Podcast episode (AI and I, Ep. 44) with Kieran Klaassen and Brandon Gell of Every about building Cora, an AI-powered email client. Kieran built Cora in about three months and shipped the original MVP in a single day; nearly 10,000 people joined the waitlist. Topics include how he built the product with Cursor and OpenAI's o1/o1 Pro, the story of the overnight MVP, lessons from onboarding new users daily, why software is becoming content and why products with a point of view win, how Kieran approaches building new products, best practices for using Cursor (including a live demo building a copy editor), and the future of Cora and Every. # Channel Identity Observations — "He Built an AI App With 10,000 Signups in 1 Month - Ep. 44" ## Explicit Self-Description Evidence ### Show Identity - The host references the show by name: **"AI and I"** — the closing segment says: *"smash that like button and subscribe to Ai and I."* - The host is identified by name multiple times: guests greet him as **Dan** (Dan Shipper), and the outro names him: *"with Dan shipper as the captain of the spaceship."* - Episode numbering convention: the title contains **"Ep. 44"**, indicating a long-running series. ### Host's Organization and Role - Dan describes Every, the company behind the show, as: > "we're a media company full of writers and editors who care a lot about language" - He describes the company structure: > "we get to take people along in our journey to build these businesses which are... a new generation of business under a new kind of structure we have multiple different products multiple different businesses Under One Roof" ### Recurring-Guest Framing - The host explicitly labels a guest as returning: *"Brandon you're now the top recurring guest on AI and I so people should be uh familiar with who you are."* This demonstrates the channel treats guests as a recurring cast familiar to its audience. ## Claimed Scope - The show positions itself around **AI-assisted building and entrepreneurship**, evidenced by the outro: *"pure unadulterated knowledge bombs about chat GPT"* and *"a journey into the future."* - Content scope demonstrated by this episode covers: - **AI coding workflows** (Cursor Composer, Windsurf, o1/o1 Pro, Claude Sonnet, Whisper, real-time API) - **Product-building philosophy** (PRDs, prompt engineering, allocation economy thesis) - **Internal company transparency** — discussing Every's own product Kora, its waitlist ("7,000 people"), onboarding process, and strategy debates on-air ## Intended Audience (Observable Evidence) - **Aspiring AI-assisted builders**: Kieran's anecdote addresses people hesitant to build: *"I hear it so many times... 'yeah but I'm not too Technical'... just try it just download composer."* - **Every subscribers**: an explicit audience segment is addressed at the end: *"if you are every subscriber... you get early access to Kora... you get access to all the other products we make and all the writing."* - **People interested in AI industry analysis**: extended discussion of OpenAI/Microsoft deal terms, AGI timelines, and AI hype cycles ("every AI wave... when they first started working on AI in the 50s"). ## Demonstrated Presentation Patterns (vs. Claims) - **Transparent founder-style content**: the host states the value of bringing the audience into the building process: *"the more we can bring people into that process of figuring things out the better"* — and the episode demonstrates this via candid strategy debates. - **Interactive/live demonstration format**: mid-episode, the host sends a draft essay to the guest and they test Cursor copy-editing in real time: *"can we try this can we try this together like I I really want to see this."* - **Host as active participant, not neutral interviewer**: Dan discloses he is an insider at Every and a user of the products discussed, e.g., *"this is what my email inbox looks like."* - **Conversational, promotional outro style**: the closing segment is high-energy and hyperbolic (*"you absolutely positively have to smash that like button"*), suggesting an intentional engagement-driving presentation. ## Uncertainty Notes - No curated metadata was supplied; observations rest solely on title and transcript. - The title's "10,000 Signups" figure is **not confirmed in the transcript**, which cites a "7,000 people" waitlist — a discrepancy between the packaging claim and demonstrated evidence. # Delivery Observation: "He Built an AI App With 10,000 Signups in 1 Month — Ep. 44" ## Speakers & Roles - **Dan Shipper** — host; drives questions, recaps guest answers, ties topics back to product strategy. - **Kieran Klaassen** — guest; GM of Kora; explains his building process and demos Cursor live. - **Brandon Gell** — recurring guest; adds context about Every and onboarding work. --- ## Tone & Register - **Conversational, expletive-casual**: multiple instances of uncensored language — "holy [ __ ]", "we had functioning V1 of Kora in a day", "make it so [ __ ] good at the one thing". - **Enthusiastic and affirming**: Dan repeatedly