Interview with Nicholas Thorne, general partner at incubator Prehype (launcher of Barkbox and Ro Health), about Audos, an AI chatbot that takes entrepreneurs from idea to pitch deck, working website, custom GPT, and customer user interviews in minutes. Thorne demonstrates Audos's chatbot live and shows how he, a non-technical founder, used ChatGPT to prototype most of its features, including building a new feature on the show. Topics include how AI makes founders more effective, using ChatGPT to prototype, refining problem statements with AI, and using GPTs to gather and synthesize customer feedback. # Channel Presentation Observations ## Channel Identity (Explicit Self-Description) - **Show name and format**: The closing monologue names the show directly: *"subscribe to how do you use chat GPT"* — an interview show where host **Dan Shipper** talks with guests about how they use ChatGPT/AI in their work. - **Host role**: Dan positions himself as interviewer and narrator: *"Nicholas welcome to the show"* and framing the episode's purpose: *"what I want to do today is go through this business that you've built and then talk about how you've built it with AI."* - **Persona in outro**: The outro describes the host as *"Dan shipper as the captain of the spaceship"* in a stylized promotional monologue. ## Intended Audience - **Non-technical builders and aspiring entrepreneurs**: Dan explicitly addresses this group: *"for anyone who's like wanting to build a product like this is a model I think especially if you're not technical that is like a really good way to get started."* - **People curious about practical ChatGPT workflows**: The episode premise — walking through *"how do I chat GPT like the way I chat GPT is to make this"* — targets viewers seeking concrete usage patterns rather than theory. - **Interviewee's target market (distinct from channel audience)**: Guest Nicholas Thorne describes his product's customers as people who *"have had a business idea"* but historically lacked time or skills — e.g., *"if we can just start to play things back to people put them in edit mode not creation mode."* ## Claimed Scope - **Episodic interview format with numbered episodes**: Title indicates **"Ep. 16"**, suggesting a serialized show. - **Demonstrations over discussion**: The show includes live screen-share demos — the guest walks through *"a quick demo"* of the product and his ChatGPT prototyping setup, indicating the channel demonstrates tools live. - **AI-focused subject matter**: Every topic in the transcript (GPT-4, function calling, Airtable scripts, prototyping with ChatGPT) sits squarely in applied-AI territory; Dan states the episode covers an *"end to end use case of I want to start a business with AI."* ## Observable Presentation Patterns (Demonstrated, Not Claimed) - **Conversational, friendly intimacy with guests**: Dan notes the guest is *"a close friend of mine,"* producing a casual, insider tone (*"I owe you and Henrik... a big debt of gratitude"*). - **Host demonstrates his own AI fluency**: Dan shows prior experience: *"I've built a lot of this stuff before and like it's really hard to get it to work well enough to do stuff like this."* - **Audience engagement prompts**: Explicit CTA in the outro: *"you absolutely positively have to smash that like button and subscribe."* - **Guest promotion is permitted**: The episode ends with guests sharing contact points (autos.com, Twitter handle, book launch *"next month"*), showing the channel surfaces guests' projects. ## Claims vs. Demonstrations — Distinctions - **Claimed by guest (not channel)**: Thorne's statistics (~60–65% of people have had business ideas, *"48 hour payback period"*) are guest assertions presented in the interview, not verified by the channel. - **Claimed by channel/outro**: The hyperbolic outro (*"epitome of Awesomeness," "pure unadulterated knowledge bombs"*) is self-promotional tone, distinct from demonstrated content, which is a long-form technical/business conversation. - **Demonstrated by material**: Deep technical walkthrough (DNS records, Airtable schema generation, Supabase edge functions) shows the channel delivers substantive applied content, corroborating its stated ChatGPT-use focus. # Delivery Observations: "Take Your Business From Zero to One With AI – Ep. 16 with Nicholas Thorne" ## Format Overview - **Interview/podcast format** with a host ("Dan") and a guest (Nicholas Thorne), including a **live screen-share demo** of the guest's product (Autos) and his ChatGPT workflow. - The transcript ends with a clearly distinct, highly promotional **outro segment** (> "you absolutely positively have to smash that like button and subscribe"), suggesting an AI-generated or scripted channel plug appended to the episode. --- ## Tone - **Casual, enthusiastic, and conversational** throughout. Host uses superlatives liberally: - > "this is truly wild" - > "I mean that's that's freaking crazy" - > "this is a lot more than I expected this is great" - **Self-deprecating humor from the guest**, especially about his technical skill: - > "I've never taken a computer science class in my life" - > "my programming is sufficiently bad" - **Playful banter** between host and guest, e.g., the mutual-gratitude exchange: > "we're a mutually assured um destruction there or gratitude whatever" --- ## Vocabulary & Recurring Phrases ### Guest's recurring language - **"Chat for the sake of"** framing: - > "it's like it's chat for the sake of calling a function" - **Hedging fillers** — very frequent use of "like," "you know," "kind of," and "um," consistent across the whole transcript. - **Repeated emphasis on closeness to customers**: - > "be as tight to your customer as possible" - > "stay close to your customer" - > "talk to your customers" - **Repeated framing of AI as magical**: - > "I just think it's magical" - > "chat GPT is magical because it like it it actually understands this" - > "the thing that feels really magical to me about this" ### Host's recurring language - **Interruption + reaction pattern**: The host repeatedly stops the guest to reflect enthusiasm: - > "I want to stop you right there because I think you just said something like really profound" - > "wait wait wait wait wait this is kind of crazy" - **Clarifying question bursts**: - > "are there any humans are you involved in like wizard of oing any of this or is it all like automated" - > "how is it architected" - > "if you're not really totally understanding what's going on how are you guiding yourself through whether chat gbt is doing the right thing" --- ## Teaching / Explanation Habits - **Demo-driven explanation**: The guest explains primarily by walking through the live product (Instagram DM bot → deck → website → co-pilot → interviews → roadmap). - **"Stats are useless until you feel them"** — offering numbers with a caveat: - > "stats are kind of like useless until you feel them but but I think these are things we feel" - **Analogies to familiar tools**: - > "really just like a glorified way of running longer Excel functions" - > "it's like Lego you're stacking Lego bricks together" (host's summary, accepted by guest) - **Process recipes**: The guest repeatedly breaks his method into numbered steps: - > "my process is really probably a three-step process one is try to come up with what's the output that you want chat GPT to create" - > "paste the error message and slowly but surely if you're patient enough you can get there" --- ## Communication Patterns - **Host summarizes back**: A consistent pattern of the host recapping what he heard, then asking the next question: - > "so I guess if I to summarize like how this is all working is air table is sort of like... the source of truth" - > "what I'm what I'm observing is you have this business that you've run for 10 years..." - **Guest's dialectic thinking method**, explicitly described: - > "I'd like to kind of go through a dialectic with you where we Define them or we list the pros and cons of them independently and then where we like crash them together and merge them" - **Frequent mid-sentence self-corrections and restarts**, observable in nearly every long turn from the guest (e.g., "the the general partner of the incubator prehype which actually um incubated"). --- ## Isolated Moments vs. Stable Patterns - **Stable patterns (well-supported by repetition)**: guest's hedging fillers; the "magical" framing of AI; host's interrupt-and-react style; both speakers' casual vocabulary ("freaking," "wild," "kind of crazy"). - **Isolated moments (insufficient repetition)**: - The outro's over-the-top tone (> "I'm absolutely hopelessly in love with you") appears only once and does not reflect the episode's overall delivery. - The "Airtable timeout" aside (> "if anyone from Air table is listening") is a single direct-to-audience aside, not a recurring habit. - The panther-vs-grey-wolf anecdote about the guest's son is a one-off storytelling moment; no evidence of a recurring personal-anecdote habit. # Position Extraction: "Take Your Business From Zero to One With AI — Ep. 16 with Nicholas Thorne" ## Participants - **Nicholas Thorne** — General Partner of incubator Prehype; founder of Autos; previously founded Basno (electronic badge company). Identified via transcript introductions and self-identification. - **Dan Shipper** — Host; identifies himself as a friend of Thorne and notes his own company emerged from Prehype. Curated metadata is absent; identification rests on transcript-internal cues (the closing outro names "Dan Shipper"). --- ## Thorne's Central Positions ### 1. "AI everywhere," not as a buzzword - Autos is **AI-native on both sides**: internally (how the team works) and externally (how it serves customers). - **Reasoning:** Founders should stay as close to customers as possible in early phases. AI serves this in two ways: 1. AI as a "conversational force" keeps you talking to customers. 