The AI Workflows Behind Every's Consulting Team

Summary

---

Podcast Summary: “The AI Workflows Behind Every's Consulting Team”

Podcast: AI and I
Host: Dan Shipper
Guest: Natalia (Head of Consulting at Every)
Date: July 1, 2026

---

Episode Overview

In this episode, Dan Shipper interviews Natalia, Every's Head of Consulting, about how her team and clients are pioneering advanced, practical AI workflows. They explore how internal AI agents like Claudie streamline knowledge work, the evolution from makeshift solutions to integrating professional SaaS tools, and showcase live examples of how AI supercharges both business and personal productivity. Natalia screen-shares her favorite Codex workflows—from sophisticated email management to custom family care apps—offering a rare, inside look at next-generation organizational and personal AI use.

---

Key Discussion Points & Insights

1. Claudie: The Internal AI Agent Employee

• Claudie's Role Evolution

  • Initially a “Wizard of Oz” prototype, Claudie now autonomously handles consulting operations: sending proposals, managing CRM, and maintaining dashboards.

    “Claudie is an agent that does work for us every day...manages our dashboards and has a trust battery.” – Natalia [02:37]

  • Claudie self-evaluates, runs performance loops, and improves based on feedback.

• Limits of AI Agents & Human Oversight

  • AI excels at executing SOPs, but oversight, direction, and “taste” still require human management.

    “Claudie still needs constant oversight and management...reaching for excellence still requires direction and managerial support.” – Natalia [03:29]

  • Human collaboration remains essential for surfacing insights and driving conversations with clients.

2. SaaS Tools vs. AI-Coded Solutions

• Why Move Off Custom Google Sheets CRM?

  • Despite the allure of custom/AIdriven builds, maintaining high data quality, scalability, and logic complexity is better handled by purpose-built platforms (like Attio for CRM, Asana for project management).

    “There are actually private and public companies whose entire business it is to do these things really well.” – Natalia [06:04]

• The Build-or-Buy Decision

  • Building internally with AI is possible, but maintaining and scaling is a massive ongoing effort. Deciding early when to buy versus build is crucial.

    “...in the era of AI, you can build anything. The question is, should you build and maintain whatever you actually build?” – Natalia [06:33]

3. Codex: The "Life-Changing" Workflow Engine

• Adoption Experience

  • Codex’s terminal and browser in the chat UI enables non-technical users to build powerful workflows.

    “Codex has been life changing...having the terminal and the browser directly in the chat interface and just having such a powerful model...it just wants to do hard work.” – Natalia [12:52]

  • Transition from Claude code to Codex reduced friction: less focus on file structures, more focus on building solutions.

• Learning as a Superpower

  • Codex supports Natalia’s “learning quests”—custom guides and visual outputs (like cartoons) for deep dives into any topic.

    “What is the history of this particular topic? What are the first principles that guide the physics of this topic? ...That is how I spend my weekends.” – Natalia [14:56]

• Email Triage App Innovation

  • Custom email triage app, built atop Dan’s open-source tool, streamlines managing, delegating, archiving, and tracking email actions.

    “My email knows what's going on more than I do.” – Natalia [22:09]

  • The system is context-aware, trained on her sent mail, and integrates with Asana, markdown files, and client pipelines.

4. The Power of Loops in Modern Workflows

• Automating Knowledge Work through Loops
  • Work is shifting from "sculpting" (manual, every-detail) to "gardening" (setting conditions, systems, and letting AI grow/operate over time).

    “Knowledge work now is turning into something like gardening...you're creating the conditions for the growth to happen...” – Dan Shipper [27:31]

  • The email flowchart and pipeline logic encapsulate this loop-based philosophy for scaling up with AI.

5. Family-Level AI: Caring for Loved Ones

• Personal Operating Systems

  • Codex built a shared, password-protected family portal to coordinate care for Natalia’s father—going from 13-hour prototype to live app.

    “What Codex helped me do was basically create kind of like an operating system for how as a family we could triage my dad's care.” – Natalia [33:14]

  • The app consolidates reports from nurses and family chat messages, translating and surfacing actionable updates.

