Dan Shipper?

  Yeah, I think a good metaphor is, I'm sorry, I'm just like, my brain is just cycling on the difference between software and language models, but a good metaphor is software is a little bit like your bones in your body. And a language model is a little bit like your brain and your ligaments.

• 10:39Dan Shipper?

  So it, like, if you didn't have any bones, there would be no structure and you'd be like just sort of a flopping jellyfish on the floor. But, but if you didn't have your brain and your nervous system and ligaments, you'd just be sort of a pile of sticks. And I think that's, that's a good way for software and language model. That's, that's how they sort of start to work together. And of course, language models can grow bones, which is interesting. That's maybe a bit different from the way we're set up, but growing bones well is complicated. And a whole body plan is very complicated. So, but, but you said something earlier that I think is, is really interesting, and I want to push on, which is, I see you going from not technical to like building stuff.

• 11:25Dan Shipper?

  And I feel like there's, you tell me if I'm wrong, but I feel like there's been a sort of step change for what you can build and what you can attempt over the last like month or two. Do you feel like that's right? And if so, tell me more.

• 11:36Speaker 01

  Yeah, 100%. I would say the other, you know, kind of like riffing on Claudio a little bit in the evolution of how I work with Claudio and also how I work with other tools. Codex has been maybe the single greatest improvement.

• 11:54Speaker 01

  I have to, you know, I have to confess on the podcast that Dan did tell me to download Codex. Maybe every day he saw me for weeks.

• 12:06Dan Shipper?

  I'm very annoying about things I think are good.

• 12:10Speaker 01

  And I think you have something that I don't have as much of, which is the sort of like fearlessness when it comes to trying out a new AI product. And I think I still have a little bit of like, you know, like, okay, like, now I have to figure out this whole other thing. And like, I love Claude Code. And, you know, I'm very comfortable and like, you know, these like folder structures and file systems that I've created. And Codex has like been life changing, right? Totally life. So thank you. Thank you for your persistent follow up.

• 12:38Dan Shipper?

  Anytime. Happy to be annoying anytime. Tell me why it's been life changing, especially coming, someone coming from Claude Code or the coworking universe. What were your expectations going in? What was it like? And then how how has it changed what you're able to do?

• 12:53Speaker 01

  It really feels like Codex, I think you've said this before, Codex, you know, looked at the things that weren't quite working with Claude Code, and then it just fixed it, you know, when it launched the product. And so for me, having a non-technical background, having the terminal and the browser directly in the chat interface, and just having such a powerful model like 5.5 that, you know, I you could just feel the compute, you know, like it just wants to do hard work.

• 13:22Speaker 01

  It's just so powerful, you know, like I think before, I feel like over the past year, I've gone through this transition of, you know, wanting to become more technical and trying to parse, you know, what are the things that are worth learning in order for me to do the things that I want to build? You know, I think generally I love learning. I'm an ambitious learner.

• 13:41Dan Shipper?

  You are really, that's something that people should know is like, you are the the most curious learner, I think I know. Like you spend your weekends like having Claude or or Codex like building these like big learning guides that you just like read end to end about anything that you're thinking about. And I love it. I think it's amazing. And it's a superpower because AI lets you do more of it. And it like helps you use it better.

• 14:05Speaker 01

  It's a, I think it is a superpower and sometimes it feels a little bit like a vice.

• 14:09Dan Shipper?

  Yeah.

• 14:12Dan Shipper?

  Like, do I need to know the history of bookshelves from first principles? Cause I feel like that's something you would look up.

• 14:18Speaker 01

  I would like to know that. Yes. I would like to know that. But you know, with Codex, I feel like the truth is that I have to, I don't have to think so much about things like the file systems and the folder structures and you know, how the scripts are set up. And it just works. And so I think I have to focus a little bit less on, you know, architecting things well, which is very much a skill and something that our engineers do extremely well. And you know, just kind of like trusting it to make good decisions and actually build solutions for me, which is really what I want.

• 14:54Dan Shipper?

  So can you show us some of your, some of your Codex workflows?