2. Offloading capabilities to AI means fewer hires to manage, so you don't "get sucked back into the organization." - Qualification: "not as like a buzzword — although happy to benefit from the buzzword if it's a benefit." ### 2. Trying beats picking - **Claim:** "We are... bad pickers of ideas — maybe not bad ones but just like that picking is hard." Going out and trying things yields first-party insights. - Everything built with Autos aims to make that trial process available to a broader group. - **Qualification preserved:** Thorne did not originally set out to scale to a broad audience — "we set out to just make our own process more predictable and repeatable." ### 3. Founders as "first draft makers" longer - **Claim:** Entrepreneurs drift into "CEO with big company problems" partly because they stop being the first-draft maker. AI tools could extend that phase. - Supporting argument: The big-company model — founder creates vision, others create proposals, "the big meeting at the end" — is "definitionally a big company thing" and hard to make work. - Framed as open question: "what happens when... the foundy team is just more often... the ones making the first drafts — then what? ...we'll find out." ### 4. Non-coders can now build functioning software - **Claim:** Thorne has never taken a CS class; prior to ChatGPT he never really programmed. ChatGPT has been "completely revolutionizing" for writing code. - Qualification, preserved verbatim in spirit: "I for programmers I know that what I create is not per se code but does function, it does work, and it does deliver a result and therefore code tends to be code." - His process: describe the desired output → paste error messages back → iterate, "probably within two back-and-forths we'll have a correct answer." - He does **not** claim to be learning to program: "I don't see it ever being a productive use of my time to start with a blank sheet." ### 5. Prototyping stack - **Airtable as lightweight source of truth** with scripting/automations; ChatGPT writes the scripts and glues together third-party services (DNS APIs, logo generators, Stripe, Google Slides via Apps Script). - Production system now runs on **Supabase** with edge functions — "not dissimilar" from Airtable scripts. - **Claim:** GUIs slow development massively ("you've just wasted days... you haven't even gotten past the login"); conversational delivery can remove the need for a GUI. ### 6. Dialectical prompting method - **Claim:** Presenting two distant concepts to ChatGPT and asking it to define, list pros/cons independently, then "crash them together" yields more than linear conversation. - Reasoning: ChatGPT "takes it seriously" — e.g., it didn't judge a question about MLM referral mechanics — enabling disciplined thinking "I don't think I'd have the discipline to do alone." - Example on screen: exploring whether non-exploitative MLM-style referral systems exist for Autos. Thorne explicitly notes he did not take this far: "I'm not sure how far this thought process will go." ### 7. Autos product claims - Lives primarily in **Instagram DMs**, chosen because of distribution: Facebook's fall product for acquiring users directly into conversations avoids installing "new behavior" in an app. - Flow: acquire via ads → AI asks for a named customer → problem definition → solution pitches across business models → auto-generated pitch deck (with icon, naming via "heroes" of the customer segment, color palette, market sizing via Google search) → $30 payment → landing page, domain registration, hosted custom GPT for the customer's own lead acquisition, ad-campaign assets → self-interview and friend interviews via voice chat → synthesized product roadmap. - Reliability claim: almost fully automated; exceptions are things like Google Apps Script permission timeouts "once every couple of weeks." - Speed/economics (as stated by Thorne and echoed by Dan): **~3 days average from zero to business**, "can't keep up with demand," "thousands of people looking to pay," "48 hour payback period." ### 8. The 60/8 gap - **Claim:** ~60–65% of people report having had a business idea, and a similar share say they have the resources/knowledge/experience to start one — yet only ~8% start one in a given period. - His diagnosis: not knowing where to start, and too many options so no progress on any. AI puts people "in edit mode not creation mode"; "momentum is oxygen." ### 9. Normative stance on AI use - **Claim:** AI can push entrepreneurship ("making something in service of someone else") to new heights. - **Contrasting worry:** passive uses — "people just use the big models and outsource parts of their life" — are "a very scary thing in my view." - Position stated as commitment: "I'm kind of committed to this." ### 10. Historical bets - Basno was an electronic badge company "before NFTs were a thing." Thorne's own qualification: "NFTs pre-blockchains is... the most laughable" positioning; but the company mined Bitcoin and "mined a block." - He was heavily into GPT-3 by **2020**; Dan confirms and admits he initially thought Thorne was "off the deep end" and that Thorne "was so right." --- ## Dan Shipper's Positions - **"Show, don't convince":** Anyone can now make a small working artifact of the idea in their head in hours — film, art, software — without funding or persuasion skills. "It's really hard to convince people of things but if they can see it... things might get funded or get made that never would have been able to be made before." - Echoes Apple's prototype/demo-driven product culture (referencing a book on how Apple builds products); Thorne agrees: "100%." - Assessment of Thorne's stack: "I don't think I've ever seen someone use AI so extensively" both in prototyping and in the shipped product; recommends it as a model for non-technical builders. - Recounts his own prior skepticism of GPT-3 in 2020 as a contrast point. --- ## Points of Agreement - Prototypes/demos beat decks and abstraction ("the prototype is worth a thousand decks" — Thorne). - AI dramatically compresses the gap between idea and visible artifact. - ChatGPT is uniquely strong at the boundary between natural language and machine-readable formats (e.g., generating hex color values). ## Unresolved Tensions (preserved) - Thorne's MLM exploration is explicitly unfinished and tentative; he jokes about having "my downline agreement" — no settled position. - Whether founder-first-drafter companies produce better outcomes is posed as an open question, not a conclusion. - Stats cited ("60–65%," "8%") are presented by Thorne as approximations — "something like" — without cited sources. - Thorne's "stats are kind of useless until you feel them" caveat precedes his own use of stats. # Speaker Attribution & Provenance Record **Video:** Take Your Business From Zero to One With AI - Ep. 16 with Nicholas Thorne ## Speakers & Roles - **Dan Shipper** — **Host / Creator**. Identified in-transcript as "Dan" (guest addresses him by name: "Nicholas welcome to the show / thank you for having me Dan"). He describes the guest as "a close friend of mine," references a "pre-production call," and asks the questions. The closing promo names him: "with Dan shipper as the captain of the spaceship." - **Nicholas Thorne** — **Guest**. General partner of the incubator **Prehype**; founder of **Autos** (AI business-building service). Identified in transcript by host: guest says "I'm also Nicholas... prehype.com." - **Unnamed narrator/promo voice (likely promotional segment)** — Closing exhortation to "smash that like button and subscribe to how do you use chat GPT." No speaker identity given. ## Roles of Referenced Third Parties - **Henrik** — other partner at Prehype, mentioned as co-recipient of host's gratitude. Does not speak. - **Guest's five-year-old son** — mentioned in the "panther vs. grey wolf" ChatGPT anecdote. Does not speak. - **"Alex"** — example Autos customer referenced in demo walkthrough (domain/DNS example). Not a participant. - **Basno** — guest's first company (electronic badge company, pre-blockchain NFT-like concept). - Companies incubated by Prehype, per host: **BarkBox, Romu.com (as transcribed), Ferry, Headway, Every**. - **Every** — host's company, incubated at Prehype ~10 years prior. ## Referenced Sources, Tools & Claims (provenance only, not evaluated) ### Technologies / Services Cited by Guest - **ChatGPT / GPT-3 (since 2020) / GPT-4 API** — core product and development tool - **OpenAI function calling** — guest cites June 13 of prior year as significant ("as of last year") - **Airtable** (with scripting/automations) — prototyping database - **Google Slides via Apps Script** (guest notes it's "not really the Google Slides API") - **Google Cloud Functions**, **Supabase** (production system with edge functions), **Stripe**, **DNSimple**, **Instagram DMs / Facebook ads** (distribution channel) - **Stanford d.school** — cited as source of the need-finding interview playbook style ### Unverified Third-Party Claims - "60 to 65% of people... have had a business idea"; "~8% start a business in a given period" — statistics attributed to unnamed research ("it's something like"), no source cited. - Guest's claim of having **mined a Bitcoin block** ("NYC bit minor is in the blockchain"). - Business metrics: "three days on average" zero-to-business; "48 hour payback period"; "thousands of people looking to pay" — speaker self-reports, unverified. ### Host-Stated Facts - Prehype has incubated "50 other startups." - Guest was early to GPT-3 in 2020 and founded an electronic badge company pre-NFT. ## Promotional Segments — Flagged - **Closing promo block** (end of transcript): explicit like/subscribe promotion for the show "How Do You Use ChatGPT" hosted by Dan Shipper, ending with an on-camera persona declaration ("Dan I'm absolutely hopelessly in love with you"). Unattributed narrator voice. - **Guest self-promotion** (closing): Autos website (autos.com → Instagram), upcoming **book launch "next month or so"**, Twitter handle "Thorn NY" (as transcribed), and prehype.com contact. - **In-show ads**: guest's Instagram acquisition ads quoted in demo ("that little business idea you have... let our AI make you an AI"). ## Availability & Uncertainty Notes - **No curated metadata supplied** — no channel, publication date, or verified speaker identities beyond in-transcript statements. - Transcript spelling ambiguities: "Romu.com," "Thorn NY," "Chachi/Chat PD" (ChatGPT), "gooey" (GUI), "Echelon" (Airtable base name in demo), "d school" (d.school). - **Comment availability**: not stated in source; no