• De-Siloing Admin Tasks

  • The nurses and family leverage streamlined communication and task management, enabling a more present and proactive support system.

6. Creating Rich AI-Generated Artifacts

• Using AI for Enhanced Information Transfer
  • Claude artifacts enable on-the-go creation of interactive guides; e.g., recommending music at French Quarter Fest based on Spotify history and festival line-up.

    “I love Claude artifacts...for a trip I took my mom on to New Orleans, I created these artifacts on the go...” – Natalia [38:10]

---

Notable Quotes & Memorable Moments

• On Tool Choices

  “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.” – Natalia [06:33]

• Building vs. Buying:

  “You can build anything. The question is, should you build and maintain whatever you actually build?” – Natalia [06:33]

• On “Loop” Workflows:

  “Instead of doing any individual email, you're building the system that does your emails for you, and you're intervening at different parts of the process.” – Dan Shipper [26:54]

• AI Automating Executive Admin:

  “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...we have this sort of super alien tool...” – Natalia [37:15]

• Learning as a Vice & Superpower:

  “I think it is a superpower, and sometimes it feels a little bit like a vice.” – Natalia [14:05]

---

Key Timestamps

• [02:37]—How Claudie, the AI employee, now autonomously manages workflows
• [06:04]—Why Every moved from AI-coded CRM to Attio (and Asana)
• [10:22]—Differences between code (bones) and LLMs (brain/ligaments)
• [12:52]—How Codex revolutionized Natalia’s approach to building tools
• [14:56]—Live demonstration: Learning guides and cartoon visualizations
• [22:09]—Deep dive: Custom AI-powered email triage app workflow
• [25:08]—Screen-sharing the logic flowchart that underpins both CRM and email workflows
• [26:54]—Discussion on the “loop” metaphor and compounding AI workflows
• [30:54]—Advice for executives: small steps to AI-augmented team workflows
• [33:14]—Personal project: Running family elder care with a custom Codex-built app
• [38:10]—Personal artifacts: Dynamic guides and festival planning with Claude

---

Actionable Insights

• Start Small: Use AI to automate well-defined tasks; then, standardize workflows before scaling.
• Leverage AI as Force Multiplier: Pair internal AI agents with best-in-class SaaS platforms for scalable, maintainable impact.
• View AI as Continuous Improvement: Treat every automated workflow as a loop—set conditions, monitor outcomes, and refine as you learn.
• Empower Non-Technical Builders: Modern tools (Codex, Claude, etc.) lower barriers for anyone to create powerful, context-rich automations.

---

Final Reflection

This episode offers a compelling, hands-on exploration of how cutting-edge teams are integrating AI agents and tools—not only to supercharge business operations but also to enrich personal and family life. Natalia’s curiosity and systems mindset exemplify how AI, when thoughtfully applied, can fundamentally reshape both work and wellbeing.

---

Transcript

[Dan 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.

[Natalia]

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.

[Dan 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. 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.

[Natalia]

Thanks, Dan. Good to be back.

[Dan Shipper]

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

[Natalia]

That's right.

[Dan Shipper]

You are also the manager of Claudie Consulting's AI agent employee, who was the star of our last episode together. And I wanted to bring you on because I feel like every couple months, things shift so radically. And for me, you're one of the 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 really great operators and executives are starting to use this stuff. So the last time we chatted, Claudie, which is the internal AI employee agent that we built to basically help to run the consulting business, to send out sales proposals and manage the CRM and all that kind of stuff. Claudio is like this nascent thing. That Nitesh, who's our senior AI engineer, was sort of. What's the word for it? He was sort of like wizard of Oz ing it in the background, making it work minute by minute. But I feel like now Claudia is actually working like, the model releases over the last couple months have dramatically changed how much it's able to do. So give us an update on Claudie. How are things going there?

[Natalia]

It's funny. With the speed of AI Claudie, it feels like Claudie is just not novel. Claudie is an agent that does work for us every day. And Claudie has its own LinkedIn and Twitter feed and manages our dashboards and has a trust battery. Now that's new. So 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.

[Dan Shipper]

I guess one of the things that's interesting is 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. For stuff that you might want to hire a human for?