• 14:57Speaker 01

  Yes. Okay. Let's see. Uh, we'll start with, let me share my screen here. We'll start in Codex with, I mean, we're talking about learning, so I have to show you my, my, my guiltiest pleasure, which is, uh, you know, the, my favorite skill I've ever built. It was originally a prompt, you know, maybe six months ago. And it codifies the way that I like to learn things, which is, you know, what is the history of these, this particular topic? What are the first principles that guide sort of like the physics of this topic? And then how did we get to where we are today? And sort of like, what are the variables in the marketplace around this topic? And you know, that is how I spend my weekends is like reading these guides.

• 15:41Speaker 01

  And sometimes I don't have, you know, 12 hours on a Saturday to just kind of read through these guides. And so instead, I, I make little cartoons that just summarize what I'm seeing and what I'm learning. So, uh, this started out, if you can see my screen here, this started out by actually a prompt that Natashe, uh, one of the engineers on our team built, uh, based on Clody, who I, we all know, it works on the consulting team, is the agent on the consulting team. And, uh, you know, Clody basically kind of like can teach principles, and, and kind of like anything that coming from this learning skill.

• 16:19Dan Shipper?

  So go back up to the top.

• 16:20Speaker 01

  Yeah.

• 16:20Dan Shipper?

  So tell me like, what, what were you trying to learn and how did this, this get made?

• 16:26Speaker 01

  So in this case, you know, one of the things that, well, one of the sad things maybe that has happened over the past six months is that as I've spent more and more 12-hour periods in front of my computer, I have prioritized my physical health less. And so I'm trying to learn about basically like what I need to know to improve, physical education is what I'm looking for, and what I need to know in order to make more strategic sort of like workout decisions. And so I asked Claudie to make a guide to explain, again, like, what is the history of like, physical education? Like, how did we find ourselves in a situation where we have to do specific types of like, you know, mobility and workouts? And, and like, basically, like, what do I need to know to make good decisions around how to spend my

• 17:08Speaker 01

  time, you know, on this particular topic? So Claudie, you know, here explains, you know, how, how we got to where we are, you know, basically, like, work, workouts as a topic, as an idea emerged about 200 years ago.

• 17:22Dan Shipper?

  Really?

• 17:23Speaker 01

  Yeah.

• 17:23Dan Shipper?

  That's actually earlier than I would have expected.

• 17:25Speaker 01

  Earlier?

• 17:26Dan Shipper?

  Yeah, because I figured, you know, even like 100 years ago, we were still doing a lot of physical labor.

• 17:31Speaker 01

  I think you're right. Yeah, you're right. I mean, it really became a thing during the Industrial Revolution, of course, as people were spending more time in factories. And so, you know, with my learning skill, I could read all about that. But with the, you know, this is a Codex OpenAI thing, with the visual models that Codex has, which are so powerful and just so, so good, we could just make it a cartoon. And, you know, this is something that I could scroll through on the subway, or on a walk, or having coffee. And

• 17:57Dan Shipper?

  What'd you learn?

• 17:58Speaker 01

  And so it takes these really complex concepts. I mean, one of the things that I, I learned that was really interesting was basically, you know, anatomy, which I did not learn a ton of in school, and was really helpful to learn about. And actually, one of the most interesting things that I really enjoyed from this particular zine, or kind of like set of cartoons, was learning about The time scales with which different sort of parts of your anatomy get strong. So muscles get strong faster than ligaments, get strong faster than, you know, bones, of course. And so like thinking about progression in, in, in sort of like physical strength as something that's happening across your body from, from your bones to your brain.

• 18:37Dan Shipper?

  Yeah.

• 18:38Speaker 01

  Yeah. So this is, this is one like very fun example, something that I will just kind of like do on, on the go.

• 18:46Dan Shipper?

