The AI Workflows Behind Every's Consulting Team

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. 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. 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. 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 slash subscribe today. Natalia, welcome to the show. Thanks, Dan. Good to be back. So for people who missed your last episode, you are our head of consulting at Every. That's right. You are also the manager of Claudi, consulting's AI agent employee, which 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. So the last time we chatted, Claudi, which is the internal AI employee agent that we built to basically help to run the consulting business, to, you know, send out sales proposals and manage the CRM and all that kind of stuff. Claudi was like this nascent thing that Natesh, who's our senior AI engineer, was like, sort of, what's the word for it? He was sort of like wizard of Ozing it in the background, like making it work minute by minute. But I feel like now Claudi 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 Claudi. How are things going there? You know, it's, it's funny with the speed of AI. Claudi, it feels like Claudi is like just not novel. You know, it's Claudi is an agent that does work for us every day. And Claudi has its own LinkedIn and Twitter feed and, you know, manages our dashboards and, you know, has a trust battery now. That's new. 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 Claudi is thriving, I guess. One of the things that's interesting is you, you hired Claudi 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? Yeah, you know, it's really interesting. I think, you know, as, as we've all 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 Claudi is exceptional at that. But Claudi still needs two things. One is it needs constant oversight and management to make sure that it's doing those things really well, actually. So, you know, the sort of question of like taste and, you know, reaching for excellence still requires direction and sort of managerial support, which, you know, can be quite tedious and time consuming. So there's still quite a bit of time involved there. And, and two is 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... I can't really relate, but I, I see, I see why someone might feel that way. 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. 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? 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. Or you decided to move off the sort of homemade one onto a professional one. So why would you do that? Yeah. So despite my hopes and aspirations that I could do all of the things and, you know, become an engineer and maintain all of these engineering products that I've vibe coded. This one I can't relate to this one. 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, you know, we, you know, I, I vibe coded a CRM tool that allowed us to manage our sort of like sales pipeline for a while. And it was managing in Google sheets. So it was like Claude, Claudi was the, was the glue between what was going on in Slack and the meetings and Google sheets. Yeah, exactly. So basically Claudi had access to, was able to read my email, was able to read our meeting note taker's notes, was able to digest kind of like an inbound leads that came and then track this all in a Google sheet. And then, you know, eventually that became 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 Claudi, you need to be on top of the quality of the data. And so it turns out this is Atio's entire business. And so, you know, I think one of the challenges with AI 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. The question is, should you build and maintain whatever you, you actually built? And I think in this, in this case, and probably in other use cases, we also rolled out Asana for our project management system. I think we're able to do the scale of the work that we are able to do because of Atio, because of Asana and because of Claudi managing all of that information is much greater than if we didn't have those tools. But now we just have less burden on the team to maintain that. Can you give me like a, like a concrete example? Because 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 Claudi 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? Yeah. So, you know, so yeah, totally. Like if you 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 after a certain amount of volume, I just can't quite track with, with a tool like, like, you know, Atio it is, it has access to all of the things that Claudi had access to, but it has really robust logic so that it can basically, you know, track 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 Claudi to do. And, and was not Claudi 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. But it's, it's ultimately like, you know, sort of like a, a reward payoff thing. 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 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, what were you trying to learn, and how did this get made? 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 Claudi 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 like, basically, like, what do I need to know to make good decisions around how to spend my time, you know, on this particular topic? So Claudi, you know, here explains, you know, how we got to where we are, you know, basically, like, workouts as a topic, as an idea, emerged about 200 years ago. Really? Yeah. That's actually earlier than I would have expected. Earlier. Yeah, because I figured, you know, even like 100 years ago, we were still doing a lot of physical labor. 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 and like, basically, like, what do I need to know to make good decisions around how to spend my time, you know, on this particular topic? So Claudi, you know, here explains, you know, how how we got to where we are, you know, basically, like, workouts as a topic, as an idea, emerged about 200 years ago. Really? Yeah. That's actually earlier than I would have expected. Earlier. Yeah, because I figured, you know, even like 100 years ago, we were still doing a lot of physical labor. 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 and like, basically, like, what do I need to know to make good decisions around how to spend my time, you know, on this particular topic? So Claudi, you know, here explains, you know, how how we got to where we are, you know, basically, like, workouts as a topic, as an idea emerged about 200 years ago. Really? Yeah. That's actually earlier than I would have expected. Earlier. Yeah. Because I figured, you know, even like 100 years ago, we were still doing a lot of physical labor. 