validates guests: "I think Kieran you nailed it", "if this works I'm gonna be so happy", "I love that so". - **Excitement markers cluster around demos and speed of building**: "It's kind of wild how much detail you're able to give", "this like changes a lot". ## Vocabulary & Recurring Terms - **AI-tool naming is constant**: Cursor / Composer, o1 / o1 Pro, Claude Sonnet, Windsurf, Whisper, Supabase, Notepads, `.cursorrules`. - **Recurring conceptual pairings**: - "taste and vision and experience and creativity" - "software becoming a little bit more like content" / "writing becoming a little bit more like coding" - "allocation economy" vs "knowledge economy" - **Kieran's metaphor habit** — he explains technical ideas through analogy: - Software as music: "software is very similar like what you try to do is tell a story" - AI as colleague: "it's really a collaborator just enabling me to do things faster" - Unclear specs cause failures: "if I don't understand all those aspects it's very hard for a cursor to do the right thing... sometimes it goes Rogue" ## Teaching & Communication Habits - **Live demonstration as a teaching device**: A significant mid-episode segment is an unscripted Cursor demo — Dan sends a draft essay, Kieran drops it into the project and applies the Every style guide live. Narration habit: "so for people who are watching / who are listening…", repeated at least four times. - **Process walkthroughs in numbered/staged steps**: Kieran describes his build pipeline as explicit stages: walk → voice memo → transcribe → LLM → PRD → Cursor. > "I just start building a prompt in my head... start working on it more and converting this into a PRD in cursor" - **Reframing questions back to first principles**: Dan often converts specifics into general theses, e.g. "how do you know when to check the work of the model... we're moving from knowledge economy to an allocation economy". - **Self-deprecating asides from Brandon**: "I'm too lazy often to think about what the architecture should be", "I don't even read the errors when I get an error". - **Closing back to product**: Dan steers tangents back to Kora explicitly: "yeah I think to bring it back to to Kora". ## Recurring Phrases & Filler Patterns - **Heavy "like" density** across all speakers, especially mid-explanation. - **Kieran's repetition clusters for emphasis**: "and and and", "it it it", "we we we" — visible in the transcript at points of excitement. - **Filler hedging**: "um", "uh", "or whatever", "that kind of stuff" appear throughout, consistent with unscripted podcast speech. - **"Kind of / sort of" as softeners**: "it's kind of like having chat gpt in your in your cursor", "I can just sort of scroll through". ## Structural Patterns - **Cold-open teaser**: the episode begins with excerpts replayed later verbatim (the Kora inbox scroll-through and the "V1 in a day" anecdote appear twice) — a clear editorial choice. - **Host-led topic pivots**: Dan uses explicit transition formulas — "I do want to go back though to", "my last question for this is", "we're getting close to time and so I just want to like take it back to". - **Question → anecdote → generalized lesson** is Dan's recurring interview loop; Kieran answers with stories (the friend who started building apps after one instruction session). ## Uncertainty Notes - Individual speaker attribution is reliable in most exchanges, but some overlapping rapid exchanges (e.g., around the model-choice discussion near [1509]–[1520]) are hard to attribute with confidence. - The outro ("smash that like button... I'm absolutely hopelessly in love with you") is tonally abrupt versus the rest — possibly a scripted/comedic insert; the transcript alone cannot confirm whether it's ironic. # Observation Document: AI & I Ep. 44 — Kieran Klaassen & Brandon Gell on Building Kora ## Speakers - **Dan Shipper** — host, AI & I (Every) - **Kieran Klaassen** — GM of Kora (first appearance on AI & I) - **Brandon Gell** — Head of Studio and Consulting at Every (recurring guest) ## What Kora Is ### Kieran Klaassen (GM, Kora) - Kora solves the **dread of email**: "we take away 90% of your email from your inbox and brief it twice a day." - Two daily moments where the user reads through briefs and bottom lines instead of archiving emails one by one. - Wears an "anti-email" hat; positions himself against the inbox experience. - **History/arc**: They started as an email-drafting assistant like "hundreds of products out there." They found even great LLM drafts fail for ~50% of emails needing response because the model lacks the user's context. Kora now only drafts emails it judges it can do well. - **Reframed insight**: The real cognitive load is *managing and cleaning* the inbox, not responding — "responding to emails is kind of like the pleasurable part." ### Dan Shipper (product demo) - Kora lets him scroll through summarized newsletters, partnership updates, lawyer agreements, promotions, spending — then "when I'm done, I'm done." No archiving needed; "return to inbox" available. - "It saves a ton of