[Natalia]

Yeah, it's really interesting. I think as we've all been using AI more, I think 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. 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. So the sort of question of 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 Claudia, I want to interface with people, right? And I find that I can't really

[Dan Shipper]

relate, but I. I see, I see why someone might feel that way.

[Natalia]

And the reality is that you. We do have all of these rich dashboards and all of this data that Claudia is populating. 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 Claudie surfaces so that we can actually do interesting things with it.

[Dan 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 cloudy, glued together with Google sheets. And I think there's this whole narrative running around. I think, honestly, SaaS docs 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. Are you just going to vibe code all SaaS? Fable currently is banned, but I'm sure it will be back. Maybe it's even back by the time this episode comes out. But if Fable can just one shot a cms, why would you use one? But 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 homemade one onto a professional one. So why would you do that?

[Natalia]

Yeah, despite my hopes and aspirations that I could do all of the things and become an engineer and maintain all of these engineering products that I've.

[Dan Shipper]

This one I can relate to this one.

[Natalia]

It turns out there are actually private and public companies whose entire business it is to do these things really well and sometimes these very specific things really well. So I Vibe coded a CRM tool that allowed us to manage our sort of sales pipeline.

[Dan Shipper]

For a while it was managing in Google Sheets. So it was like Claude Claudia was the. Was the glue between what was going on in Slack and the meetings and Google Sheets.

[Natalia]

Yeah, exactly. So basically Claudia had access to, was able to read my email, was able to read our meeting note takers notes, was able to digest kind of like an inbound leads that came and then would track this all in a Google sheet. And then 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, almost like Claudia, 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 actually build? And I think 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 Claudie. 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.

[Dan Shipper]

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

[Natalia]

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 a tool like Attio, it has access to all of the things that Claudia had access to, but it has really robust logic so that it can basically 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 Claudie to do and was not. Claudie was just not inherently set up for it. It could do that if I spent more time training it to do that. But it's ultimately sort of like a reward payoff thing.

[Dan 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 compiles thousands and thousands of little logical rules that you wouldn't expect you would need beforehand. And the whole job of the company and the engineers is to gather all the rules that are needed and then put it into the system. And when something breaks, change the rules. And AI is very good at 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.

[Natalia]

Yeah. Needless to say, I've become a really big fan of PRDs and actually scoping what I'm building, which 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.

[Dan Shipper]

Yeah, I think a good metaphor is. And sorry, I'm just like, my brain is just cycling on the differences 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. So 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 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 a good way for software and language model. 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. But you said something earlier that I think is really interesting and I want to push on, which is I see you going from not technical to like building stuff, 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.

[Natalia]

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

[Dan Shipper]

I'm very annoying about things I think are good

[Natalia]

and, 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 a, you know, like, okay, like now I have to figure out this whole other thing and like, I love cloud code and you know, I'm very comfortable in 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.

[Dan Shipper]

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

[Natalia]

It really feels like codecs. I think you've said this before, codecs looked at the things that weren't quite working with Claude code and then it just fixed it 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 could just feel the compute, it just wants to do hard work. It's just so powerful. I Think before. I feel like over the past year, I've gone through this transition of wanting to become more technical and trying to parse what are the things that are worth learning in order for me to do the things that I want to build. I think generally, I love learning. I'm an ambitious learner.

[Dan Shipper]

You are. Really? That's something that people should know, is, like, you are the most curious learner, I think. I know you spend your weekends having Claude or Codex build you these big learning guides that you just 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 helps you use it better.

[Natalia]

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

[Dan Shipper]

Yeah. Do I need to know the history of bookshelves from first principles or something? Because I feel like that's something you would look up.

[Natalia]

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

[Dan Shipper]

So can you show us some of your Codex workflows?

[Natalia]

Yes. Okay, let's see. 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 guiltiest pleasure, which is my favorite skill I've ever built. It was originally a prompt maybe six months ago, and it codifies the way that I like to learn things, which is, what is the history of this particular topic? What are the first principles that guide the physics of this topic? And then how did we get to where we are today? And 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. 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 this started out, if you can see my screen here, this started out by actually a prompt that nitesh one of the engineers on our team built based on Claudie, who we all know works on the consulting team as the agent on the consulting team. And Claudie basically kind of can teach principles and kind of like anything coming from this learning skill.