comment data available. - No timestamps present in source; quotations above are paraphrase-adjacent excerpts from an untimestamped transcript. there's this sort of like end to endend process of like start with a couple questions to a deck to a website to a little wizard that can like help you modify a couple different things I hope you're not tired of all the AI because unfortunately the answer to it is that we use a lot of AI to make why did I know that was coming I've never taken a computer science class in my life I don't know anything about computer science I've never prior to chaty BT I never particularly programmed anything chat gbt has been completely revolutionizing to me of being able to write code and and I for like programmers I know that what I create is not per se a code but does function it does work and it does deliver a result this is truly wild Nicholas welcome to the show thank you for having me Dan I'm excited to have you so uh for people who don't know you are a close friend of mine you are the the general partner of the incubator prehype which actually um incubated or really was like where every came from where where my first not not my first this company my first company was 10 years ago um where where uh where every came from is from pre hype um which so I I owe you and Henrik uh the other partner uh a a big debt of gratitude for that um and uh in addition to types of debts of gratitude when they when other sides of the coin feel that they are the ones who owe the debt of gratitude so I suppose we're in we're a mutually assured um destruction there or gratitude whatever po that gets a little too close to Maga so we'll stick with um so and you have incubated um I mean every is obviously one of your illustrious uh illustrious uh examples but you've also incubated 50 other startups including BarkBox Row umu.com for them Ferry and Headway and like one of the things that I think is most interesting about you is you've been very early to like the two biggest technology Trends over the last decade and a half so your first company basno uh was a electronic badge company before nfts were a things so you like you totally like called the nft thing like 10 years ago is yeah laugh laughably so I have I have to basically say to everyone who I who comes upon some version of that conversation that like unfortunately nfts pre- blockchains is a is like the most laughable set senten yeah I guess you were yeah you were too you you are too early in the sense that the blockchains were not not around but still you had the concept at least we were mining Bitcoin as a result of it and mined a block so NYC bit minor is in the is in the is in the blockchain There You Go part of History um and then uh you were also like just really into gpt3 like in 2020 is when all 2020 yeah and I gotta say like when you first starting getting into it I was like this is kind of interesting but I don't know Nicholas is like off the deep end again like you know and you were so right like you you freaking called it um and one of the things that I uh like one of the really interesting things about being so early is I think you've been able to like really understand what these tools are useful for and um apply them in your life and and in your business and um you know at prehype your job is to start an incubate companies um but uh what you've done is you've actually gone and uh started a new company to help do more and better incubations with uh with gpt3 or GPT 4 now um and it's sort of like this interesting GPT all the way down thing where you're using chat GPT to help you build the business um the business itself the product itself uses um uses GPT the GPT API to serve your customers and your and your customers are using chat GPT or the GPT API to like build their businesses so it's like uh you're using AI to like the fullest extent that I think you possibly can in the result yeah maximalists or whatever the whatever the word yeah and um and I think the results are like like really sort of speaking for themselves like I you told me in in the in the pr in the pre-production call that like your goal is to help people go from zero to business help your customers go from zero to having a business as quickly as possible and with AI that takes like three days now on average um where it used to take months or just wouldn't happen at all because they didn't have the skills to do it um and you're basically in this in this place with this company it's called Autos where you can't keep up with demand and you have thousands of people looking to pay you to help you build their businesses um and with like a 48 hour payback period like it's kind of a crazy thing that you've discovered and what I want to do today is go through this business that you've built and then talk about um how you've built it with AI and then um how the product itself works with AI to serve customers because I think it's it's this like end to-end use case of I want to start a business with AI and I want to learn how to like Leverage it to build stuff and to even if I don't know how to code and and to um make products and and make money online and I think you're like the perfect person to like help walk people through that because that's literally your job and you've done it yourself yeah and we've um I mean as you're saying it the interesting part is to me in in just reflecting on it on the Fly is there's both like AI native in our capability Set uh you know like the the way that we work is you know AI is everywhere um and then there's also kind of you know in a in a way we serve a customer and our interaction with our customer AI is super native you know and so we're we're sitting on both sides of that trade which which is very purposeful um in as much as we have been trying forever to just you know remove as much of the between you know founder and customer as possible like that's both the advice I would give other Founders is especially in the earliest earliest phases to like you know be as tight to your customer as possible and that and and and you do that in two ways one is obviously by like trying to talk to them and spend time with them and so AI is a conversational force is an incredible power for staying close to your customer but then you also do that by like not getting sucked back into the organization as much as possible and so if you can imagine the amount of capabilities that if you can turn them over to AI and you don't have to like hire people that you then have to manage and spend time with well then like definitionally you you stay clo tighter to the customer too and so it's like it's both because you of the way you interface with people and by not getting drawn back into the you know into the org that you stay close to the customer so you know I for sure we're just kind of like AI everywhere not as like a buzzword um although happy to benefit from the buzzword if it's a benefit but um but also just because like I think it's a great way to spend time with customers that makes that makes total sense I would actually really love like can you show us yeah let's let's do like the the normal yeah the business that you build and and show it to us a little bit yeah as you mentioned um our our core business has been helping entrepreneurs figure out what company to start next um and that we we've tried like a hundred different ways to do that and um but like by call it you know 2020 and having been in that roughly business for a decade um you know that looked like maybe we could a few times a year like help someone start something and that was because a we need to like have a good relationship with them and get to know them and um and these things take time but also it's because like practically speaking there was a lot of work to in the way that we were doing it to do to kind of like help someone go from thinking about a couple different business ideas framing them up in like a consistent enough way that you could even kind of like compare Them Apples to Apples um going out and and finding some customers for those things and talking to them and synthesizing the results of those conversations uh and then going out and finding like some some more customers who are hopefully like strangers and talk you know talking to them in some way probably less of like an actual conversation more of some sort of you know lead acquisition flow um all towards like helping create this Dynamic for a Founder where they were you know as much as possible not kind of a priori making judgments about which of their ideas were good ones but instead like just building some early momentum and seeing if anything kind of like just stuck um you know like out absurdum like we are feel like bad Pickers of ideas or maybe not bad ones but just like that picking is hard uh and that if you can just like go ahead and try things that you end up learning a lot and like getting first-party insights and so everything about like what we've built with Autos is to try to like make that set of processes available to a much broader group of people uh we actually didn't set out to do that we set out to just like make our own process more predictable and repeatable Etc and the natural result of it of course is that if you encode it in software then you can do more and so the demo I want to stop you right there I want to stop you right there because I think you just said something like really profound that um that I've encountered two and it sounds like we're we're sort of like I I always love when you when two people like have similar insights from maybe without having talked like they've come to the same conclusion and the thing that you said about like um we're we're not great Pickers or maybe we're average Pickers or whatever um but it's always better to like um to go out and like try something to know if it works um the thing that that that resonates so much for me about that is I think it relates very deeply to um what you're probably about to show and also what I've seen AI do for people like when I when I try to figure out when I when I try to get that core of like what's most useful is that for any project that you want to do you can go and show it like show how it would work and start getting feedback