time" and deals with the dread feeling; "it's a pleasure to use." - Built internally at Every; launched as waitlist product before the holidays; went viral; ~7,000 on waitlist with onboarding underway. ## The Build: Speed and Process ### Kieran Klaassen - Built end-to-end in ~3 months; **MVP built overnight** after a call with Brandon: walked home, voice-recorded a ~58-minute prompt on his phone, transcribed it, built that night, emailed Brandon. - **Percentage of code written by AI**: "I think everything is written by AI or maybe 80% or 90%, but 100% has been thought of by me." AI as **collaborator** speeding up tedious work. - Background: composer/film musician for 8 years; sees software like music — "you create an experience... tell a story" — rather than purely an engineer's problem-solving view. - **Walking-prompt process**: walks to reach flow state, builds the prompt in his head by visualizing the app ("I'm opening my phone and just imagine it and just talk through what happens"), including visual detail (four-way gradients, grainy texture, "apple design"), self-correcting mid-ramble, until "my brain is empty." - Transcription via voice memos → MacWhisper (or iOS 18 native transcription); then into an LLM to convert to a **PRD**, sometimes a notebook/file outline, then builds in Cursor. ### Dan Shipper & Brandon Gell (on the overnight build) - Dan bet Kieran would "have something by the morning" — "not something we could ever imagine a year ago, two years ago." They woke to "a functioning V1 of Kora in a day." ### Dan Shipper on prompt engineering - Claims of prompt engineering's death apply only to incentive-style prompting ("I'll pay you $10,000"); detailed specification of desired app behavior and styling "is not going away... that is prompt engineering." ## Tools and Workflow Details ### Model choices - **Kieran**: "always trying to use the best model... currently that's o1 Pro." Also praises Claude Sonnet — "there are no bad models anymore." Uses o1 Pro for planning, coding when he knows what he wants, strategy, bouncing ideas. Embraces its slowness: "it makes me chill a little bit." **Never looks at the thought process**. - **Dan**: main model is o1; o1 Pro feels "Galaxy brained"/slow; uses it to untangle loops in Windsurf/Cursor Composer and to review code ("is it actually doing what I think it's doing"). - **Brandon**: primarily o1; can't use Claude because it's unavailable in Nicaragua ("I have no idea why"). ### Cursor practices (Kieran) - Main tool: **Cursor Composer**; uses known technology stack (Ruby on Rails, HTML — 15–16 years' experience) so he can judge output. - **Where things go wrong**: not the code, but unclear ideas — "if cursor writes code that is not good, it just means it's not clear what it should do." Example: defining email model states. - Uses **`.cursor/rules`** file, updated from observed failures (e.g., controller helpers); sometimes references Every's style guide so Composer can copy edit app copy. - Explains **notepads** (injectable prompts/PRDs) vs. rules (always-on), and **agent vs. normal vs. chat** modes in Cursor. ### Live experiment: style-guide copy editing - Kieran applies Every's style guide to Dan's draft essay in Cursor. - Dan's assessment: first pass "missing things"; rule-by-rule application needs prompting. - **Dan's claim**: current LLMs are "not that good at taking a rule and applying it in every instance where it's violated"; only o1 is good at this, but o1 lacks tool calling in agent interfaces — "that's coming... this quarter... it'll totally change how this works." - Kieran demonstrates workaround: create a notepad instructing "go through the items one by one." ### Agents going off-track - When asked to create a promotional email, Cursor edited an existing template — Dan: "this is what we don't want... you have to keep your eye on your agents." Kieran corrected by editing the prompt ("create a new email"). ### Brandon on accessibility - Built a Spanish **verbal flashcard app** in ~3 prompts plus error handling; Google's audio API was "awful," switching to the real-time API. - Claims it's "still far underappreciated how easy it is for non-technical people... to make something real." - **Dan**: hosting/deployment is the hard part now, not code — agent deployment will enable "luxury software and one-time software." ### Kieran on non-programmers - Friend who said "I'm not too technical" built multiple apps within days of trying Composer — "it's in your head... just go do it." - **Dan**: "the limiting factor now is not knowledge, it's just patience." - **Brandon**: doesn't read errors — "my goal is to not understand this, my goal is to just build the thing." ## Themes About AI-Era Software ### Dan Shipper - **Allocation economy thesis**: shifting from a knowledge economy to one where compensation follows "how well you can allocate intelligence" — like managing people, deciding when to check work vs. delegate. - **Software as content / writing as coding**: cheap software makes *what* you build more important; products that "make you