[Dan Shipper]

So go back up to the top. So tell me, what were you trying to learn and how did this get made?

[Natalia]

So in this case, 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, 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. Of mobility and workouts? And basically, what do I need to know to make good decisions around how to spend my time on this particular topic? So Claudia here explains how we got to where we are. Basically, workouts as a topic, as an idea, emerged about 200 years ago.

[Dan Shipper]

Really? Yeah, that's actually earlier than I would have expected.

[Natalia]

Earlier.

[Dan Shipper]

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

[Natalia]

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.

[Dan Shipper]

What'd you learn?

[Natalia]

And so it takes these really complex concepts. I mean, one of the things that I learned that was interesting was basically 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 timescales with which different sort of parts of your anatomy get strong. So muscles get strong faster than ligaments get strong faster than bones, of course. And so 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.

[Dan Shipper]

Yeah, there you go.

[Natalia]

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

[Dan 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. ADEO 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. Addio 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, whisper flow and every. Addio runs the work behind every win. That's Adeo, the Agentix CRM. Go to adeo.com every and get 15% off your first year. That's adeo.com every and now back to the episode.

[Natalia]

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

[Dan Shipper]

First of all how do you, how do you organize your codex? Okay, so you have a bunch of different projects. What are the products? So you don't use pinned or do you do use pinned?

[Natalia]

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

[Dan Shipper]

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 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. Tell me more.

[Natalia]

These are my learning quests. I don't know what to tell you. Really suddenly, really excited about how Aristotle came up with syllogistic systems and how we use them today. We definitely don't need to go into that.

[Dan Shipper]

It's incredible. We actually might need to.

[Natalia]

I've spending too much time around you.

[Dan Shipper]

So.

[Natalia]

No, I basically just store organize my codex as I organize my projects. So it does feel like this is a thing that I think Codex does really well, that you had to do some mental organization in Claude code, which is in Claude 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'm prioritizing that day.

[Dan Shipper]

Okay, got it. And show us email triage. Because I've done a video on email triage the way that I use Inbox Sweep, or now we're calling it, tend to. And this looks like you're still using the original, but I think you've made some of your own custom modifications, which is another thing that I love. 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. Tell me about how you use it, how you do your email now, how it has changed things for you and then what modifications you made.

[Natalia]

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 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 are 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. I basically created 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 we can maybe we'll blur out any of this that shouldn't be here. But as an example, my inbox was trained on sort of like this ghostwriter that I built I think about a year ago was one of the first sort of skills or prompts that I built for myself. So it's trained on 150 emails that I. The most recent 150 emails that I've sent and it understands all the different contexts in which I need to communicate. And so now it is overlaid on my inbox. It has all of the context 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 your app. We can 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 needs to go into kind of like its own markdown file. So every client that I work with has its own markdown file. And basically, at this point, my email knows what's going on more than I do. So whatever it's drafting, it's 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 kind of just go into spam, and then there's basically kind of like a save action here. So 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.

[Dan Shipper]

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

[Natalia]

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

[Dan Shipper]

Can we zoom in a little more?

[Natalia]

Yeah, sure, go for it. High level. This is sort of just like a sales pipeline management flowchart. This is the kind of thing that Apptio just does really well, right? You kind of, like, import the logic, and then it can help you manage your pipeline at scale.

[Dan Shipper]

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

[Natalia]

So this is for Atio. But this is the same logic that I need to use when I am triaging my email. Actually, it goes to both places. When we get an inbound and it comes to my email. Depending on 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. This is basically the logic that enables me to do this, and it's the same logic that enables Codex to use.

[Dan Shipper]

You made this and then how did you feed it into. Into Codex?

[Natalia]

I PDF'd it and shared it with Codex.

[Dan Shipper]

So, like, okay, 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 writing or email or whatever, it was sort of. It was very similar to sculpting, where when you're sculpting, every single thing that happens on the sculpture is something that you did with your hands. 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.

[Natalia]

Yeah.

[Dan Shipper]

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

[Natalia]

Right?