  You already know how AI is changing how everyday work gets done, how much ground you can cover and how fast a team can scale. To stay ahead, you need tools that give you a competitive advantage built for this new era. Adio is the CRM for the agent native world. It meets you where you work, compounds every customer signal into context, and then acts on it across your pipeline to let you move at unmatched speed and scale. With agents and automations for every job, Adio orchestrates your work around the clock. We use it internally at every and we love it. It's built to handle the scale of your workloads. It's extensible with an API and MCP access and is built with infrastructure to keep up with your most ambitious agents. It's loved by high growth startups like Granola, Modal, Whisperflow, and Every.

• 19:29Dan Shipper?

  Adio runs the work behind every win. That's Adio, the agentic CRM. Go to attio.com/Every and get 15% off your first year. That's attio.com/Every. And now, back to the episode.

• 19:41Speaker 01

  Diving into codex, I, you know, I will share.

• 19:45Dan Shipper?

  First of all, how do you, how do you organize your codex?

• 19:47Speaker 01

  Okay.

• 19:47Dan Shipper?

  So you have a bunch of different projects. What are the projects? So you don't use Pinned? Or do you, you do use Pinned?

• 19:52Speaker 01

  I, I only use Pinned for my email triage, which is the app that you so generously gifted me this year. And, and, and so the email triage is the only thing that I really pin. Everything else I just kind of like work in.

• 20:06Dan Shipper?

  Okay.

• 20:06Speaker 01

  You're, you're a codex pin.

• 20:08Dan Shipper?

  I'm a big pin guy because I, I find that I lose stuff otherwise. Like I don't have a project for everything. And so it just like, it is just all the work I'm doing is just all pinned. But this is interesting. So you have a project for every sales strategy, your dad, NZQ epistemology, incredible.

• 20:30Dan Shipper?

  Tell, tell, tell me more.

• 20:32Speaker 01

  I, I, these are my learning. I don't know what to tell you. Really, suddenly really excited about, uh, you know, how Aristotle, like, you know, came up with

• 20:45Speaker 01

  sil- sillogistics systems and how we use them today. We definitely don't need to go into that.

• 20:49Dan Shipper?

  It's incredible. We actually might need to.

• 20:53Speaker 01

  I, I've been spending too much time around you. So no, I, I basically just stole, you know, store, uh, organize my codex as I organize sort of like my, my projects. So it does feel like it, you know, this, this is a thing that I think Codex does really well, that you had to do some, sort of like mental organization in Claude Code, which is, you know, in Claude Code, I spent a bunch of time really understanding file systems and I would always have the finder open to understand where things were being saved and what was really being created. In Codex, that's all happening in a really visual way. And so I feel like there's just a little bit less of a mental load that I have to take.

• 21:33Speaker 01

  But I, I just basically work in whatever project I, I'm prioritizing that day.

• 21:37Dan Shipper?

  Okay, got it. And show us email triage, because I've done a video on, on email triage, the way that I use Inbox Sweeper, now we're calling it Tend. Um, and this looks like you're, you're still using the original, but I think you've made some, some of your own custom modifications, which is another thing that I love. Like, I built an open source app that lets you turn your emails into cards and will blur anything out that you don't want people to see. But this look is different from the app that I made. So, so, um, tell me about, tell me about how you use it, how you do your email now, how it has changed things for you, and then what, what modifications you made.

• 22:09Speaker 01

  Yeah. So, uh, when in V1 of, oh, thank you. In V1 of, uh, the app that you shared with me, uh, you know, it was obviously very custom to you and it had kind of like these buttons in order to kind of like archive or send emails. There's a few things that I need to do in my inbox. I'm either delegating, uh, something. I am, you know, tracking it in Asana. Um, and, and then, you know, we work with, uh, clients that have hundreds of employees and we need to track what is going on across, you know, the different teams that we're working. To support. And so there's a lot of sort of, there's a big mental load when I'm triaging my inbox.

• 22:48Speaker 01

  And I basically created, you know, kind of like a second brain in my updated version of the inbox. Because my email can do, my email app can do a few things. So, you know, we can maybe, we'll, we'll blur out any of this that we shouldn't be here. But as an example, my, my inbox was trained on sort of like this like ghostwriter that I built, you know, I think about a year ago, was like one of the first sort of skills or prompts that I, that I built for myself. So it's trained on, you know, 150 emails that I, the most recent 150 emails that I've sent. And it understands all of the different contexts in which I need to communicate.