feel a thing" win when everyone can solve the problem. Strong perspectives (like Superhuman's "marking as done") can now be enforced via LLMs. - Big labs optimize verifiable step-by-step problems (coding, math); once solved, "how few problems in the world are actually like that" will become apparent — squishy problems needing taste, intuition, iteration remain. - AI hype cycles: every wave since the 1950s ("we'll get it done in a summer") predicted imminent breakthrough; progress reveals new peaks — his **Angel's Landing "false peak" anecdote**. ### Kieran Klaassen - On completion: "completion State doesn't exist" for building a company/product — "embrace the suck," "type two fun." - On prioritization: an alternative framing — ask "what works very well and what can we make even better... be very good at one thing because then it will forgive you for the rest." ### Brandon Gell - **Founder bias risk**: "we just have a bias to use the products that we make" and may convince ourselves problems aren't real. Manual onboarding surfaces real user concerns — e.g., some onboarded users worry about Kora archiving important emails; the team doesn't feel that problem but can't tell if they're rationalizing. - OpenAI/Microsoft aside: their deal reportedly defines AGI via a $100B product revenue threshold — "best negotiation for Microsoft"; complex utopian business structures often lose to regular ones. - Whiteboard visual: AI as a small blip slightly expanding the "circle of human knowledge" — doomer fears of no jobs/creativity overblown; AI "will just open the door to something else." ### Dan on Kora vs. AI-email doomers - With Kora, his inbox is "only humans"; AI summarizes the automated/marketing noise, "presenting all that other automated stuff... in a way that's more consumable." Kieran: "maybe Kora is the most human way to email." ## Open Questions / Unresolved Tensions (as expressed) - Are the team convincing themselves the archived-email problem isn't real? (Brandon: "an impossible question to answer.") - Is the current user base the ideal customer segment? Not enough data yet — Dan: "you just need more data... instead of two people, 30." - Feature parity vs. focus: Dan argues against racing Gmail to table stakes; aim to be 10x for one type of person. - AGI timing: Dan believes "by some definition" within one to two years, while also arguing each peak reveals more complexity. ## CTA (as stated) - Join the waitlist at **kora.computer**; Every subscribers get bumped off the 7,000-person waitlist and early access. # Speaker & Provenance Observation Record ## Video Metadata - **Title:** He Built an AI App With 10,000 Signups in 1 Month - Ep. 44 w/ Kieran Klaassen, Brandon Gell - **Video ID:** 01a0f15a-e854-72d2-8d24-2f421f002616 - **No curated metadata was supplied**; all facts below are drawn from the transcript only. ## Speakers & Roles | Speaker | Role (as stated in transcript) | Evidence | |---|---|---| | **Dan (Dan Shipper)** | **Host / creator**; references "this is AI and I" and "the show" | Introduced guests, conducted interview; addressed as "Dan" by guests; outro names "Dan Shipper as the captain of the spaceship" | | **Kieran Klaassen** | **Guest**; **GM of Kora** (first time on the show per host); founder/engineer of Kora; former composer/film musician | "you are the GM of Kora"; describes building Kora's MVP in one night | | **Brandon Gell** | **Guest (recurring)**; **Head of Studio and Consulting at Every**; conducting manual Kora onboarding | "you're the top recurring guest"; "you are the head of studio and Consulting at every" | | **Outro voice (unnamed)** | **Narrator/promotional announcer** | Final scripted like-and-subscribe segment addressed to "folks" | ## Products & Entities Referenced - **Kora** — Every's email product; discussed end to end; 7,000-person waitlist; built internally in ~3 months per guests. - **Every** — media company; multiple products "under one roof"; style guide referenced. - **Sparkle** — mentioned by host as a similar perspective-driven product. - **Superhuman** (email app), **Gmail**, **Cursor / Composer**, **Windsurf**, **Replit**, **Supabase**, **Figma**, **Whisper (Mac/voice memos)**, **Claude 3.5 Sonnet / Claude**, **OpenAI o1 / o1 Pro**, **OpenAI/Microsoft** deal, **Zion National Park (Angel's Landing)** — all referenced by speakers as third-party tools, events, or anecdotes. ## Third-Party Claims (attribution notes) - **OpenAI/Microsoft AGI clause:** Host relays a claim that the deal ends when OpenAI builds a product generating $100B, framed as "AGI = $100B" — speaker notes it as something he "guesses" saw; flagged as **unverified third-party claim by host**. - **AI history claims** (1950s optimism, hype cycles): host's personal reading, not a cited source. - **Claude unavailable in Nicaragua:** Brandon's first-person claim. ## Promotional Segments 🚩 - **Closing outro** ("smash that like button and subscribe...") — explicit channel promotion. - **Kora waitlist promotion**: "join the wait list core. computer"; **Every subscribers get bumped off the 