on it and getting um hype or what like whatever you want whether that's software whether that's filmm whether that's art like whatever you can just do that like in a couple hours whereas before um either it would have taken a long time and you would have had to have a lot of skills and a lot of whatever or you would have had to be able to convince someone to invest in you to like fund your your movie to like get all the cameras in the director and whatever or you would have had to get someone to fund your um you to go and hire Engineers to like make your make your app and I think the like one of the core things that's happening is we are moving into this world where anyone can just like make that little thing to like show to show their work to show someone how amazing the thing in their head is without having to convince them and it's really hard to convince people of things but if they can see it you might like you might get a reaction and things might get funded or get made that never would have been able to be made before and I think that's sort of what you're doing yeah yeah there's the like the Prototype is worth a thousand decks you know type of mindset in there and I and I completely agree and not to like um we've been working on a book um and one of the things that I just will call out to that is uh to to your point here is that to me um one of the profound implications about you know of of that Dynamic is not just true in terms of how you get started with things but is also true of how you operate them you know over time and um you know the the point being that like yes that's that's true of how you get started it's also true of um like once you're once you're starting and the and the practice of continuing to uh you know build things um because you know imagine that one of the reasons that a entrepreneur goes from being kind of like an entrepreneur to being you know a CEO with big company problems over time is that they are no longer like the first draft maker U within their company and so one of the one of the things that we have been thinking about is like what happens if you can be the first draft maker longer as someone working on something and arguably in our view it like helps you stay close to your customer but which which is important but in general you know like the rarely is it that like the like I think we can all in it that if if the founder CEO could stay close to their customer longer um that that would be very valuable right um and it doesn't mean that they would have all the ideas um but like at least they could have contribute more of the ideas right and um and so anyway so these kind of hybrid Concepts in my mind are are really important in terms of both sitting in the customer service seat longer I guess I'd call it I.E just being a little bit closer to the conversation that your organization or your you know business or product or project is having with your customers um you know if you can just hang on to that a little longer stay a little bit closer to that obviously your information flow improves but then to the to your point if you can use those tools to create more for straps just like the Fidelity of what you create as a CEO is less of this like you know I like we talked about this like concept that you know if if you sit there as a running a big organization and all you do is you like create this big vision and then other people go off and create proposals as to how to achieve it and then there's like the quote unquote big meeting at the end you know that's just like a very difficult organizational model to make work you know um or or like it works but it but it's but it's like definitionally a big company thing and so I'm so interested in what happened I mean this is like looking forward really it's like what happens when you have companies where the founders and or the foundy team is just more often and and for a longer period of time the ones making the first drafts like then what you know um and I think what you'll find is there are just really interesting like you know Downstream implications of that but we we'll find out no I I think that's I think that's great it reminds me a lot of um it's not the exact same thing but there's there's that book about how Apple um Apple builds products and it's all about prototypes and demos and it sort of reminds me of well yeah 100% yeah yeah yeah totally um okay so Autos so so I was kind of like going into this background of Auto so Autos um currently lives primarily and I guess I'll just do a quick demo here Dan and then you yell if like if if something we should do differently so Autos currently lives primarily in an Instagram uh you know DM and so it's a it's an AI you can imagine wait why did you start there so it's it's a it's a DM AI bot why did you start with a bot um in DMS yeah uh we started with a bot and a DMS um because distribution like what do you know matters you know and um and Facebook has introduced as of like last fall a a product to acquire people straight into a conversation um and that was like a dream come true for people who like spend a lot of time using the word talk to your customers you know if you're in the business of telling people and yourself trying to talk to your customers well then like where where do you do that where you can have kind of like a persistent conversation and not have to like install some new behavior for people where they come you know into your app which is like laughably difficult to do you know um and so I think the question was like could we could we actually just make a version of a um you know a chat experience that would would live inside of Instagram so that we could both take advantage of like Facebook's products as well as uh frankly just do something that was natural and native to the to our customer um and so you know that's where that decision got like made for us we had we had had these like on-site versions in fact at some point I was like talking to a journalist and they're like going through some they're like why does this work this way I'm like what what are you talking about like and they're using some version of a product they found online from like six months ago I was like oh frud like that's not the right one um you need to go over to Instagram we start with a conversation so people find us there we we do have like a following and and you know I don't know we got thousands of followers who who have traditionally you know we we were publishing these like Business book little videos and shorts and that was like just build up a little a little bit of like audience and whatever but people do come and find us there uh but mostly we just acquire people we run ads that say varying versions of like you know do you want to like start a company or um do you have an example yeah you know we run ads that are things like you know that little business idea you have like it'll still be an idea next week or you can let our AI make you an AI and go from z w I think that's probably I would click that I like that a lot you know we do we do a lot of that kind of stuff and we're we're testing into more like different creative but um but what happens here is um very quickly we do a few things one is we we anchor and the AI is trained to like request a name from you the entrepreneur um and so what we learned over time is that like obviously when you when you start to create um chat experiences like where you start matters a lot especially if what you're trying to steer towards is like a fixed outcome and in our case we have some very fixed outcomes that we want to be able to deliver so that this is not just chat for the sake of chat it's like it's chat for the sake of calling a function and and we can get as wonky or not about that as we want but like suffice it to say that June 13th of last year when you know opening ey comes out with um you know function calling now tool you know kind of calling was like a big was a big deal for us um but so we try to get you to name a person again that's like a a very basic that has nothing to do with AI that has to do with like our own sensibility that the type of business that we um feel we can help people start uh but maybe in general like you know the way we happen to know how to help people start companies certainly not the only way but the way we know is to you know help them really like kind of deeply imagine who the person is that they're going to serve and almost with the with the unsaid truth that if if you do not know that person or they're not in your phone book or a few of them maybe are not in your phone book like you're you're G to have an uphill battle whereas if you can kind of cultivate founder customer fit if you can you know actually like take this knowledge of someone it could be even yourself really and um and turn that into an initial product offering and then build an entire kind of company that you know protects and and and and um cultivates your fit over time that you know really interesting things start to happen but anyway so this person uh provides a name of uh their their customer uh you can tell that this person has thought about this um because once we ask them the next question which is what does the customer need or want but can't get what's and what's stopping them from getting it they've provided a a detailed answer so they say in this case that Camden their their customer wants to save to buy home and this is really just to get a little bit deeper into like what is the problem uh and so it provides a couple of different options as to like what are some other interpretations of the problem where obviously our our perspective is that if you can you know be very precise about the problem you're trying to solve it just makes coming up with a solution easier um that's true generally again it's also true in how well the the uh the GPT can do in in providing interesting solution Alternatives and then in this case we'll pitch a series of potential Solutions which are really just across like a bunch of different business models and and solution Styles like what you know what how could we think about solutions for this and rarely are they mutually exclusive you know we we pitch you'll see the first one is