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 it takes these really complex concepts. I mean, one of the things that 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 sort of like physical strength as something that's happening across your body from your bones to your brain, as you said. So this is this is one like very fun example, something that I will just kind of like do on on the go. You already know how AI is changing how every day 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. Adio runs the work behind every win. That's Adio, the agentic CRM. Go to adio.com slash Every and get 15% off your first year. That's adio.com slash Every. And now back to the episode. Diving into codex, I, you know, I will share. First of all, how do you how do you organize your codex? OK, so you have a bunch of different projects. What are the projects? So you don't use pinned or do you do you use pinned? 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. OK, you're you're a codex pin. I'm a big pin guy because I find that I lose stuff otherwise. Like I don't have a project for everything. And so it's 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 epistomology. Incredible. Tell me more. I, I, these are my learning classes. I don't know what to tell you. Really suddenly really excited about, you know, how Aristotle, like, you know, came up with the the logistics systems and how we use them today. We definitely don't need to go into that. It's incredible. We actually might need to. I've been spending too much time around you. So no, I, I basically just store, you know, store 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 cloud code, which is, you know, in cloud code, I spent a bunch of time really understanding file systems and 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. But I just basically work in whatever project I I'm prioritizing that day. Okay, got it. And show us email triage because I've done a video on, on email triage, the way that I use inbox sweep or now we're calling it tend. And this looks like yours. 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 looks different from the app that I made. So, so 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've made. Yeah. So when in V1 of, oh, thank you. In V1 of the app that you shared with me, 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 something. I am tracking it in Asana. And, and then, you know, we work with 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. 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 Uh, and, uh, 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. Um, 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. Um, but let's keep going. I wanna, I wanna do some more. Um, I know you have some, some like, personal projects and other things that you wanted to share. Sure. Uh, I will share, you know, on, I am personally fascinated by the role that AI will have on how, uh, we run our lives. You know, I, 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, uh, 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? 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. I had this, you know, long, 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 live app. All right. So what we're seeing here is, um, uh, you know, now the portal that my family shares for tracking, you know, what, what is going on with kind of like my dad's latest and greatest in 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, uh, 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, 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. And your other family members are also accessing this? Are they also accessing it with Codex, or how does that work? No. So this is just a, this is 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 continuity in care. And you'll love this. Uh, Dan, there is a tracker for uh 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 amazing. What do the nurses think? Are they just like, what the fuck is this? This is the most organized family I've ever run into. Like, what are they thinking? Do they like it? You know, it's funny, you know, 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. 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 a family member or anything else in our lives, uh, that it sort of takes, takes a little bit off your plate. Yeah, definitely. I mean, I, and 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. Clairevo, who we love and um 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. 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, like we talked about this a little bit, 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 helps with rich information transfer that I think is really important. Um, can you show us some stuff? Yeah, sure. So, uh, maybe one example that I love, Claude artifacts. They're just so cool and powerful. One example of that recently, uh, is from a trip that I took my mom on uh to New Orleans. Uh, so of course, the thing that I was most excited to uh learn about was the uh pump system that New Orleans uses, uh, which is just incredible engineering and um 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, um, it was at, it was Jazz Fest, uh, when we were going over the weekend. And so I created, you know, basically these artifacts on the go as I would come across um things that I was interested in seeing or learning about. And, you know, it would basically kind of give us uh 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, um, uh, actually it was French Quarter Fest, not Jazz Fest. The French jazz fest was the week after. Uh, what it would do is, you know, it basically, I asked it to um read through my Spotify playlists to get a sense of what kind of music I liked and then to look at the lineup uh that we had for French Quarter Fest. Oh my God, that's so cool. And then to basically just like select which uh bands it thought we were most likely to uh want to see. And so it, it was amazing. It was great. You know, it's just like, you know, the Timba and the salsa, you know, uh 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. Um, 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, uh, which just feels like a really, a really fun use of, of AI. Incredible. Uh, I love getting to talk to you. I always learn something, uh, when we chat. And uh if you want this kind of thinking inside of your organization, uh, Natalia runs our consulting. So if you, if you want to get this out into your executive team, into your product teams, into your engineering teams, reach out every dot co slash consulting. And Natalia, we'll have to do this again in a couple months. Yeah, we will. All right. Thanks for having me, Dan. Thank you. 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