7,000-person waitlist and early access to Kora and all Every products/writing** — explicit promotional offer. - Host states Kora launch "went really viral" — self-reported growth claim (provenance: speaker's own account). ## Availability Limits - **Comment availability:** not stated in transcript or metadata — **unknown**. - No curated metadata, timestamps, citations, or external source links supplied. instead of going And archiving those and reading them And archiving them one by one what I can do with Kora is I can just scroll through and be like okay like there's some partnership stuff going on with every I got an agreement from our lawyers like all that kind of stuff and I can just sort of scroll through um I can see the money that we' spent I can see all my newsletters summarized I scroll through it oh I can see all the promotions I got and then when I'm done I'm done so Kier I remember we got off a phone call and I was catching up with danad and he was like how long do you think it's going to take him to do a want and I was like I think he is going to have something by the morning and that's just like not something that we could ever imagine a year ago two years ago that you could possibly do that and you did and we woke up and we're like we had functioning V1 of Kora in a day your process is basically go take a walk like talk out a prompt get home transcribe the prompt and then get started but like give us more details into how that works cuz I want to selfishly I'm like how can I leverage this in my own process I wanted to make a music app that had a whole complex positional system but really what I do in A Moment Like This is I just start building a prompt in my head and then from there I go into my choice of llm for the moment and start working on it more and converting this into a PRD in cursor sometimes I add a like a notebook and I create like an outline of files or whatever I want to do after that I take it from there but it's a separate thing there's a lot of talk about how prompt engineering is dead or will die but being able to say like hey I want an app that does this and I want the background to look like this and I want the style of the button on the left hand side to look like this is actually um that's not going away and that is prompt engineering Kieran and Brandon welcome to the show thanks Dan thank you uh so Brandon you're now the top recurring guest on AI and I so people should be uh familiar with with who you are um but if if they're not you are the um head of studio and Consulting at every and Kieran uh this is your first time on a Andi and you are the GM of Kora um and yeah tell us a little bit about who you are and what Kora is yeah very excited to be on here um I'm been building Kora it's a product that solves the pain we're all feeling when we think about the word email hence my hat here anti- email I I wear a hat that says anti-il very largely printed on the front um we're trying to solve a problem that everyone is feeling uh when they're thinking and working in email which is a dread and no one feels like oh yeah let's open my email inbox with my 10,000 unread messages and let's go through or people that want stuff from me or random people that sent me stuff that I have to do now today and there has to be a better way that's like Dan and Brandon and I when we met we we all kind of felt it and we were like why the hell that no one solve this problem yet like why is Google not doing this why are they big like no one is doing this and we were playing with AI and we felt like there was something here so uh we started working Kora and uh it it it basically helps you reduce the stress you feel when you open your inbox because we take away 90% of your email from your inbox and brief it twice a day so there are two moments in the day where you can read through uh yeah read through everything that you need to know and read to bottom line of that and really focus on the important stuff that that's a very short version of it we do way more uh but would love to like get into more details uh yeah and hear other perspectives as well totally and and and for for context for people we we built this internally we launched it as a uh as a weight list product uh right before the holidays and it went it went really viral I'm like super I'm super proud of that launch I'm super proud of the product that we have and we're just starting to onboard people right now and try to figure out like how to make it work really well and I just want to give people a sense of like what does the product actually look like because I think I think it's I think it's very cool and I think it's it's a really good example of like the new types of things that you can do with AI that were like previously impossible like a couple years ago so this is the product this is what my email inbox looks like so basically um all of the emails that I get that I don't really have to respond to um so like you can think newsletters or any kind of email that I get where someone's saying like here here's like a