Dan Shipper interviews Natalia Quintero, head of AI consulting at Every, about building Claudie, an AI project manager she vibe coded with Claude that saves her around 14 hours a week handling client onboarding and generating weekly updates across all projects. Drawing on conversations with 100+ organizations—including hedge funds, private equity firms, and Fortune 500 companies—Quintero shares what separates companies thriving with AI from those floundering: why AI adoption must come from the top down, why giving employees permission to fail matters, the benefits of connecting AI to proprietary context, and a plan-delegate-assess-compound framework for engineering teams. She also covers how a private equity firm cut investment memo creation from three weeks to 30 minutes, how non-technical team members are becoming vibe coders, and why creative exploration time outside the 9-to-5 is essential. Includes a live demo of how Claudie automates client onboarding and tracking. Timestamps: 00:00:00 - Introduction 00:01:30 - Why successful AI adoption requires coordinated, top-down effort 00:07:05 - How a private equity firm reduced investment memo creation from weeks to 30 minutes 00:13:30 - The benefits of connecting AI to proprietary context 00:15:20 - The plan-delegate-assess-compound framework for engineering teams 00:17:55 - How non-technical team members are becoming vibe coding addicts 00:20:50 - Building Claudie: an AI project manager from scratch 00:23:00 - Why creative exploration time outside the 9-to-5 is essential 00:27:50 - Live demo: How Claudie automates client onboarding and tracking 00:38:40 - The human side of AI: spending less time in spreadsheets, more time with people Resources mentioned: What Natalia learned from working with companies on AI adoption: https://every.to/on-every/the-next-chapter-of-every-consulting Every's compound engineering plugin: https://github.com/EveryInc/compound-engineering-plugin # Channel Identity Observations: "How We Built 'Claudie,' Our AI Project Manager (Full Walkthrough)" ## Explicit Self-Description Evidence - **Show/creator identity**: Host Dan Shipper addresses the audience directly in the outro: *"smash that like button and subscribe to AI and I... a journey into the future with Dan Shipper as the captain of the spaceship."* This names the channel/show as **"AI and I"**. - **Format claim**: Self-described as a **podcast** — Dan says, *"You've never been on the podcast... I'm just really excited to get you on the podcast."* - **Company affiliation**: The channel is presented as produced by/for **Every**: *"we've also done a lot of work... with hedge funds and also with tech companies"* and references to "the every team," "Every Consulting GitHub page," and "Think Week... where we were all in Panama together." - **Topic scope claim**: The outro frames the show as delivering *"pure, unadulterated knowledge bombs about chat GPT"* and covering AI more broadly (agent workflows, Claude Code, AI adoption). ## Demonstrated Presentation (Observable Patterns) - **Content format**: Interview/conversation between host and guest (Natalia, introduced as *"head of consulting at every"*), with a **live screen-share demo** portion ("Can you see my screen?... this is where Claudia lives"). - **Tutorial element**: The guest explicitly frames part of the content as a reusable template: *"if you're watching this and you need a project manager, this is going to be a pretty good sort of template or model for how you can think about setting up a project manager."* - **Monetization/sponsorship evidence**: A mid-roll ad read for **Framer** ("framer.com/dan for 30% off"), indicating sponsor support. - **Audience call-to-action**: Like/subscribe solicitation with an affiliate-style enthusiastic tone, including *"Dan, I'm absolutely hopelessly in love with you."* ## Intended Audience (Observable) - **Business and AI-adoption leaders**: Content addresses executives rolling out AI ("your job as an executive who's leading your org is to identify those people"). - **Finance and tech professionals**: Explicit outreach at the end — *"if you're a financial institution and need help thinking through your AI strategy but more importantly implementing it, reach out to us and also if you're a tech company."* - **Hands-on AI builders**: Practical guidance on Claude Code, CLAUDE.md files, MCPs, tasks, and sub-agents suggests an audience experimenting with agentic tools. ## Claimed Scope / Authority - **Consulting credibility claims**: Natalia states, *"I personally have spoken to over a hundred companies in the past year"* and describes work with *"hedge funds, PE firms, Fortune 500 companies, lots of name brands."* - **Named client/brand references**: Shopify's CEO Tobi Lütke cited as an example; demo references client "Headway" and team members from Perplexity and Kora. - **Funnel evidence**: The episode ends with contact info — *"They could find us on the every site. So we are at every.2cculting"* — indicating the video also functions as lead generation for Every's consulting practice. ## Claims vs. Demonstrated Distinction - **Claimed**: Show value ("epitome of awesomeness," AI knowledge source), consulting reach (100+ companies). - **Demonstrated**: Actual walkthrough of a working agent system (architecture, CLAUDE.md file, dashboard output, live client-onboarding run in Warp with Claude Code), internal team practices (6 a.m. vibe-coding sessions, "promote yourself day"), and concrete metrics stated by the guest (*"at least 10 to 15 hours on just project management... now with Claudia I am collecting information for an hour a week"*). # Delivery Observation: "How We Built 'Claudie,' Our AI Project Manager (Full Walkthrough)" ## Format Overview - **Two-person conversational interview** between a host (Dan) and a guest (Natalia), with a mid-episode **sponsor read** (Framer, ~[1393–1469]) and a closing **exaggerated YouTube outro** (~[2791–2826]). - Structure: welcome/context → consulting-patterns discussion → client case stories → guest's personal "vibe coding" story → **live product walkthrough** of the "Claudia" agent system → wrap-up with contact info. ## Host Delivery Patterns - **Enthusiastic interjection and "pause the tape" reactions.** During the walkthrough he repeatedly stops to express astonishment: > "I just want to pause and be like that is that's crazy. That's kind of crazy." > "Absolutely incredible. And how long would this normally take you?" - **Restating and generalizing the guest's points into "patterns."** He converts anecdotes into reusable lessons: > "I think that's another really good pattern is you have Nateesh who's an applied AI engineer who can literally sit with you..." > "I think that's like a interesting lesson that we definitely just know ourselves internally" - **Frequent intensifiers and superlatives:** "really," "so," "actually," "incredible," e.g., "This is so cool. There's so much in here." This is a consistent habit across the transcript. - **Conversational hedges and self-corrections mid-sentence:** "um I I don't see nearly as much as you but I do see a lot um on the top down front." - **Humor and banter:** ">> living dangerously. Dangerously skipped permissions. Love it." and "So what do you do with all your time, Natalia?" - **Guiding questions that steer toward specifics:** "Do you have any specific stories? ... want to get down into the nitty-gritty of here are some like actual concrete stuff." ## Guest Delivery Patterns - **Filler-heavy, run-on phrasing** with heavy use of "um," "uh," "you know," and "kind of like" — e.g., "Uh and uh that one comes to mind because our partner kind of like our day-to-day liaison at that firm..." - **Enumerated structure within answers.