software the next one's like a platform or a network the next one is kind of a product a physical product the next one is some sort of financial product the next one is some sort of kind of content product so they're all these different angles and most of the time what happens is people say oh well it's a little bit of that and it's a lot of this and and maybe it's a touch of that um but within those three or four questions what we then move on to is the is the GP tool will say okay great give me a second and I'm going to try to kind of frame this up um in a uh in a presentation and so what happens now in the background is uh a a set of uh gpts really are running a variety of processes that all then lead to contributing to the creation of a a little presentation which works through high level like what's the context um a couple slides on like what context um does this problem and customer exist in um if we kind of restate the problem how would we wait wait wait wait wait this is kind of crazy so like basically you acquire a customer with an ad saying I want you uh do you want to start a business and the customer's like yeah and then you ask them a couple questions with gbt through Instagram uh and then like five questions in they just get a automatically generated I mean this deck looks really good like beautiful deck is are there any humans are you involved in like wizard of oing any of this or is it all like automated uh you know no you know every once in a while something breaks and someone has someone starts yelling and we have to go like uh you know hit a button or something to restart things um you know like Google times out our permissions on the Google Slides like little API it's not really the Google Slides API it's an app script if you want to get wonky and like we have to rep permission it that's probably been the the key thing that keeps you know comes up once every weeks and it's the type of thing where like it's not working for a couple customers what's going on there I'm like why did we not put down a list that says don't forget that that's all automatic um and so yeah let's just go through super fast because what we do is we talk about the context we talk about the problem we then have had a you know a a little GPT go off and and think about like you know defining at at every level like what what are the words that would describe uh the iconography for this business and then and then over time then using some models not the case to make um a little you know icon um what should we call this which we do based on actually a process whereby we figure out like who are the heroes of the people of these customers like who are some some celebrities or scientists or whatever that that these people might look up to and then what would they call this business um and so we have like all these different processes that are running in the background obviously we had to pick a color palette because this one is Browns and greens and whatever and other ones are you know different colors um yeah and so so then we um yeah so we so we work through we've had these sub agents go off and do these various um you know jobs um we go through a a user Journey um or or attempt to kind of frame up what is this solution and then what how would someone experience it um all the way through to kind of what would you think about as being the key benefits and how much would you charge for that how many people are out there that um might want this and so in the background a Google search has been run to go look for you know data and and to Source data um obviously we can then take like how many people times how many much would they pay and at least like start to think about the size of this opportunity and then we create like a to-do list but all of which yeah again yes happens automatically and happens in I don't know you know if as long as gp4 is not too backed up it happens in you know five or six minutes like the thing that feels really magical to me about this is um it's like seeing your idea come to life in this like in a couple of questions is so cool um it must be so validating because I feel like there are so many people out there that that have these ideas and have never seen them like actually in the real world because they just haven't they don't have the time or they don't have the skills or whatever and even though this isn't the real product yet just like seeing a deck with your logo and your problem like played out like this I think is probably a huge moment for people I think so I mean I maybe just to give you some stats but and and stats are kind of like useless until you feel them but but I think these are things we feel and so therefore I think the stats give you know give better talking points it's something like 60 to 65% of people who if you ask them um have had a business idea um and and it's the same number of people and this is true both in the US and I think globally who say that they have the resources and the experience and the knowledge to start a business um so then you have this qu but eight % of people or something like that start a business in any given period so you got you have a big gap you basically have 60% of people who have had ideas and separately think that they have the resources the knowledge and the experience to do it um and then you have like basically 90% lossess you know and it's like why is it lossy um some portion of that I think we can think is is probably a good thing um but like you know generally speaking I think it has a lot to do with like not knowing where to start having way too many things to potentially make progress on such that you don't end up making progress on any of them and so yeah like to your point I think if we can just start to play things back to people put them in edit mode not creation mode a little bit more often um it just allows the like little early bits of momentum to build on themselves and you know momentum is oxygen for these types of things so you just you give a lot of chance that something might stick um if you can if you can get people out of their own heads and give them a little bit of a a way of working yeah that makes sense so okay so I think I I think I get the deck I think this is awesome what is like once you've built the deck like what is yeah yeah what happens um so the first thing you can do is obviously you can like play back into it um this this person did not do that I think he just said okay um but just okay like give me a little Kudos there man well he says okay but then I think he goes yeah actually sorry no no no no he said okay too I'm gonna make a deck and then he said looks great keep going okay and so that's very very very common uh people do have like uh you know feedback that they'd like to give and so let me just go find quickly here like a link to this guy's feedback you know he if he had asked for it the the co-pilot would have just gathered up a few of the key kind of assets um one of the things we've also learned is like trying to give you full I mean by the way they can just duplicate that deck and then they can take it and make whatever edits and sometimes the co-pilot's a little cheeky and we'll when it doesn't when it finds the comments to be a little bit too um specific it'll say you know why don't you just go ahead and and duplicate aop yeah which again you and I Dan will appreciate from having written decks like these with a lot of different people I wish I could have said that sometimes that's a very human the the human and the correct answer to the uh to the question right um at which point he would have arrived on a little interface where he could have edited the icon for example so he might say um you know I don't know I needs to have a home or you know tall home um and at least uh it'll go off and you know create new ones for him um and um uh and he could rename it and he could pick new um you know you could pick uh new fonts and new colors and things like that so you know if he wanted to say this is the one I'd like then or you know you could go do that um it's obviously got something in it around kind of mountains and things and so he could do that he can also go and say yeah that's not quite the way I want to like pitch this and so we have this kind of elevator pitch version of it which is actually a lot of what was generated as the underpinning of the whole um deck and so we do that anyway so he could do that and then he make his saves and then he regenerates everything um from there a couple things will happen one is um he does make a small payment here um and then as soon as he's done that um we do a few things the first is that we we do make him a landing page what is the small payment just like he makes a $30 payment um in this case to uh to basically move on to the next step okay um which is gathering customer feedback which is basically a set exactly right it's a set of tools to allow you to start to talk to your customers and so there's they're really um two sides of that the first is um to talk to to set yourself up I should say to talk to strangers and so we do this now it's a little bit actually inverted in order but we do it basically because I think this feels very real to people to have like a website created so in addition to having had his um deck created this is a website that was made for him where it took obviously a lot of the assets and the copy and other kind of Concepts from the slides and it it made it a deck it it does go on in the conversation by the way in the next set of conversation It'll ask him like okay well let's find a a URL for a domain for this and so it did go by this domain and register this domain for him um so that's kind of like one part of it uh the second part of it is that we will also um well actually there's there's two sides of that so one is that then actually what he also gets is his own um GPT and so imagine that he can start acquiring uh leads just as we acquired him he can now start to acquire leads into a conversational experience uh that will um that will chat to his customers and can both kind of like use a conversational model to qualify them much as we are doing with you know our customers but also to begin to like sell them on the different