status update or whatever instead of going And archiving those and reading them And archiving them one by one what I can do with Kora is I can just scroll through and be like okay like there's some partnership stuff going on with every I got uh I got an agreement from our lawyers like all that kind of stuff and I can just sort of scroll through um I can see you know the money that we' spent I can see all my newsletters summarized I scroll through it oh I can see all the promotions I got and then when I'm done I'm done um and I don't have to press archive I don't have to do anything like that if any of these things are something that I want to like uh actually see in my email inbox I can press return to inbox I can I can click uh and like read the full email if I want to but but basically for me it just like saves a ton of time um every day like going through my email I think I think Kieran you nailed it like it's it it it really um deals with that like Dread feeling and and for me it's sort of like a pleasure to use um but I think what's really important for people to understand is Kieran you like you built this end to end in like three months or something like that uh which is kind of crazy yeah and it's really fun as well like it's the best thing it's also like yes I build this in three months but also we were like feeling this idea already four months and we were thinking about this like it's in the air like we're we're not the only email tool long ing yeah I think it's I think it's worth like talking about the history of Kora for a second too because we actually didn't start here we didn't start with briefs we kind of started where everybody else is right now which is email assistant uh which there are like hundreds of products out there at this point that do that for you with all draft or emails um and we did that at first and we got really good drafts but I think what we realized is doesn't matter how good an llm can mimic your voice if it it's not in your brain so it doesn't have context that you have and it just can't write a good email for you period for like 50% of your emails that you need to respond to because 50% of your emails that you need to respond to you need additional context the LM doesn't have and um so cor does draft emails for you but it only drafts emails that it thinks that it can do a great job drafting or like you're going to have to edit very small amount and I feel like we actually throughout this process realized that the actual cognitive load is the stress that you feel about like managing your inbox not necessarily responding to emails because the responding to emails is kind of like the pleasurable part of emailing because it means you're maybe progressing something forward it's like the managing and cleaning of your inbox which is actually a majority of what we all do uh that is really stressful um so I feel like yeah there's been like an interesting Arc getting to where cor is today it has been an interesting Arc and I think that um we're starting to hit on something that I think is important for anyone who's thinking about building in AI right now which is um for a long time we've always talked about solving problems in software right but for a long time the most expensive thing was actually like building the software um and that's changing dramatically it's much much cheaper now and and what what that does is it makes the question of what you're building way more important because like you can build anything in a couple days if you want at least like a really rough version um and so going on that journey of uh okay we have an idea let's do Drafting and then oh wait drafting works but like we're actually spending a lot of time reading And archiving emails that like we don't need to respond to and like maybe maybe AI is better for that like that Arc is actually in some ways um it's getting more and more valuable to be able to do that than it is to like write the underlying code uh because a lot of the underlying code can be written for you um but I am curious like Kieran how are you able to make this so quickly um and like take us into a little bit of your process how much of it is just like you're I mean you are you've founded companies before you're you're a fantastic programmer um how much of it is that you're just a fantastic programmer and how much of it is uh you're using AI to like make you faster at this yeah it's a great question I I think it's everything together um it's really about really drilling down to understand what the problem is you're trying to solve and at the same time being super free in just doing \[ \_\_ \] like uh how we started like we started with drafts and and and Brandon and I were on the call and we were like oh yeah like hey hey uh I have an idea and we started suddenly let the sparkk lit and we were like oh yeah we should do this and this and this I was like it was buzzing in my head and I think I was walking back home and opened up my phone just memo recorder started speaking a large prompt I was already like okay um it's