** She repeatedly frames responses as numbered lists: "there's really two things that we see working well"; "There's there's two things that come to mind"; "There's two kind of truths to that that are maybe non-obvious." - **Frameworks and quotable formulations**, e.g., the four-step engineering process: "you plan you delegate you assess and then you compound"; and "you can only really compound as much as you plan." - **Concrete before/after metrics** as evidence: "previously took two to three weeks and they can now get like a really high quality draft in literally 30 minutes"; "I spend at least 10 to 15 hours on just project management. Um now with Claudia I am collecting information for an hour a week." - **Vivid analogies:** "this is like Savile Row sort of prompt tailoring" (note: transcript rendering of this line is garbled with repeated characters, so the exact wording is uncertain); the horse-and-buggy/car analogy comes from the host. - **Self-deprecating repetition of a signature phrase:** "I am a bonafide vibe code addict at this point" appears twice ([33]/[1181]) — once in a cold-open clip and again in the main interview. ## Recurring Teaching Habits (Both Speakers) - **Analogy to human employees/hiring** for explaining agents. Guest: "if you had hired a project manager, you would not expect them to not have a job anymore" (host); guest: "it knows who we work with... every time... you always know where you work, what your job is." Both use this framing repeatedly. - **"Job description" metaphor** for the Claude MD file, stated multiple times during the walkthrough. - **Emphasis on iteration and failure as method:** "we had to throw our project manager agent away three times before we found this scaffolding that really works." ## Walkthrough-Specific Delivery - The demo segment shifts to **second-person instructional address**: "if you're watching this and you need a project manager, this is going to be a pretty good sort of template or model." - Guest manages expectations during the live demo: "we think that things are going to be instantaneous, but uh I think this is just kind of like a myth... it just takes time." ## Uncertain / Isolated Observations - The **closing outro** ("I'm absolutely hopelessly in love with you") appears to be a scripted joke segment, not representative of the interview tone — an isolated moment. - Speaker attribution for a few lines (e.g., the "promote yourself day" discussion around [2387–2429]) is ambiguous in the transcript; the pattern claims above avoid relying on those lines. - The garbled "prompt ta t t t t..." segment suggests a transcription error; the exact "Savile Row" wording cannot be verified. # Position Extraction: "How We Built 'Claudie,' Our AI Project Manager (Full Walkthrough)" ## Speakers - **Dan Shipper** — podcast host (identified by transcript: "Dan, I'm absolutely hopelessly in love with you") - **Natalia** — head of consulting at Every (per Dan's introduction) --- ## Core Positions on Enterprise AI Adoption ### Natalia: Coordinated, top-down effort is required - For AI to be a **high-leverage tool**, adoption "needs to come from the top down" — contrasted with historical software (e.g., SaaS) purchases a CTO could make and hope for usage. - Without coordination, AI "doesn't go anywhere": a few high-powered users gain leverage while "everyone else is sort of floundering." - Basis: she has **personally spoken to over 100 companies** in the past year, hearing concerns and benchmarking competitor usage. - **Two working patterns** she identifies: 1. Leadership understands AI as a high-lever tool fundamentally changing work. 2. Empowering **AI champions** to experiment, fail, train peers, then double down on what works. ### Dan: CEO adoption ceiling - "You'll probably go as far as your CEO has gone" — **AI adoption is not delegable** by a CEO. - Public example cited: **Toby from Shopify** "hacking on stuff on the weekends"; Dan predicts Shopify's culture will differ significantly in a year because of this. (Dan qualifies: "you don't necessarily have to be that far.") - **Bottom-up complement**: executives should identify natural early adopters and elevate their status to pave the path for others who won't try new technology unprompted but will use it if shown its value. ### Dan on resistance to automation - Change-management resistance stems from not wanting to give up tasks "until I have a vision of what comes next." - Every's internal response: a "**promote yourself day**" — framing agents as promotion (managing the project manager rather than doing IC work), analogous to hiring a human project manager. --- ## Case Studies and Claims ### Private equity firm (unnamed; liaison "Jonathan") - Jonathan mapped **every task** investors perform (research, diligence, market mapping, portfolio management), then highlighted high-leverage AI opportunities, producing a detailed task map by team. - Claimed result: investment memos that took **2–3 weeks** now get a "really high quality draft in literally 30 minutes." - Method: connecting a decade of SharePoint-stored investment thesis material ("the IP of the firm"), funneled through prompts trained on how the firm thinks about its strategy, via GPTs and prompts. - Natalia: this only worked because of insider specificity — "Savile Row sort of prompt tailoring"; the prompts act as "an analyst that does really high quality work that is dependable." - **Qualification preserved**: this is a draft, not a finished memo. ### Tech company engineering org - Four-step framework: **plan, delegate, assess, compound**. - Diagnosis: engineers were effective at delegating, assessing, and compounding but had **no planning phase**, so they solved small issues but not big problems. - Claimed result: with the framework in place, engineers "frequently" generate **two weeks of work in an afternoon**; Natalia adds "I wouldn't be surprised if that continues to speed up" (explicitly hedged: "that's a difficult question to answer"). ### Dan on data-source connection and domain knowledge - Connecting AI to data sources is "table stakes." - The greater value in an **agent-native world**: encoding how the organization defines things (e.g., Austin's specific definition of MRR across Stripe/ChartMogul/PostHog) so the agent doesn't re-derive it each time — "a lot of what makes your use of AI different from someone else's." --- ## The "Claudia" Project Manager Agent ### Origin story (Natalia) - Realized she was falling into the client trap she warns about: no time to experiment. With **Nateesh Agarwal** (applied AI engineer, ex-Kora), they started meeting at **6 a.m. to vibe code 6–9** before the workday. - Goal: "hire an agent to be our project manager." - **Iteration preserved as stated**: got "85% of the way there three times" and had to scrap and restart before reaching a working framework. - Two failed iterations diagnosed: one **too engineering-focused** (framework/data strategy), one **too work-focused** ("just a job description"). Success required mixing domain know-how with Claude Code infrastructure (tasks, agents, sub-agents). ### Architecture (Natalia's walkthrough) - **CLAUDE.md file**: a concise "job description" — identity, data sources, dashboard conventions, ID conventions modeled on database management principles, and operating principles ("data accuracy is key," "be proactive not reactive," "formulas over manual entry," "when in doubt, escalate"). - Qualification: "Claude is really, really smart" (runs on **Opus 4.5**) and doesn't need project management defined — only "boundaries, conventions, and sharp edges." - **Commands** for quality checks, weekly updates, client onboarding. - **MCPs** connecting Gmail, calendar, Google Drive, meeting transcripts. - Onboarding a client: Claudia launches four sub-agents to gather foundational context before populating dashboards; last onboarding run took ~30 minutes. Natalia notes the "myth" that AI is instantaneous — useful AI "takes time" and needs quality checks. ### Quantified claim - Natalia: previously **10–15 hours/week** on project management; now **~1 hour/week** collecting information. ### Ongoing-management qualification - Natalia stresses it is **not set-and-forget**: when Claudia errs, she must feed back context (into commands or the CLAUDE.md file), analogous to onboarding a human staff member. - Personal framing: hours freed go to client relationships — "any hour that I am not spending tabulating information, I am spending with the people that I get to work with." --- ## Dan's Supporting Patterns - **Protected play time**: Natalia carving out hours outside the 9-to-5 parallels Every's "Think Week" retreat in Panama; risk-free space to learn new tech. His analogy: don't