parts of the product and the experience that he's envisioning and so the kind of website plus the this hosted GPT that we've created for him is really part of and then a set of assets that we create to help him go run an ad campaign are uh are like the part of how you go get strangers um before we do that uh and and again it's inverted only in the presentation here because of uh two things one is I happened to pick a demo that's a few weeks old uh but second of all it is it is kind of like feels more like something you want to buy to buy these external facing assets and then we back you into the the hard work or a slightly harder bit of work that you need to do for yourself which is that we ask him um to go off and interview himself yeah basically to complete an interview from the perspective of the of the customer um and um and also to and then we also ask him to share this with a few of his friends and and so what this is is a um is something that more like orients towards collecting feedback from the people you already know who might be potential customers of this product um before you go into the business of like talking to strangers and this is a voice um you know oriented chat uh that goes through basically the need finding kind of Playbook that you might be taught if you go to the D school at Stanford or something like that and you're trying to kind of really get into what's the problem and so here I might say um you know yes I I fit that profile um I am trying to buy a new home um and and so this will um initiate a conversation uh between me and the um and the GPT and and then lastly it will actually take every one of these conversations that uh I have and it will with my or that the that the GPT has with um my friends let's call it and it'll synthesize them into a basically a product road map so it'll use these conversations to help kind of identify what are the key features of this potential product and then to play them back to and organize them in a dashboard this is this is truly wild like I knew you had a lot of AI stuff but this is a lot more than I expected this is great like can we because okay so there's this sort of like end to endend Pro process of like start with a couple questions to a deck to a uh like a website to a little wizard that can like help you like modify a couple different things to a like customer interview thing that will uh you know you get a bunch of interviews and then it will create a product road map to like running ad campaigns run some Camp quir I mean that's that's freaking crazy can you just can we I I want to move into like how this all works like how do you build this how do you make the like crazy mashup of models that makes this possible because like I've built a lot of this stuff before and like it's really hard to get it to work well enough to do stuff like this and I'm just super curious to understand um how you're actually doing it how is it architected I hope you're not tired of all the AI because unfortunately the answer to it is that we use a lot of AI to make why did I know that was coming that actually what that kind of came up in our in our in our pre-c conversation that I that was you know as with many things when you when you start talking to someone about them or you hold them at a little bit of distance you you kind of realize about yourself is you know you asked and I think your normal like production Doc is to talk about how do you GP how do i chat GPT like the way I chat GPT is to make this and um I think it's probably relevant to say a I've never taken a computer science class in my life I don't know anything about computer science I've never prior to chat gbt I never particularly programmed anything maybe I'd like messed around in a Jupiter notebook and you know done some like data science or whatever you want to call that uh which is really just like a glorified way of running longer Excel functions on you know bigger data sets than Excel could handle right um so I was basically taking whatever Financial learning I had and and applying it to a bigger data set so chat GPT has been completely like um you know revolutionizing to me of being able to run you know write code and and I for like programmers I know that what I create is not you know per se code but does function it does work and it does deliver a result and therefore code TS to be code you know um so I've WR written I've generated many many more lines of code in the last you know year and a half than than I'd ever generated in my whole life combined um and that's because I just think it's magical that you can say like this is what I kind of want to do can you like write me the first version of a script and then you can plug that script in and run it and then just paste the error message and slowly but surely if you're patient enough you can get there and so basically everything you're looking at so far uh absent the customer interviewing stuff uh was stuff that I prototyped by talking to chat GPT um it's been productionize but I have I for sure most of that like processes the system design certainly and and some of even like the scripting concepts are very much still there and so I think maybe what we can do is just look at one of the new features that we're creating um or or one of the things we're trying to prototype which is to um make the the launching of those custom gpts so you're a customer you come in we want to be able to have you have your AI co-pilot that you can use to talk to your customers as quickly as possible currently it does still require some manual work but we are I am in the process right now of prototyping that in my prototyping framework um so that I can then hand it to the real engineers and have them once it's working and say hey can you please make this and so if it makes sense we can just go do that right now let's do that I want to see it let's go it'll use me it'll it'll be a productive period for me um okay so like just to this is a very typical thing that I would spend a lot of time doing in um in chat GPT uh which is you'll see here I've basically just copied and pasted a script that I have running in this case in an a table where I do a lot of my work because it's like the most intuitive combination for me of like a you know a database that I can write to and read from but that like I can also provide anyone access to and they have kind of like you know gooey I just wish that air table would if anyone from Air table is listening if you could please extend the Timeout on a script Beyond 30 seconds I would no longer have to use Google Cloud functions that would be great thank you um um but um and so I I do stuff where I like paste this whole thing and I just say hey this is what I want to change can you change that and so you paste this whole thing and like it'll it'll actually go and write the response and fix it and do whatever and so IIT yes okay um like frame this up for me a little bit like at the top so tell me about like where yeah so I will let me just go into an error table quickly so I can give you even more even more context one um all right so the job that we need to do right now we you you me and dpri um is to um is to do the following which is we are going to take um I I have two jobs to do really one is one is that in order to do this the way that we've like specked out this system so let's just talk you and like um the uh we need to One update a DNS record for this person's website by API in order to have it point to the server where we're hosting these gpts for folks so that's so one part of the job is to uh create a new subdomain for them which let's just say is going to be until they ask us otherwise GPT doom.com so we've we've bought the domain and and registered it we it is on our register we have we have API access to it so one little job to do is to go off and call the DNS simple API to update the the DNS records to take the subdomain and point it at our IP address um the second thing to do is we have to make for each one of these we have to make an air table uh we could do anything but it's a database in this case that we provide to the entrepreneur so that they have an easy way of seeing for example who is who are the people that are coming and talking to my GPT where is that information being saved can I see the chat history and air table is at least like the place where we've decided to do that for the moment where because it's it's easy if we send them a link they go in they have their own it's their own little CR protoc CRM if you will that's starting to be populated for them uh but to do that we have to automatic like if we really want it to be automated we have to automatically generate uh a new air table and it has to have columns that match to what the gpt's instructions are in terms of how what information it's looking to collect so let's say you and I went through this and we were creating one or let's stick to our guy Alex he wants to collect information about do you own a home or or not um have you saved it all for your home if so in what format how much have you saved well so to make it automatic we have to have a GPT that has those instructions to look for that information we have to have it have defined the schema of the of the database that it's going to write to and we have to then create that database to match that schema so that it all functions properly and so I don't know how to do any of those things other than if I ask chat GPT to help me you know um so what you are seeing there in this case is um uh let me just go back to my so like for example what I was working on right there when I pulled up my chat GPT screen let's just expand this a little bit um was a script that chat GPT wrote obviously duh um wherein we we Define um the what a like we are going to create a new air table base and so this is a database schema writing uh let's just find the instructions because basically uh that's that will tell you what it does um I'm not even giving it instructions right now because I give it this very detailed um function call but what what you'll this is just a bunch of code that says this is we're going to make a table with an air table you got to give it a name you have to give it a this you have to give it