in my head like I have some idea of what we need to do and from my experience as programmer before I already were think was thinking about like how would I implement this with what technology would I use I would just talk it all out it's probably 58 minutes um and and convert it to text and um yeah go from there and and that night I think I built an MVP and sent an email said yo Brandon here it is send emails here and it will drop now for you yeah we were both like holy \[ \_\_ \] I remember so k i remember we got off a phone call and I was catching up with Dad and he was like how long do you think it's going to take him to do a V1 and I was like I think he is going to have something by the morning and that's just like not something that we could ever imagine you know a year ago two years ago that you could possibly do that and uh and you did and we woke up and we're like we had functioning V1 of Kora in a day um Kieran how much I don't even know if like how you'll answer this but how much of the code behind Kora which is a huge product now it does a lot was written by AI do you think what percentage Yeah I think it's a good question I think everything is written by AI or maybe 80% or 90% but 100% has been thought of by me so I think that's how how I think about it it's like AI helps me but it's really a collaborator just enabling me to do things faster the tedious things are just faster um so I I probably I didn't think about everything but uh and who does right most of it well what's amazing is like you're almost more of a writer now that knows how to program versus a a programmer absolutely yeah like for me this is very natural like a littleit background I'm a musician I studied composition I did film music for uh eight years did like uh conduct uh Orchestra and scoring and like the whole thing commercial music and for me software is very similar like what you try to do is tell a story um like with music you do that you support a film or like a short with music to make you feel a certain way and I think of it a similar way with software where you create an experience where it makes you feel or experience something or tell a story um and and that's kind of different than maybe like a problem solver like engineer kind of perspective which is like another way to look at it which is like hey I have I I'm going to program this thing I always think big too small and then I don't like don't really care really how it works like clearly I care about beautiful codes and things that looks good but if it works that's more important and if it's um solving the problem or telling a story or like making you feel something like that's the most amazing thing like if you build something that excites you as a user like that's that's positive energy uh and that's been something we've been talking about a lot here at every like in in the q1 sort of kickoff that I did we like we were talking about um software becoming a little bit more like content because it's like it's just much easier to write and it Al it also like um uh goes viral like a lot of our growth at every has been us releasing software products like Kora over the last couple months um and also writing becoming a little bit more like coding because because you can actually build stuff with your writing so there's this like merging and I think what you're pointing to is for a long time we thought a lot about software engineering as about problem solving like solving really really well- defined problems which is I think a great way to look at it and we think about that also like you know today we were debating um what problem you're solving with a particular on boarding feature and I think that's a really important lens um but I think being able to really crisply Define and um uh and resolve a problem is in a lot of ways a function of the fact that software has been really expensive to build and so you don't want to take a risk to to to build something that like doesn't actually solve a problem for someone and I think you're coming at it um from a different direction which I think is in general how we try to think about it at every uh because it's really compatible with with writing and and just creativ in general which is like making something that makes someone feel a thing which is a lot harder to Define um and and a lot of it has to come from sort of like taste and vision and experience and creativity and all that kind of stuff and I think software is moving in that direction more which is another way in which it's a lot more like content now is like yeah if anyone can build like a email summarizing tool or like an email response tool or whatever the one that makes you feel great is going to be the one that wins because the pro everyone can solve the problem um I think that's like a really interesting thing and it's one of the one of the most special things about every is I think we're all trying to do that yeah absolutely and what what is very interesting or about that concept is like it's more about uh good taste and style and just experience