be "the fastest horse and buggy driver" — take time out to learn "what is this car thing." - **Pairing with an expert**: having an AI-literate person (like Nateesh) sit beside you is a pattern he sees successful CEOs adopt — "half learning, half knocking out an ambitious thing." ## Noted Tension / Unresolved Points - Dan jokes that Natalia's freed 15 hours go into "extra vibe coding" — a light tension with the framing that freed time goes to clients. - Natalia's admission of skipping permissions ("I wouldn't recommend this to our enterprise clients") sits against the firm's enterprise consulting work. - Speedup claims (2 weeks → afternoon; 2–3 weeks → 30-minute draft) are presented as observations without measurement methodology, and Natalia herself hedges the engineering figure. ## Closing Notes - Natalia credits Nateesh Agarwal; **Brooker Belor** (ex-Perplexity) leads the finance practice. Contact via the Every site. (Dan's closing call-to-action is a paid-ad-style outro, not a substantive position; a Framer ad read appears mid-episode.) # Speaker & Provenance Observation Record ## Video - **Title:** How We Built 'Claudie,' Our AI Project Manager (Full Walkthrough) - **Video ID:** `01a0f15a-ae03-7ec0-be8c-34bac54520a7` - **Format:** Two-person podcast/interview conversation with a product demo segment ## Speakers & Roles | Speaker | Role | Evidence | |---|---|---| | **Dan (Dan Shipper)** | **Host / creator-side interviewer** | Welcomes guest: "Natalia, welcome to the show"; references the podcast, his own seat at "every"; delivers promotional outro addressed to audience ("Dan Shipper as the captain of the spaceship") | | **Natalia (surname not given)** | **Guest — Head of Consulting at Every** | "you are the head of consulting at every"; "you've been with us for like nine months" (per Dan); self-describes as "a bonafide vibe code addict" and lead builder of the Claudie/Claudia agent | | **Unattributed ad-reader voice** | **Sponsor promo narrator (promotional segment)** | Reads Framer advertisement mid-transcript; separate outro voice urging like/subscribe and "in love with you" sign-off — likely AI-generated or narrator, role unclear | > **Note:** No curated metadata was supplied; speaker identities beyond first names are inferred only from in-transcript statements. Third-person name references (not speakers): **Nateesh/Natash Agarwal** (applied AI engineer, ex-Kora), **Jonathan** (client-side PE partner), **Toby/“Aobby”** (Shopify CEO, cited as public example), **Brooker Belor** (finance practice lead, ex-Perplexity), **Austin** (head of growth at Every). ## Promotional Segments — Flagged - **Framer sponsor read** (mid-episode): full ad copy with URL `framer.com/dan` and 30% discount offer. - **Channel outro promotion**: like/subscribe appeal, hyperbolic praise of the show — explicitly promotional. - **Service promotion within content**: Dan and Natalia promote Every's consulting practice; Natalia closes with a direct solicitation: "reach out to us" via the Every site ("every.2cculting" as transcribed) for finance and tech AI strategy work. ## Referenced Sources & Third-Party Claims - **Client anecdotes (anonymized):** private equity firm (SharePoint thesis repository; 2–3 week investment memo → ~30 min draft claim); unnamed tech company (missing "planning phase" in plan/delegate/assess/compound framework). - **Natalia's claim:** personally spoken with "over a hundred companies in the past year"; references an earlier Every post on those learnings. - **Dan's claim:** engineers "generate two weeks of work effectively in an afternoon" under the framework — attributed to Natalia ("we're consistently seeing"). - **Named third-party individuals/companies:** Shopify CEO Toby (public AI example), Kora (Nateesh's former employer), Perplexity (Brooker Belor's former employer; also cited as Framer customer), Miro (Framer customer). - **Tools/products referenced:** Claude Code/Claude (Opus 4.5), ChatGPT, Warp, SharePoint, Stripe, Chartmogul, Post Hog, Zoom, Notion, Granola. ## Comment Availability - **Not stated** in transcript or metadata; no information on comment availability. ## Uncertainty Notes - Guest's surname never given; the agent's name appears variously as "Claudia," "Claud," "Clotty," "Cludie" (transcription variance). - Speaker attribution relies on `\>\>` turn markers without name labels; dialogue is assigned by contextual cues only. - No timestamps available in source; none invented. For AI to be useful to a company, it needs to be a coordinated effort. Claudia is our project manager for the consulting work that we do with our clients. \>\> You just launched four sub agents to like look through your Gmail, look through your calendar, look through your drive, look through your meetings to like get contacts on the project and then it's going to go and gather that information and then put it in the right place into the spreadsheets that you use to run the business. Just want to pause and be like that is that's crazy. That's kind of crazy. I mean, the only thing that's crazier is that the alternative to Clotty doing this is me doing this. I am a bonafide vibe code addict at this point. \>\> Natalia, welcome to the show. \>\> Hey Dan, good to see you. Happy to be here. \>\> Good to see you, too. So, for people who don't know, you are the head of consulting at every um we've known each other for a really long time. You've never been on the podcast, even though you've been head of consulting for a while now. I think you've been with us for like nine months or so, and you've done a fantastic job. So, I'm just really excited to get you on the podcast and share who you are and what you know with people. \>\> Thanks. Yeah, I uh I love our community and the podcast and just excited to um chat and also hear how other people are thinking about consulting, you know, and uh and AI in their companies and um so yeah, happy to be here. \>\> Awesome. So, one of the things I think could be super helpful for you to share is over the last nine months, you've had a front row seat talk to some of the top companies in the world about how to do how they do AI deployments. U and that those are people that have reached out just to chat. Those are clients that you work with, do a lot of um training and integration implementation work with like hedge funds, PE firms, Fortune 500 companies, lots of name brands that you know about. And so I just feel like you've had this front row seat for um what works and what doesn't and like what are the patterns that the companies that are really doing well at AI adoption, AI transformation are following and I'd love for you to share some of those things. \>\> Yeah. Uh that's true. I mean I think we have been a real in a really unique position in the consulting work that we do at every because uh I mean I personally have spoken to over a hundred companies in the past year hearing their concerns around how they could be using AI trying to benchmark how other competitors might be using AI and then trying to get a sense of what actually works. And it really comes down to two things. We talked about this in a post that we did um a few months ago uh about kind of the learnings from those 100 companies that we we talked to or so and one is you really need an organized effort uh when it comes to using AI well in a company for AI to be useful to a company um it needs to be a coordinated effort for AI to be a high lever tool at any given company it needs to come from the top down So unlike historic you know kind of like software where you know someone heard that a sauna was helpful for a company to use and they just let the CTO sort of uh buy it and then hope that people would use it. If there isn't a coordinated effort to um understand what the possibilities are in using AI at a company, creating tailored opportunities to actually getting leverage and value out of those sort of use cases and then tracking how people are actually using it and then um really implementing the the ways in which it works really well. AI really kind of doesn't go nowhere. it ends up being that there are like a few high-powered users that get a ton of leverage out of it and then everyone else is sort of um sort of floundering. And