• 23:28Speaker 01

  And so now it is overlaid on my inbox. It, it has all of the contexts of the work that I'm doing across all of prospective clients, existing clients. It drafts a note in my voice. And there's a few things that I can do. One is I can approve to send it. So I could just click that button and it'll get sent. We'd ask to rewrite it. This was one of the great original buttons that you had in, in your app. We could just archive it if we don't want to reply to it. We could archive it. Maybe this is something that I don't need to reply to, but it, it needs to go into kind of like its own markdown file. So every client that I work with has its own markdown file. And it basically, at this point, my email knows what's going on more than I do.

• 24:09Speaker 01

  Whatever it's drafting is probably slightly more accurate than what I would have come up with. So sometimes, again, I don't need to reply. Someone else might reply, but I do want that context to go into the markdown file. If I click the task button, it'll become an Asana task as well. I can click a few of these things. It can, you know, kind of just go into spam. And, and then, you know, this is kind of like a save action here. So this is, this is the kind of thing that's just so insane. Because you can build an app for yourself on the go, right? Like I was realizing I need to triage my inbox and send stuff to different places. And I could just ask Codex to build a button that made that integration and then keep using it on the go.

• 24:51Dan Shipper?

  I remember we were sitting in the office on like a Sunday and you were like making this extremely complex flow chart. Do you have that? Can you show the flow chart? Because that was a moment where I was like, holy shit, she gets it.

• 25:05Dan Shipper?

  Bring up the flowchart, we want to see it.

• 25:08Speaker 01

  Let me, let me see if I can pull up the flowchart. So, you know, what you're seeing here at a high level is,

• 25:15Dan Shipper?

  Can we zoom in a little more?

• 25:16Speaker 01

  Yeah, sure, go for it. A high level, you know, this is sort of a, just like a, a sales pipeline management flowchart. And so this is the kind of thing that Atio just does really well, right? You kind of like import the logic and then it could help you, you know, manage your, your pipeline at scale.

• 25:34Dan Shipper?

  Oh, is this for your email or is it for Atio?

• 25:36Speaker 01

  So this is for Atio, but this is the same logic that I need to use when I am triaging my email. So actually it goes to both places. And, and so when, you know, when we get an inbound and it comes to my email, depending on, you know, whether it is a fit for the work that we do, there are different kinds of emails that need to be sent. And then obviously that advances as the conversation evolves. So this is basically the logic that enables me to do this. And it's the same logic that enables Codex to do this.

• 26:04Dan Shipper?

  And did you like, you made this and then how'd you feed it into Codex?

• 26:07Speaker 01

  Uh, I PDF'd it and shared it with Codex.

• 26:10Dan Shipper?

  So like, okay, one, one thing that's really interesting about this is what's really hot right now is loops. And everyone's saying loops, but no one knows what loops are. This is an example of a loop. And the way to think about loops is I've been using this metaphor a lot. Previously, knowledge work, whether it was code or, you know, writing or email or whatever, it was sort of, it was very similar to sculpting where, uh, when you're sculpting, every single thing that happens on the sculpture is something that you did with your hands.

• 26:43Dan Shipper?

  I think that knowledge work now is turning into something like gardening, where when you're gardening, you're creating the conditions for the growth to happen, but you're not like making the plant with your hands.

• 26:54Speaker 01

  Yeah.

• 26:55Dan Shipper?

  And that's what a loop is, is instead of doing any individual email, you are doing, you're building the system that does your emails for you. And you're intervening at different parts of the process. Like one of the things we talk about a lot is the human sin, which at the beginning and at the end to, uh, you know, to say, this is, this is maybe worth my time. And then I'm refining the draft or something like that. And you're, and you're trying to compound it. So you, you, you create a flowchart, you do your email with, with that flowchart that, that, that represents a loop. And then every time you're done, you can like compound learnings back into the system so that it gets better over time.