a that and then what you'll see here is that it responded when I tested this with a long um thing that set up a new table for this concept Echelon with a with a table inside of the base called leads and with a couple different columns they need a name and a phone number and these different things um and so what I was doing right there in chat gbt was just I I needed to update it because we actually need two tables uh inside of our air table base um let's go to the actual air table that we're going to make make um I needed one of them to be called leads where we were going to save that information and then I need another one to be called chats where we're where we save just the the raw content of the chat um and it's not doing the second part yet and so what I asked it to do here is I said I'd like to create the Json schema to provide for the creation of a second table in each base that like and again this makes no sense to you I I can barely even spit this out but obviously chat GPT is magical because it like it it actually understands this and then gives me the correct answer right so I said the second table should be called chats and it should have two columns uh of the type single line text chat ID and chat and then I literally just pasted I took this whole thing I copied it I pasted it in here you can see that it's kind of like not nicely formatted Etc and then open AI is nice enough to say okay like to do that we need to do the following and here is the modified portion of your script that would allow you to do that this and it's pretty close by the way I'm lazy enough to say hey instead of like here it it it said like go ahead and reproduce the part that's already in here my programming is sufficiently bad that I like would be nervous to do this and that I'd mess up the the um you know the the uh spacing and things like that and so I just ask it to redo it and it does the whole thing for me and then I'll just go paste that back in here and try it and it'll probably throw an error and then I copy paste the error back in here and probably within two backs and forths like we'll have have a correct answer and then I move on I mean I love it I that's it's amazing like okay I'm kind of curious about like if you're not really totally understanding what's going on how are you guiding yourself through whether chat gbt is doing the right thing is it just sort of like you check it and if it seems to work it works or like what are the I think I think I've obviously gotten like a slightly better you know sense of this now that I've done it a lot right like I I'm sure that I'm I I do try to read I'm not gonna say that I'm like trying to teach myself how to do these things I don't I don't see it ever being a productive use of my time to start with a blank sheet of paper or a blank sheet of screen and and start writing to it that doesn't that's just not like where I'm gonna you know spend my time um but to the extent that you know I want something generated quickly um it feels like it's it's pretty good at it and and I can once you've made the mistake a few times um you can tend to be pretty like smart about what the mistake is that you're making and and try not to make it again and so in that case for example I know that if I took that code which I hadn't if I hadn't read it I I know for sure they they try to like excerpt something because it's trying to not generate too many tokens and whatever and so it it like comments out like a section and it's like hey just plug that section in there and I've always like well I'm not I I think I know what section you want in there but I'm not positive and it will take me more time to go do that than just to burn more tokens so can you go do it um I think that's probably the main thing the second thing is it's so good at like you know I was when I was preparing I like my process is really probably a three-step process one is try to come up with what's the output that you want chat GPT to create so in this case obviously it's like a it's code but it could be when we were building the initial part of our system it's like um imagine that you just want to we had to come up with a color palette for the slides right or for the brand of this thing well like what is the color palette of a of a given you know new idea and how would you come to that and so we I spent a bunch of time with chat PD just going back and forth like um if I tell you this like then can you propose a color palette and then and then I'd have to say oh well you know and and lone Bal it's pretty good at actually you could say to chat GPT um give me neon volt yellow Allah the Nike brand in HEX no problem gives you the correct answer or something very close to it so like one of these amazing things where like I have no idea what the heximal notation of volt yellow is I know how to like pick it on a Color Picker but I don't know how to like you know like I would never generate off the top of my head so it has no problem in this like weird space between natural language and and code or versions of like you know machine readable information and so anyway so I would basically go through a process say hey can you make a color palette oh well basically it needs to describe it first and then I need to get it translated to heximal you know um notation and then I need to into adjacent object and so finally I would arrive at this instructions set that's basically like your job is to take the following input and turn it into the following Json object which has a text based description of the color palette as well as three you know hexadecimal references of to like what the color is and then I'm going to take that and I'm G to do something else with it you know and so then you would basically like now let's say that you need to go make a logo with those colors okay well now you got to co call a new API I'd often just go copy and paste like huge chunks of open of of API documentation from some random service that I found to do some job right and I would paste it in and I'd say you know how how do I make a proper how do I format a call to this um API if I know that I need to provide it these things and then it would do that and then finally I would say okay now write me a script that I can run an a table for example that would allow me to do that when something else happens assume that I can take care of the Automation and so we do a lot of that kind of stuff that's really interesting so I guess if I to summarize like how this is all working is air table is sort of like like a core thing where it's like the it's the source of truth it's the database that you can um people can interact with you can interact with it um your customers can interact with it and and and it's like this this the first building block and then um air table has these automations these scripts that can run based on different actions that that happen so if someone adds a record or if someone something changed like it can it can launch a script and what you're doing is you're using chbt to basically build whatever that automation is to to to program like okay uh someone fills out a form um and it goes into the air table we send them an email saying you need to pay or whatever and chat gbt is writing the script and then helping you connect to thirdparty services that are like other building blocks that you might have like stripe or like any of these other things so you're kind of like it's sort of like um and that's certainly how prototype things and then obviously if once something is being done enough times then we'll move it into it like and we run our main system now on superbase but it has a very similar um set of features in terms of a DB with these Edge functions which are not dissimilar from the script running capabilities of air table so air table to me is like the lightweight place that either I as a novice or our customers can hang out and then we can productionize things over time yeah right okay no I mean that makes perfect sense like and I think it's such an interesting model for people who are thinking about like okay how do I um H how do I get started with this stuff how do I prototype stuff it's like uh an air table with chaty BT is sort of the glue that connects you to all these other third-party services that can be like it's like Lego you're stacking Lego bricks together and then you have something that functions and once it functions then you can be like okay maybe I should hand this off to like a professional developer that can actually to like do that or you know and also I think it puts a lot of pressure on like what the delivery model is I mean chat I think has done a great favor to entrepreneurs and people trying to build projects and certainly something that we are leveraging for our you know for our customers um which is that like you know you and I know that the minute that you start trying to design UI and do wireframes of like new Services the minute that a gooey is involved I mean you slow your pace of development down massively right like on silly stuff not silly but like important stuff like oh where's the forget password button and what does what does your forget password experience look like and oh well actually maybe we should just do two factors so we don't even have to have a well how does that like what does the screen look like if someone where does the button go to to request a a new code um like you've just wasted like days out a time on not even you haven't even gotten past the login and you're and you're back and forth with stuff you know um so I think what what resonates with me about what you played back is like yeah if you can get something functioning you can also often like make the hard decisions about do I really need that goey to like you know put present that or could I just put it in a text message to my client or whatever and then is the service just something that kind of runs in the background for them but delivers them this thing and if it is something that I need to deliver is there some really like lightweight away for me to do it so I think it is a really empowering thing to have this little yeah combination of a database that you can Implement you know play with in the form of air table but also this