[Dan Shipper]

Yeah.

[Natalia]

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

[Dan Shipper]

Couldn't be me. Could not be me. But I'm glad that you're able to do that.

[Natalia]

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.

[Dan Shipper]

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

[Natalia]

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

[Dan Shipper]

share some more, show 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.

[Natalia]

Yeah.

[Dan Shipper]

Which is crazy. So what, what else?

[Natalia]

What else? So I can also share, you know, maybe on the personal side, I could share a little bit of my. So maybe I'll anecdot share. My best loop that I've run is when we were setting up Attio. I basically had this moment where we're working with this really fantastic team who is helping us sort of, like, organize the logic of the CRM. And they asked me to enrich the information based on some context of what had happened on the calls and what had happened in the emails. And 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 to accurately reflect what had happened in my conversations and in my inbox for each one of the hundreds of conversations with clients and prospective clients that we've had. And I gave it more of a robust kind of prompt and direction in order to do that. And I think 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 created. And it's just one of those, like, moments of joy and delight with AI where I wake up and, like, my life, my quality of life has improved as a result of. Yeah, as a result of this loop.

[Dan Shipper]

I guess before we move on from this, 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 of those people, training of their teams, all that kind of stuff, trying to help organizations get more AI pilled 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 workday.

[Natalia]

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 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, 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 for my clients. Mike Taylor on my team did recently tell me he cloned me. So. Remember me as the original version of the talk.

[Dan Shipper]

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

[Natalia]

We'll never know. I might be a hallucination. So, yeah, you know, start with that shared sort of context, that shared infrastructure. Think about what are the things that you want only your people to do and then start with small tasks. I think the single biggest mistake that, you know, I, 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 task and define what that looks like, and 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 not particularly sexy. It's just you having to read a markdown file or a very simple set of instructions and starting there.

[Dan Shipper]

And so what was I going to 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.

[Natalia]

Sure, I will share. You know, on. I'm personally fascinated by the role that I 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, he's 81, he's the best. He works with multiple nurses who support his care. And there's just a lot of health things that need to be triaged, right? Medical appointments, follow ups from recent procedures, WhatsApp threads for me, you know, with the nurses, with my family. And so 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 could help us with my dad's care. And I'll pull up the site here. It's now a live Apple. All right, so what we're seeing here is, you know, now the portal that my family shares for tracking, you know, what is going on with kind of like my dad's latest and greatest in his health. And so, you know, we get Google form reports from the multiple nurses that support him. And then we also have a WhatsApp thread 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 a top line, like, here's the latest. 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 it'll just give it to me in English so that I can digest the it a little bit faster. But really what we have is just like this one central place where instead of having to dig through all of these different threads and sources of information, Codex has just made it really 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 loving as his family.

[Dan Shipper]

And your other family members are also accessing this. Are they also accessing it with Codex or How does that work?

[Natalia]

No, so this is just a password protected website that we use. We use and share. 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, 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, 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.

[Dan Shipper]

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?

[Natalia]

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 I think for them it's just, we've just been better partners to love it.

[Dan Shipper]

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. And 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 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, that it sort of takes a little bit off your plate.

[Natalia]

Yeah, definitely. I mean, 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. Claire Vo, who we love and the Cut recently ran a big piece on how moms are using agents to do something similar. So really excited about that space.

[Dan Shipper]

So I know one of the other things that's happening for you is not only you're building these apps, but you're building artifacts that help you. We talked about this a little bit. That help you learn stuff, for example, or just generally 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. Can you show us some stuff?

[Natalia]

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. Just incredible engineering and. 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. It was Jazz Fest when we were going over the weekend. And so I created, you know, basically these artifacts on the go 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 Festival.

[Dan Shipper]

That's so cool.

[Natalia]

And then to basically just like, select which bands it thought we were most likely to want to see. And so it was amazing.

[Dan Shipper]

It was great.

[Natalia]

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 quarterfest, we could kind of go and see the bands that would most resonate with us, which just feels like a really fun use of AI.

[Dan 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 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 months.

[Natalia]

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

[Dan Shipper]

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 rollercoaster 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

[Natalia]

in love with you.