• 27:32Speaker 01

  Right. I I mean, I think this really is just an an evolution of the model manager analogy that you shared, you know, what, four years ago, uh, which is, you know, we are going from using these systems effectively as individual contributors, right? Where we are asking them to do like this, these one thing really well, or a small set of things really well, to create it, to creating a system, which is something that a good manager does when they have a big team that they need to help, um, operate.

• 27:59Dan Shipper?

  Couldn't be me. Could not be me.

• 28:05Dan Shipper?

  But I'm glad that you're able to do that.

• 28:11Speaker 01

  But it's the same thing, right? It's like you need to create the conditions to help people succeed. And similarly, you need to create that shared context for AI.

• 28:20Dan Shipper?

  Okay, so is there, are there more things on your email app to show us?

• 28:24Speaker 01

  Uh, I think that might be it on the email app. There's a bunch of other things that I'm doing in Codex that I can share.

• 28:29Dan Shipper?

  Yeah, show us some more, show us some more stuff, because again, like, there's just, just the email itself, I think, is life changing. Like, it's been life changing for you. You get a lot of emails. I get a lot of emails. I think we're both getting through our emails way faster than we ever have before.

• 28:43Speaker 01

  Yeah.

• 28:43Dan Shipper?

  Which is crazy. So what what else?

• 28:45Speaker 01

  Um, what else? So, uh, I can also share, you know, maybe on the personal side, I could share a little bit of my, so maybe I'll anecdotally, I can share my best loop that I've run is when we were setting up Atio, uh, I I basically had this moment where, you know, we're working with this really fantastic team who is helping us sort of like organize the logic of the the CRM. And, you know, they asked me to enrich the information based on like some context of like what had happened on the calls and what had happened in the emails. And, uh, the the my favorite loop that I've run so far on Codex is I just gave Codex a goal, which was to set up my CRM, uh, you know, uh, to accurately reflect what had happened in the conversations and in my inbox

• 29:30Speaker 01

  for each one of the hundreds of conversations, you know, with clients and prospective clients that we've had. And, you know, I I gave it a more of a robust, you know, kind of prompt and direction in order to do that. And You know, I think like six hours later, I went to sleep and six hours later it was complete. I woke up to effectively a CRM that was fully set up and had done, I think, what would have been like weeks of work that otherwise I would have had to do. That was actually only possible because of the fake jam, you know, because of this logic. It could make good decisions, make good calls with the shared context that, you know, we had, we had created. And it's just one of those like moments of joy and delight with AI where I wake up and like my, my life,

• 30:14Speaker 01

  my quality of life has improved as a result of, yeah, as a result of this loop.

• 30:18Dan Shipper?

  I guess before we move on from this, we do, you do a lot of consulting. We do a lot of consulting with executives at big companies, at tech companies, at hedge funds, at PE firms. We do a lot of training, training of those people, training of their teams, all that kind of stuff. Trying to, trying to help organizations like to get, get more AI built like this and to do work like this. So what is the takeaway for someone like that who's listening about a workflow like this? And how they should think about whether and how to start incorporating some of this into their work, workday?

• 30:54Speaker 01

  I, I think my first tip would be to start with the systems that you have already. So if you are already managing a big team and you have, you know, KPIs and shared goals and OKRs that you're tracking, the same architecture or system that you're using to guide your team, give to AI, provide to AI if that is something your company allows. And then think about what are the tasks that you want your people to focus on and to do, right? So at the end of the day, only I can get on calls and have productive conversations with our clients.

• 31:31Speaker 01

  Mike Taylor on my team did recently tell me he cloned me.

• 31:39Speaker 01

  Remember me as the original version of Natalia.

• 31:42Dan Shipper?

  How do we know that you're not already a clone? Like, I just, I don't actually know.

• 31:46Speaker 01

  We'll never know. I might be a hallucination.