so there's really two things that we see working well at companies. One is it comes from the top down. So leadership understands that this is a really high lever tool and it's fundamentally changing the way that we think and relate to work. And two, they're really giving people an opportunity to become champions and owners of what it means to work with AI and creative power to explore how to rethink their roles and how to train other peers and other people to use AI really effectively given kind of this new um you know this new paradigm that we're in. So it coming from the top down there's a coordinated effort and people AI champions really being empowered to think creatively try experiment fail around AI initiatives and then really doubling down on the things that really work. \>\> Yeah, that makes a lot of sense. Um I think some some color I can give from from my seat because I I don't see nearly as much as you but I do see a lot um on the top down front. um the CEOs that are actually doing not just saying you need to do this but actually doing it. Um like those are the companies that go the furthest. Um you you will probably go as far as um in terms of AI adoption, you'll probably go as far as your CEO has gone. Um it's not something that the CEO can delegate. uh the ones that are really far ahead. It's like they're they're in Chbt, they're in Cloud Code, they're like trying new stuff and being excited about it. Like you know, Aobby A Toby from Shopify is like a good public example where he's just like hacking on stuff on the weekends and you don't necessarily have to be that far, but um Shopify its culture will be is a lot different and will be way different in a year because of that. And I think that's really important. So that's the sort of top down and then I think the bottoms up the thing that you're you're alluding to is inside of any organization there are people who are just natural early adopters and your job as an executive who's leading your org is to identify those people and spread what they know and elevate their status so that they can kind of pave the path for for everyone else who um is maybe like super valuable but is is not naturally just going to like try some new technology um but but will use it if they're shown hey this is like actually something that is going to help you in your job. \>\> Yeah. I mean Dan I feel this with you all the time. You know a new model will come out and you'll be like why haven't you run this through X model? And I'll be like you're right. Why haven't I run it through this model? Um but also you know I see it internally in the ways that it comes up naturally when in our Monday standups uh someone will say they were tinkering with a whole new use case or application uh and then the rest of us will sort of see there's this new dimension of what is possible and it's exciting when it works it's exciting but you need to be in this creative space where you're trying you're failing it's not really working it is really working it's really powerful and then when you see what's possible then you really understand like where you can go and just how far it can take you. \>\> Do you have any specific stories? You know, obviously we can't share from clients like by name, but do you have any specific stories about unlocks that you've seen that were particularly powerful? Um well, maybe it's something that we've done with our clients or just something that you've seen that maybe feels a little bit counterintuitive because I could imagine people listening to this and being like, "Yeah, that sounds good." Like generally it's great if CEO is into AI. Generally it's great to uh to promote your power users internally but like want to get down into the nitty-gritty of here are some like actual concrete stuff that is maybe a little bit counterintuitive or is a really big unlock versus the effort required. Like what comes to mind? \>\> There's there's two things that come to mind. Um one is with a private equity firm that we've we started working with last year that we're still working with. Uh and uh that one comes to mind because our partner kind of like our day-to-day liaison at that firm is both brilliant technically but his superpower is actually that he understands the people dynamics around AI really really well and because his role is he's taken it upon himself to roll out AI at his firm and um he understands that it's a technical challenge but what he really understands is that it's a people challenge. And because he's at a private equity firm and like a lot of other investment firms, there's a lack of bandwidth. There's a lack of capacity to, you know, try a new technology, see it fail. Um, there's people that are more advanced teams that are already using it in pretty uh advanced kind of interesting ways. There's other teams that just haven't had capacity to implement it. And so one of the things that uh we did together is we started out our work together by um uh he he sat down with the investors at his firm and I think you know he basically mapped out every single task that they do in like to to the most detailed kind of like end. every single task that they do from research to diligence to market mapping to portfolio management to just kind of like the day-to-day of like running their lives as investors. And so what we ended up with was the starting point of a very very detailed view of what it looks like at this firm for an investor to do their job. And what that looks like also by team because it can vary quite a lot depending on what the strategy is. And then what we did is we looked at that long task, that long list of tasks for that firm and um we went through and highlighted where there are opportunities to use AI that are really high leverage. Um, and so what we ended up with is this uh is this this this map that we end up creating for all of the clients that we work with, but it was so detailed that we could really be very very precise about looking for solutions that would give the team not just bandwidth but really high leverage in any of the training and work that we did together. And that that's the kind of work that's only possible when you have someone on the inside who is not just describing the work and workflows that teams um rely on generally but like very very specifically to the work that they do and the the the way in which they approach or think about their work. And it's made it so that in the training and the enablement and the tools that we've been able to develop together, there's this moment, this like aha moment that is like wild, you know, where investors will kind of come and realize that there is a new way that they can write an investment memo that previously took two to three weeks and they can now get like a really high quality draft in literally 30 minutes. And that's only possible when you have someone on the inside who understands all of the elements. That's interesting. Tell me more about that moment and like what that kind of either automation or workflow what what is that is that like they're using CHB well they're using odd code well like yeah go get more deep into that. So in that case it's a few things. One is this particular firm has um a lot of resources in SharePoint around the thesis that they have their investment thesis. Uh and this is this is kind of like the IP of the firm right they've spent a decade if not more really thinking about how they approach a particular um area of investment. And uh when they're diligencing a new company, they want to understand given this repository of knowledge that they've accumulated over a decade, how should they be thinking about this opportunity, you know, beyond just the number crunching? And that's something that is like really quite ownorous. It's a huge task to take on to like really read that and then digest how it compares. And of course, that's something that just CHAP GPT is able to do effectively, very very effectively. And so what it looks like for them is uh connecting the right context really the right sort of uh sources of data and then funneling it through this prompt that is trained to understand how they think about that particular investment strategy. Um, and then