has this kind of scripting layer on it which chat GPT is just so good at writing these scripts you know like it's just logical that they exist all over the internet and it's pretty good at at Crea I love it I love it that makes a ton of sense um so I I'm I'm obligated to ask this but you don't have to answer it if you don't want to but because it's on the screen it's sort of my professional responsibility to ask you what AI co-pilot MLM strategy is oh I was looking at um well when we were talking about like how to well let me just find it I mean I don't know that we took it that far um or you know we're we'll see um but that was a good example I was trying to come up with I think it's it's higher up in the thing but you didn't I can't believe you didn't ask about panther versus Greywolf that was coming next I'm gonna start with panther versus Greywolf because because I'm gonna try to make a slightly more meta Point um what what what this is obviously something I do with my son um my five-year-old son is like obsessed with animals and uh we we we run this game at infinitum and I am so grateful to chat GPT for for this because I've saved a lot of money on these books that you can buy on Amazon that compare random animals but that fail the next test which is like obviously he reads the great white shark versus Orca book that's been published but then he's like what if a Orca fought a you know a sperm whale and you're like oh well they don't have that book you know um and so Chachi is great at this I have realized that and in just preparing to talk to you that a lot of the way that I kind of if if what we just have discussed a lot is how I work with chat PT a lot of the way I think with chat PT is to try to basically say I'm thinking about the two things and I'd like you to talk like I'd like to kind of go through a dialectic with you where we Define them or we list the pros and cons of them independently and then where we like crash them together and merge them and and whatever and um I think that like honestly it's it's in my own review it's a way that chat gbt I feel does a lot more for you than if you just go into this like linear conversation where you say I'm thinking about X and like it it almost has no frame of reference for like what the Opposites in fact sometimes it'll ask you like what are the what are the Alternatives um and so I just try to like start with it also because if you give it to kind of like almost seemingly very you know um distant things um it it takes you seriously it doesn't tend to say like why would you ever compare Ai and an MLM strategy like it it it tends to take it like it takes it seriously and so it tries to then do the work and and it's like work that often I don't think I'd have the discipline to do alone even if I could say oh well like I should really spend 30 minutes like going through what's what makes for an MLM strategy and what are the characteristics of it and how would you merge that with a you know this thought process and whatever and so um yeah I mean I think in this case like all that uh well panther versus grey wolf like what I mean we gotta oh panther versus grey wolf I think they're form predor let's see the outcome uh considering the Panthers greater size strength and lethal Ambush tactics it might my son would be very happy for this he's a uh he's a feline over K9 with this um interesting I I mean in this case we just I just did a thing where i' like asked it to um I mean this in this case I don't think I did the kind of dual model although I can I were we to go through this again I I would definitely do this because I have some Alternatives in mind but I was basically just trying to think about you know in our case obviously we've had people who are trying to uh refer our product to other entrepreneurs in their Network and asked us you know do we have like referral codes and things like that and so um I was just trying to kind of like imagine is there a way are there any versions like an MLM that are not um you know like too mean or or or exploitative and if so like what yeah like what what would be the um you know what would be the way that you would like think about that um interesting and TBT is not gonna judge you for asking that question but someone else might for asking that question and in fact again to the point like takes it quite seriously and tries to like go into you know these different mechanics and um and then I think you have the ability therefore you know if you if you kind of take this in Earnest to um I actually in this case obviously didn't follow up but what I would normally do here is say things like okay well you know I'm really most interested let's just say um you know uh I'm most interested in the downline concept and how that would you know work for me I might even say things like um what what does the typical downline uh agreement look like for a MLM participant and can we draft one and I guess I I do stuff like that where I I just try to like be way more uh result oriented way faster than I would normally be to because it can often you know do such a good job of creating the thing and then I I find that that helps like imagine you know the output but um I love it I I'm just thinking about I'm just have that that video of you know Jim from the office and he's like drawing the like pyramid thing and then he's like going like this I mean you know I don't know I suffice to say given that I didn't have a particularly in-depth conversation with Chachi I'm not sure how far this thought process will go but no I think it's I think it's I think it's really at least at least now I have my downline agreement that I can use if necessary I'm uh you know if you need you need your your first uh customer let know my first mega you know and and just to be really uh it's a full circle uh we had a couple of mlms issuing digital badges on our badge issuing platform they were they were the social media cred dour in 2013 for uh for women in particular who are interested in flexing their MLM muscle I love that um cool well we're we're getting pretty close to uh to our time and uh I just I want to kind of like back up and and talk about what we've talked about and and leave people with um a message and also like Point them and direct them toward what you're doing to to Autos to the book you're writing all that kind of stuff so I mean I think like at a high level what I'm what I'm observing is you have this like you have this business that you've run for 10 years helping entrepreneurs start companies and then you have created a system that effectively scales this like non-scalable business using like 50 different AI tools that you've built yourself using AI um and you've basically abstracted yourself away from that process and created this thing that a person with a couple chat messages can create a pitch deck a landing page can start recruiting customers like all that kind of stuff which I think is like totally wild and really interesting I don't think I've ever seen someone use AI so extensively um both in the sort of prototyping of the product and in the like actual product that they they make like like um weaving together all these different microservices that you built basically is I think is really cool and and for anyone who's like wanting to build a product like this is a model I think especially if you're not technical that is like a really good way to get started um yeah what do you think um what do you think of that summary are there other things you want to like leave people with um yeah I think it's well well summarized um I think AI can be a force for you know pushing entrepreneurship to new heights and I think um and I guess I use the word entrepreneurship and other people might use creativity or um productivity or you know the different things but I guess I use it as making something in service of someone else um and I just think that um and I've lived that now um for a couple years just from from wanting to do more of what we do to serve our customers um but I think everyone you know will get a a whiff of it not to be like overly dramatic I think we kind of need it I think a that is like bad for entrepreneurship I.E ones where people just like use the big models and and Outsource you know parts of their life Etc as opposed to kind of um yeah like that's a very scary thing in my view uh whereas so so I'm kind of committed to this but I but yeah I think that I think it's possible I think it can be like just an amazing Force multiplier for people's you know how people Express themselves entrepreneurially speaking and so um if anyone I guess I'd say as like a call to arms or whatever is like broadly interested in this stuff like I'm I'm here and and want to chat with anybody yeah no I mean I love that like it's I love this as a tool for kind of creative expression for making things and I think that's exactly what you're what you're building for yourself and for other people and I I really I really I really love it um where should people who are interested in and connecting with you or or using Autos or reading your book like where should they find you yeah um going to launch our book next month or so um that's me my customer and AI in which most of any of this thought process will be kind of documented worst case scenario um I think like you know I have a very uh I can't say I post much on Twitter but I will definitely post our our book um so I'm Thorn NY on Twitter you go to autos.com and it'll redirect you to our Instagram um place if you want to get started there um you know Dan's got my phone number so if you've got Dan's phone number he can give you mine great but I'm also Nicholas I'm also Nicholas ni preh hype.com and and um I'm pretty good at at doing that too so whatever works and um thank you for hanging out Dan as always it's fun to uh you know share some of the stuff with you this was a pleasure um really really fun to spend time together um and uh I'm excited to see where it goes me too that's every day there's something new so that's the fun part for sure oh my gosh folks you absolutely positively have to smash that like button and subscribe to how do you use chat GPT 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