• 31:51Speaker 01

  So, yeah, you know, start with that shared sort of context, that shared infrastructure. Think about what are the things that you want all your people to do? And then start with small tasks. I think the single biggest mistake that, you know, I often still ambitiously make and also see our clients make is you want to just remake the whole thing. You want to be AI-pilled, be AI-forward, just be an AI-first organization. And so often that just means you need to standardize and write down how you do a single thing really well. And if you do that and you do the next, you know, task and define what that looks like and when it's done, when it's done really well, you can end up with these more complex systems that can do sophisticated work for you. But the work at its baseline, it's, it's not particularly sexy.

• 32:36Speaker 01

  It's, you know, just you having to like read a markdown file or like a very simple set of instructions and starting there.

• 32:43Dan Shipper?

  And so, what was I gonna say? So if you're one of those people and you want to try something like this workflow, by the time this video is out, by the time this podcast is out, we will have an open source version of Tend, the email sweep app that Natalia just showed. We'll put a link in the description. You can just throw it into Codex, or honestly, you could throw this video into Codex and Codex will just watch it and then just make something that works like it, but for you. But let's keep going. I want to, I want to do some more. I know you have some, some like personal projects and other things that you wanted to share.

• 33:14Speaker 01

  Sure. I will share, you know, on, I'm personally fascinated by the role that AI will have on how we run our lives. You know, I think, you know, I don't know if this is your experience, but certainly my experience is that there's just so much that needs to get done. And so many of those things are administrative tasks that I just can't find, you know, kind of like time in the day to do. And so one of the most recent things that I asked Codex to do, and so I gave it a goal to basically create an app that triages my dad's care. My dad works with, uh, he's 81, uh, he's the best. He works with multiple nurses who support his, um, his, his care. And there's just a lot of health things that need to be triaged, right?

• 33:59Speaker 01

  Medical appointments, follow-ups from recent procedures, um, WhatsApp threads for me, uh, you know, with the nurses, with my family. And so, uh, what Codex helped me do was basically create a kind of like an operating system for how as a family we could triage my dad's care. Uh, I had this, you know, long, uh, this is a 13 hour project that Codex worked on to basically like help go from like a prototype to creating a full app that, um, could help us with my dad's care. And I'll pull up the site here. It's now a, a live app pool. All right. So what we're seeing here is, um, uh, you know, now the portal that my family shares for tracking, you know,

• 34:41Speaker 01

  what, what is going on with kind of like my dad's latest and greatest and, and his health. And so, you know, we get, uh, Google form reports from the multiple nurses that support him. Uh, and then we also have a WhatsApp thread, uh, of like, you know, many sort of like casual updates of how an appointment went or how his dosage on a certain medicine is going. And so what I have here is just, um, a top line, like here's, here's the latest. Um, I'm, I'm Colombian, so usually this is happening in Spanish. But sometimes if it's the middle of the day and I need to know what's going on, I will just toggle it and, uh, it'll just give it to me in English so that I can digest it a little bit faster. Um, uh, but really what we have is just like this one central place where instead of having to dig through, uh, you know, all of these different threads and sources of information,

• 35:26Speaker 01

  Codex has just made it really easily, easy to digest all of that information in a single place and to allow us to support my dad. And what we can do best, which is to be present and, uh, loving as his family.

• 35:36Dan Shipper?

  And your other family members are also accessing this? Are they also accessing it with Codex? Or how does that work?

• 35:41Speaker 01

  No. So this is just a, this is a, a password protected website, uh, that we, we use and share. Um, the nurses have a version of it so that they can also see what the other nurses have been working on. So there's kind of continuing care and you'll love this, uh, Dan, there is a tracker for, The different things that each one of us is responsible for and should be following up on, right, which are things that, you know, we all have, you know, personal busy lives that we need to do. And, um, you know, based on what's going on in our conversations, these things will get either highlighted as things that have not been resolved, or they will just be completed and kind of grayed out. So this has been.

• 36:17Dan Shipper?

  What do the nurses think? Are they just like, what the fuck is this?

• 36:22Dan Shipper?

  This is the most organized family I've ever run into. Like, what are they thinking? Do they like it?