yeah, basically just creating kind of like a set of like GBTs and prompts that make it so that it's really easy to synthesize all of that information into an investment memo that really gives them sort of that general rubric of how that company compares to this broader opportunity and to the decade of information that they've collected. Um, that's something that again an analyst and associate of principles spend, you know, two to three weeks to pull together before it goes to the IC, the investment committee. And now you get like a really solid draft in like 30 minutes. \>\> That's really interesting. And I I think that's like actually a broad general pattern that we see in a lot of companies even in our own company is like the first one the obvious one is the connect the AI to all your data sources which is it's hard but like that's uh that's sort of table stakes is it needs to be connected to the place where all the context lives. But \[snorts\] then the other thing that's been happening especially as you know our org and lots of other orgs that were around are transitioning more into a like agent let's say agent native world where they're using cloud code or they're using co-work or they're using you know all these other kinds of tools where you kind of expect the agent to be going off and doing some work for 20 minutes and it's not necessarily like a back and forth chat in the same way. Um once you have the connections to all the data, it's really important to have the prompt or the skill that you've built um be able to tell the AI like, "Hey, here's how you find the specific thing that you want." Like for example, for us, if you wanted to figure out um what our uh like what our revenue is, like there's like three different places you could go. You can go into Stripe, you could go into Chartmogul, maybe you could go into Post Hog, but like our head of growth Austin has like a particular like way that he's defined what our MR is that instead of forcing the agent to like figure that out from scratch every single time. um sort of putting into place here's how we think about what MR is and that transfers into like you know for consulting uh for for one of these clients like uh here's how we think about this sector and here's where you get the data for this particular sector that's like where a lot of the value is um and and a lot of what makes your use of AI different from someone else's use of AI. \>\> Yeah, that's totally right. I I think it's the hardest part of AI actually and this is the part that has been so magical at this particular firm that we've been working with is that um our our partner his name's um his name's Jonathan. Jonathan basically interviewed every single investor and every single team to really understand the the the nuance in which a team collectively thinks about every part of the investment memo and this work that we've been able to do together really would not have been possible if it didn't have such a high degree of tailoring. You know, this is like uh this is like Savile Row sort of prompt ta t t t t t t t t t t t t t t t t t t t t ting. Like it's so so so specific the way that numbers show up, the way that figures show up, that the way that they express or think internally around this stuff, it's really important. Uh and the prompts reflect that. And so the prompts really end up being this analyst that does really high quality work that is dependable. And that's so cool. \>\> That's really cool. Um I I know we're we've also done a lot of work um with hedge funds and also with tech companies. Any other examples you want to share in those domains? \>\> Yeah, I mean let me think there's so there's so many cool applications. Maybe I'll speak to um there's a really interesting um pattern that we're that we're seeing at one of the tech companies that we're working with right now. uh we know that when it comes to working with engineers and with engineering orgs there's sort of like a four-step process that works uh well when it comes to implementing AI and that is you plan you delegate you assess and then you compound what works or kind of like the learnings of that that particular session and uh when we spoke to the engineers in this particular org we found that they were actually really effective at the delegating at the assessment and even the compounding um but there no planning phase and so they weren't going very far. Uh and they were running into the same sort of challenges over and over again because there wasn't a good plan for them to really scaffold significant workarounds. So they could solve a lot of small issues but they weren't able to address these big sort of like meteor problems that we kind of hope for AI to help with. And so this is the kind of thing that only by understanding how that particular you know group of engineers was using AI could we really realize like you're just missing the planning phase right like we just need to do enablement around what good planning looks like and we're already seeing that as I think we all know it makes a huge difference uh and you can only really compound as much as you plan right so um now that they're starting to compound these big plans that are developing significant work. I think we're starting to get that sort of high leverage machine that we hope to see work in engineering orgs. \>\> What do we think is possible here? Like what are the kinds of speedups that that we expect \>\> in engineering in particular? \>\> Yeah. You know that's a difficult question to answer but you know I would say we're consistently seeing um when this plan delegate assess compound framework is in place and used well we're frequently seeing engineers generate two weeks of work effectively in an afternoon and I wouldn't be surprised if that continues to speed up. Yeah, I mean we see that too and it it it it definitely changes how we think about who we can hire on the technical side and what we are optimizing for and even how we do like you know programming interviews and stuff like technical interviews. It's like a really it's a really interesting change. But I think one of the more interesting ones is for you. I've just watched you and several other people who are not technical inside the org just get totally like your your your mind totally blown over the last like three or four weeks. Like it feels like there's been this like massive phase shift where um I would just like message you and you'd be like, "Yeah, I've been up since like 6 a.m. by coding." \[laughter\] Can you like can you tell us about that because I think it's really interesting and I think that you're if I had to guess you're sort of the leading edge of the spear and there's be a lot of people coming after you that are feeling the same way and that we're going to spread a lot of things that you're learning right now to our clients and just really anyone who's like watching videos like these uh because it's it's a it's a new way of working that really valuable. So, I'll be honest. I uh So, yes, I I I think I will admit that I am a bonafideed vibe code addict at this point. So, I the way this happened is a funny it's a funny thing. I I actually realized I was starting to fall into a trap that I often see our clients fall into. So at the end of last year, you know, we had so many projects going on. We were supporting hundreds of people across organizations and every day my day would start and I just had a bunch of meetings and a bunch of work to do. And so I didn't really have time to play with a lot of these tools. And going into this year uh we realized with Natash Agarwal who is our applied AI engineer uh that is on the consulting team uh and is fantastic. He was previously an engineer at Kora uh and helped build this beautiful product and then moved uh into the consulting org to help you know amplify the work that we're doing with our clients. uh we realized with then with Natash that we weren't going to move as fast and do the creative work that we wanted if we were scheduling the work to happen in the 9 to5 if you will and so we decided to start our day three hours early so we would meet at 6:00 a.m. And we would basically just vibe code from like 6:00 to 9:00 a.m. And it all started with us asking, you know, could we create this really ambitious project which is, you know, project management is really time consuming for any consulting business, right? Any great consulting business has an entire function around project management. Uh, and it's a real skill, but it it also requires, you know, understanding a lot of moving pieces. um how clients prefer information, how they are scheduling sessions, like all of the sort of like nuance things that are happening for any given project. And uh Natash and I sort of asked, you know, do we think we could really spin up uh a we could spin up basically like an agent, hire an agent to be our project manager? And the answer really quickly was yes. But also um the the framework for how to do that effectively, this is in claude code specifically, actually took a lot of iteration. Like I would say we got 85% of the way there three times and then had to scrap it given kind of what we learned and then start again to get to somewhere to get to a new framework that actually got us to 100%. Uh so it's just been so fun. It's so cool to really build something. Uh, and it's just I think it's really creative work, right? And it's really also clarifying work to really understand to think about the questions. What does it mean to be a good project manager? What does it mean to be a good project manager for me in the business that we're running? And how do I codify this into a series of instructions? You know, we talk about AI using AI effectively being a lot about being a good manager. It's like how do I how do I um how can I be a clear communicator and provide clear instructions so that we can really create this agent we call Claud uh to really run on their own and do this work for us. And it's just so cool to be a few weeks out from that and to really have this system working. \>\> Growth is good, speed is good, but there's a specific tax that comes with growing fast. Every campaign needs a new landing page. Every product launch needs copy updates and every AB test sits in a backlog somewhere. Your site becomes the thing slowing you down and you just don't have enough engineers to keep up. Framer is a website builder that works like your team's favorite design tool. With real-time collaboration, a robust CMS with everything you need for great SEO and advanced analytics that include integrated AB testing, your designers and marketers are empowered to build and maximize your.com from day one. Companies like Perplexity, Miro, and Every use Framer because it eliminates the bottleneck. Marketing can test ideas, designers can ship updates, all without touching the engineering queue. Changes go live in seconds. One click, publish, and done. And it's built to scale with you. Premium hosting, 99.99% uptime SLAs's, enterprisegrade security, and more. Whether you're launching your first site or migrating an established.com, Framer turns your website from a constraint into an advantage. Learn how you can get more out of your.com from a framer specialist or get started building for free today at framer.com/dan for 30% off a framer pro annual plan. That's framer.com/dan for 30% off. Rules and restrictions may apply. Back to the episode. That's really cool. I want you to I want you to show us the system. Before we get there, I want to point out the that interesting pattern which is instead of just expecting it to happen inside your nineto-5, like you actually just carved out three hours outside of your job to like play. Um, and I think that's like a interesting lesson that we definitely just know ourselves internally inside of every like we just got back from Think Peak, which we do every every six months where we were all in Panama together and we just got rid of all of our day-to-day work and the whole point was just to like play around with new technology, get to know each other, build interesting things, just just play like do whatever you want. And I think that's so important in a world where technology is changing so fast because what you don't want to do is like work really hard to be the fastest horse and buggy driver, you know, and and you can't learn to drive a car until you like take some time out of your horse and buggy race to be like, what is this car thing, you know? Um, and I think you you've discovered that. I think that's something that that we've done inside of every and it's also something that a lot of our clients and just generally companies that I think do this well know how to do is um give people the space that they need in order to feel like they can try out new technology in a risk-free way where they're not going to get behind in their job. um they can kind of like learn its ins and outs and fail and then after a couple times of the a couple you know iterations of this they're like holy I had this I'm driving a car now like I'm not driving a buggy anymore and I think that's so valuable \>\> and it's really hard actually having that creative space is very very counterintuitive to the way that we usually work right how how much of our time is really spent uh you in traditional jobs just like figuring out like seeing if there's like a new way to do things, right? Historically, usually when you're hired to do a job, you're hired to do a specific set of functions that have been laid out to you that you're supposed to do until you get to the next level, whatever that is. And for a company to be so bold as to say, "Hey, we think this is all changing and we don't know exactly how it's changing, but we trust that you can figure it out and you can figure out what this means to you and maybe we'll bring in outside partners to like accelerate the way in which you do that." It's really revolutionary. It's really amazing. Um, but also it can be a really creative space where you have to be at a company that's willing to see things fail to experiment, right? Like we had to throw our project manager uh agent away three times before we found this scaffolding that really works and that saves us so much time per week. But I'm not an engineer. I'm not a product manager. This isn't kind of like my day-to-day job. And this is only exciting and possible when you put on this creative hat and just keep on tinkering until you find something that really works. Uh and for me having an aesh you know for me having uh these like incredible resources you and everyone on the every team around me where I'm seeing constantly what's possible um it just makes all of these things so much more achievable. Yeah, I think that's another really good pattern is you have Nateesh who's an applied AI engineer who can literally sit with you and help you figure out okay given my workflow how can I build this project manager and you have the expertise and like what's needed and he has the expertise in like what's at the edge of technology and I also I think that that's another really good pattern I see a lot of CEOs doing is okay the company's going to only go as far as I go in terms of um knowing how to use AI I'm going to have someone who knows about what they're talking about in AI, like just literally sit with me and talk me through. Okay, I have this project on my mind that I feel like would be really fun and really valuable if I got it done. It's going to be half learning, half just like trying to knock out this like really ambitious interesting thing. And I think that's actually a really good way to get in get yourself addicted to is have someone who's sitting next to you as you put your coe in the water. \>\> Yeah, absolutely. I'll also say I think there's something to be said about you need as much engineering power and like sort of like AI knowhow as you need an understanding of like what good looks like which is very specific depending on what it is that you do. And the different iterations of our agent that didn't work were one was just too engineering focused. It was too focused on the framework and the strategy of how the data would be connected to each other. Uh the other one was too focused on just what the work is, right? So it was just kind of like a job description. And it wasn't until we realized like all right it's a mix of the knowhow of like what good pro project management