• 36:29Speaker 01

  You know, it's funny, like, I think like a really good tool is not about the tool. I think the nurses just feel like we are more proactive in showing up around the topics that they need help with. Right? So, um, I, I think for them, it's just, we've just been better partners to them.

• 36:44Dan Shipper?

  I love it. It's just one of those things where this is so obviously useful and good for you and your family and for people. And I think that gets missed so often when we talk about AI is great at coding and stuff like that. It's like, actually, yeah, it is. And you can use it to do stuff like this. And people don't realize, they don't realize that they can do that and how available it is and how applicable it is to like all of the tasks and all of the stuff that we have to do, whether it's caring for family or anything else in our lives, uh, that it sort of takes, takes a little bit off your plate.

• 37:15Speaker 01

  Yeah, definitely. I mean, I, and I, I think I'm just so bullish on women using AI and all of the administrative tasks that will suddenly kind of like be taken care of because now we have this sort of like super alien tool that can support on those things. I know Claire has talked about that, Clairvo, who we love, and, um, uh, the Cut recently ran a, you know, a big piece on, you know, how moms are using agents to do something similar. So really excited about that space.

• 37:40Dan Shipper?

  So I, I know like one of the, one of the other things that's, that's happening for you is not only you're, you're building these apps, but you're building artifacts that help you, uh, we, we talked about this a little bit, art, like that help you learn stuff, for example, or just generally like navigate the world. I think people think of AI as being, oh yeah, I guess it can generate text documents, like slop text documents, but I think you're using it in a way that.

• 38:05Dan Shipper?

  Helps with rich information transfer that I think is really important. Can you show us some stuff?

• 38:10Speaker 01

  Yeah, sure. So maybe one example of that, I love Claude artifacts. They're just so cool and powerful. One example of that recently is from a trip that I took my mom on to New Orleans. So of course, the thing that I was most excited to learn about was the pump system that New Orleans uses, which is just incredible engineering and the kind of thing that I just, I don't have time to, you know, do a deep research sort of into. And so what I did going into this, it was Jazz Fest when we were going over the weekend. And so I created, you know, basically these artifacts on the go

• 38:53Speaker 01

  as I would come across things that I was interested in seeing or learning about and, you know, would basically kind of give us guides in Spanish so that we could both share in, you know, what was interesting to us as we were walking around the city. It would also, actually, it was French Quarter Fest, not Jazz Fest. The Jazz Fest was the week after. What it would do is, you know, it basically, I asked it to read through my Spotify playlists to get a sense of what kind of music I liked and then to look at the lineup that we had for French Quarter Fest.

• 39:26Dan Shipper?

  That's so cool.

• 39:27Speaker 01

  Then to basically just like select which bands it thought we were most likely to want to see. And so it was amazing. It was great. You know, it's just like, you know, the timba and the salsa, you know, bands were the ones that were highlighted. And so we could really use our time optimally so that we could kind of go and explore New Orleans. And then when we were showing up for French Quarter Fest, we could kind of go and see the bands that would most resonate with us, which just feels like a really, a really fun use of AI.

• 39:58Dan Shipper?

  Incredible. I love getting to talk to you. I always learn something when we chat. And if you want this kind of thinking inside of your organization, Natalia runs our consulting. So if you, if you want to get this out into your executive team, into your product teams and your engineering teams, reach out every.to/consulting. And Natalia, we'll have to do this again in a couple of months.

• 40:22Speaker 01

  Yeah, we will. All right. Thanks for having me, Dan.

• 40:24Dan Shipper?

  Thank you.

• 40:33Speaker 02

  Oh my gosh, folks. You absolutely, positively have to smash that like button and subscribe to AI and I. Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard. But instead of gold, it's filled with pure, unadulterated knowledge bombs about ChatGPT. Every episode is a roller coaster of emotions, insights, and laughter that will leave you on the edge of your seat, craving for more. It's not just a show. It's a journey into the future with Dan Shipper as the captain of the spaceship. So do yourself a favor. Hit like, smash subscribe, and strap in for the ride of your life. And now, without any further ado, let me just say, Dan, I'm absolutely, hopelessly in love with you.