looks like and what it looks like to us which is kind of the information and context that I have and then also you know how tasks and agents and sub agents and all of this cloud code infrastructure can best be um organized so that it serves kind of the need that we're specifically looking to solve that it really came together and worked. And so you you know you can have really great engineering power but you also need to have like the knowhow to get to something useful. \>\> That makes sense. Um can do you want to show us uh a little bit of Claudia? \>\> Yeah, let's do it. Okay, cool. Can you see my screen? \>\> I can see your screen. \>\> All right, so welcome to the Every Consulting GitHub page. And this is where this is where Claudia lives. So Claudia is our project manager for the consulting work that we do with our clients. And the first thing that I'll show you is the architecture, which I think is pretty cool. This this took, you know, two weeks to like really refine and come up with uh to have it work. So I won't, you know, I actually won't uh I won't go too into the details of this. We actually have a great post that we'll share and go into the details of how this is set up. But at the highest level, we have this uh Claude MD uh file that has, you know, the instructions, the context. I'll share that in a second. Basically, kind of like the job description that Claudia has. Um then we have a list of commands that basically run Claud. So if we want to do a quality check on the data that that is collected, if we want a weekly update on what's going on across clients, if we're trying to set up a new client, if we're onboarding someone new, um then we have a list of tasks. tasks came out fairly recently and they have been instrumental to Claud being effective because um they are tasks happen in phases and so uh they manage dependencies and enable sub aents to basically doublech checkck and triple check the quality of the work that's being done before it comes back to us. Um and then we have some general purpose sort of agents. So as you some skill files general principles you know we want things to be well formatted. We want the things to be written in a way that reflects you know every in our brand and those are skills that we've enabled on the back end and then this is kind of like maybe the most important uh part it's the data sources right so we uh we enabled MCPS that connect to Gmail to calendar to Google drive and then to the meeting transcripts for the work that we do so at the highest level this is sort of like the architecture of Claudia our project manager uh and these are some of some of the commands uh to to to to kind of these are some of the commands that help Claudia work effectively. So, if you're watching this and you need a project manager, this is a pretty good this is going to be a pretty good sort of template or model for how you can think about a setting up project manager that could work for you. Um I'm actually going to now dive into the uh what I'll call this is the claude MD file and this is really what I'll call the job description that we've given Claudia. So this is a file that uh Claudia reads every single time we ask her to do something. And we found this to be really important uh because if you are a project manager, you always know where you work, what your job is, what it means to do a good job, who you report to, and who your colleagues are, right? If you're a person, you always know this information. And so we wanted to create a file that at its baseline always gave Claudia this information to remember where who it's working with and where it could be drawing information from in order to do its work really well. So um so it knows who we work with. It knows where to draw data from and then it knows every time it encounters a dashboard. This is the general way in which we've structured information um so that it can continue to populate and maintain that information uh with high fidelity. uh here uh there's some ID conventions that I'll actually mention really quickly because if you are creating your own project manager we realize there are some principles of database management that actually help a lot in in project management where you are relating different pieces of information to each other right did this person attend this training session did this training session deliver prompts or agents or whatever it was and so uh creating ID convention ions that are effectively like database management that that allow Claudia to connect who did what where were a huge unlock for us to have this entire system work well and then we gave Claudia some principles to always keep in mind so you know data accuracy totally key you have to be proactive not reactive don't wait for you know if you want to be a good employee you want to be proactive right you you don't want to be asked to do things so we kind of gave it that mentality um you know every interaction builds or erodess trust formulas over manual entry. These are just good good best practices that if you are a project manager or you deal with data, you really think about um and then when in doubt, escalate. So just ask questions. And these are some general principles that we've seen really help Claudia work very well. Um and what you'll just see here, you know, I won't go into the rest of the details, but what you'll see here is this is actually a fairly concise file. you know, we're not giving a job description that is um incredibly detailed. Claude is really, really smart. Opus45 is what Claudia runs on. And it actually doesn't need to have us define what a project manager is or what it does, but these boundaries, conventions, and sort of sharp edges, refining of sharp edges have really allowed Claudia to do really good work uh for us. \>\> This is so cool. There's so much in here. What but what I want to do is just show like actually I don't want to see it myself. I want to see okay um how does how does it work in action uh maybe like how so how how it works to set up a new client because I know that that that's one of those things where it's like okay you send a new client it's usually a big deal like it's a lot of money but like it takes a long time to get them all in all the systems so that we can actually execute the project. Can you take us through like how that works? \>\> Yes. So, let me take you I'll create a new warp page here. All right. So, we're going to open Claude \>\> living dangerously. Dangerously skipped permissions. Love it. \>\> Always living dangerously. I wouldn't re I wouldn't recommend this to our enterprise clients, but no better way to do it. All right. So we are in warp and uh I've just uh opened claude and I'm going to um so what we did here is if you go to our plugins you'll see that we have uh all of our plugins collected connected here in in the every consulting. So we have a few things that if you're following closely you might have also heard about. We have a PowerPoint skill. We have you know client work skill. Um this actually work lives Claudia lives in the workflow plugins and that's all updated. So what we do is we go to Claude and let's say we're onboarding a new client. Uh so we would say new client setup and uh I'm going to pretend like I'm onboarding uh one of my favorite clients that we've been working with for a little bit now. Headway. So going to go to Headway and uh what you'll see is it loads the skill. So now it knows what it's doing and it's going to read information. So as required by the handbook, right? So now it has really clear instructions on what to do in this case when it's creating when it's setting up a new client. Now, often with AI, we think that things are going to be instantaneous, but uh I think this is just kind of like a myth, right? I probably like with AI, for anything to be actually useful, it just takes time, right? And you want to do quality checks. And so, we're probably going to see Claudia work for a while. Um last time we set up a client, I think Claudia worked for about 30 minutes. Um, but what you'll see here is that we've instructed Claudia to do a lot of work in gathering information first. So here the first phases of her of the work are looking through my Gmail, looking through my calendar, looking through the drive, um, looking through call transcripts just to establish kind of like a a foundational set of like truths before it goes and then starts populating information into a dashboard. \>\> This is so cool. Like I it's like okay you just launched five sub agents or four sub agents to like look through your Gmail, look through your calendar, look through your drive, look through your meetings to like get contacts on the project. Like I just want to pause and be like that is that's crazy. That's kind of crazy \[laughter\] that that's possible. And then it's going to go and gather that information and then put it in the right place into the spreadsheets that you use to run the business. \>\> That's right. I I mean the only thing that's crazier is that the alternative to Clotty doing this is me doing this. \>\> Like suddenly that feels crazy. But four weeks ago it didn't seem so crazy. I was like, "Yeah, well that's the job." But now it's not. So what do you do with all your time, Natalia? \>\> Work with more clients, Dan. Of course. I think that's actually really interesting though because um you know one of the most important things about doing change management inside big companies is this feeling that okay if I do something like this but I set up an agent that does all this stuff and legitimately it can do a good portion of a job at this point not a whole job but a good portion of it or at least the tasks of a job what am I going to do and uh and that's where a lot of the resistance comes from is like I don't want to give it up until I have a vision of what comes next. And what we've been doing inside of every is on Think Week, we had a day called promote yourself day where the the idea is like literally figure out how to promote yourself so that you're not doing your IC job anymore. You're you're one level above. And framing it that way, it's like, yeah, of course, once you're once you have hired a project manager, you wouldn't expect like if it was a human, if you had hired a project manager, you would not expect them to not have a job anymore. you would expect to be like, well, now I manage the project manager and I can do a lot more stuff. And the same thing is true for this, which I think is really interesting to see. \>\> Yeah, definitely. There's two kind of truths to that that are maybe non-obvious. One is you are still managing something, right? So anytime Claudia inevitably makes a mistake or lacks, you know, sufficient information to have updated me in a way that I wish I had been updated, I have to go back and then give it context that will live somewhere in some command or maybe in the claude file uh in order for it then to do that in the future. And this is the same way that you would build a relationship with any new staff member that you would bring on board. you're really building and cementing that relationship and you're also investing in that relationship as being something that you can rely on in the future to get good work done. So that's one thing, right? When you set something like this up, it's an ongoing effort where we are constantly improving it and constantly evolving it to meet your needs. Um the second thing is this is exactly where AI shines and this is where I get most excited about AI. I my favorite thing about any of the work that I've ever done has been working with people. I I love our clients. I love the companies that we get to work with. I love spending time with them. And any hour that I am not spending tabulating information, I am spending with the people that I get to work with. And that is so much more fun and so much more valuable to me as a person who gets to spend a little bit less time in an Excel sheet. All right, so let's see. This is a little bit of a dummy dashboard that we've set up for this demo. But this is effectively the structure of what we the output that we would get. So here we have you know the total number of sessions that um we might work uh to deliver with this client uh the deliverables for that we will ultimately give to them any open items and these are tracked again across the email the granola notes or the notion sort of meeting notes that we take. So if I say in a call, okay, I will follow up with this, then that's going to come up as an open item and how sort of important it is that I track that open item. Uh so again that those would be cataloged here. Then we have the people. Uh I've hidden columns that you know sort of explain who the people are specifically, but I talked about this earlier. We have some database sort of management principles here where every person has an ID and a title and also a team ID. So we actually know how they map to each other and we understand how they're moving across different initiatives that we are that we're working on. We have a team summary so we have a good sense of you know how many people are part of a given team. Uh how many sessions they've participated in if there are any coming up. Again this is all information that's populated uh that's populated automatically. Um once we've delivered say a training session, we have a session ID and then we know what team participated, what people participated, what we covered in that particular session, where it was delivered, in this case Zoom, who delivered it and how many people attended. Um this is information that's really important to track over time so that we know really what we've done. And it's really quite tedious and it has been historically to catalog this information and save uh and save it. And now it's just populated automatically as a sk as as a session is scheduled. And once it's complete, it's just automatically marked as completed. Same for deliverables. Anytime that we deliver a new workflow or training material or a curriculum, this is all tagged here. And then we have source materials that finds and tags it to um and gives us a status for for what what's going on. We have a feedback tab where that is also uh accumulated. And so all of a sudden we're going from a working relationship where uh I am looking for this information my drive and populating this dashboard manually to I just open this drive. I ask Claud to update the uh the dashboard based on what's happened in the past week and it proactively tells me how we're doing with any given client. \>\> Absolutely incredible. And how long would this normally take you? Uh on any given week I spend at least 10 to 15 hours on just project management. Um now with Claudia I am collecting information for an hour a week. \>\> That's incredible. And then you're spending an extra like 15 hours vibe coding. Um so it just and you can \>\> I love that Natalie. This is so impressive. It's so cool. The work that you've done in the last year has been incredible. I feel very lucky to get to work with you. Um I'm super excited for what we're going to do this year. If people are interested in following you or um getting in touch with every to consulting, where where can they find us? \>\> They could find us on the every site. So we are at every.2cculting. And uh I will give lots of kudos to one Natash who's just been an incredible partner to work with. We just we're so lucky to have such an awesome team. Uh and then we have a uh a really outstanding lead who runs our financial practice. Um Brooker Belor came to Every from Perplexity where he built and ran the finance arm there. And he now is in charge of all of the work that we do for hedge funds, private equity firms, and all of our finance clients. So if you're uh in finance and interested in working uh developing an AI strategy and helping need sorry if you're uh a financial institution and need help thinking through your AI strategy but more importantly implementing it uh reach out to us and also if you're a tech company that's doing this for for your org. We have a fantastic uh lead on the tech side that we've been um that has been leading that effort and we're excited to be doing more of that this year. \>\> Awesome. Nice to call you. \>\> Thanks, \[clears throat\] Dan. \>\> 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 chat GPT. 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.