and like what you take with you like your perspective and and especially with with Kora like you see that like everyone on the team uh like brings their vision and it's a different kind of uh solution to email like we hear people say like there's no one else like this uh like it's different and that can be good that can be bad but we're very proud of that and sometimes we have discussions like oh should we make it a little bit like easier on the user here or like make it a little bit smoother and I'm like H maybe it's okay um to make make a statement or or do something a certain way uh especially to stand out and and that comes with that taste and uh yeah like kind of feel you get yeah I feel like a lot of what we build and a lot of what the most successful businesses are that I'm seeing right now that are being built using AI or leveraging AI they come from people or organizations that have really strong perspectives like sparkle is the same thing and Kora you know they're actually very similar it's we're applying a perspective that we have and it's not going to work for some people and it'll work great for some other people and um it's a perspective that only can be applied by hand in a previous world like how I organize my files that's like something that takes a certain level of intelligence to be able to do um only looking at my emails at 8: am and 3M that's something that like you need to force yourself to do um so having like a really really strong perspective right now feels or or methodology feels like for the first time you can actually force people to follow that methodology superhuman for email like kind of did this a little bit I remember when um I used it for the first time and instead of marking emails as unread you were marking them as done and that felt like the big unlock where you're actually saying I'm I'm archiving this Emil I don't want to see it in my inbox whatsoever and I think um yeah you it's just like amazing how much more you can do now that you can apply a intelligent perspective through llms yeah and I think that that's also another overlap with writing is like it's a writer's job to have a perspective um and uh and that's another way in which product I think product building is is starting starting to overlap I do want to go back though to Kieran you said you had this great anecdote of like building that first Kora MVP in in one night and you said like your process is basically go take a walk like talk out a prompt get home transcribe the The Prompt and then get started but like give us more details into how that works because I want to selfishly I'm like how can I leverage this in my own process because for example like one of one of my big questions is what is that prompt like what are you trying to especially let's say for a new a new project what are you trying to get into that and initial prompt as you're walking and talking that sets you up well can you find this prompt Kar that would be great I love that idea this is an example um of something I was thinking of um at some point walking somewhere so nor normally what I do uh is when there's a new model coming out like I think this was 01 uh coming out I want to make an app I want to build an app and I'll see how far I can push it uh how far it will go and where it breaks it's just a good good way to test it out so I was a composer and I wanted to make a music app that had a specific thing where you where you clicked somewhere and there's a synthesizer and a sound generator and like a a mirror note like a whole complex compositional system but really what I do in A Moment Like This is I just go walk and walking uh enables me to just like keep going like not thinking too much about it like getting more into a flow State um and just start building a prompt in my head it it's kind of weird like you're basically talking like it will become a prompt and this is something I actually I learned from you Den uh in earlier uh episodes where you said you need to ground it and like how to like push the model into a certain direction so I should start dropping like oh yeah you are a very good iOS engineer and you do like Swift Swift 18 you're amazing or like just start with something like that and it's a start and you like start grounding it um and here it's like I'm going to describe an app and its elements this app is called uh these if you open it there's only one screen uh well I just visualize the app here in my head and just do like I'm opening my phone and just imagine it and just talk through what happens so maybe every corner has a different color fourway gradient tones of green and blue a little bit of texture on it like a grainy noisy texture so it looks a little bit fancy like using words like fancy and maybe apple design like just describing the feel um that's the background then in the middle there's a separation there's a line in the middle somewhere in the middle and the line is actually it's not a line but is like two parts of gradients so you see I I was thinking about something I was like oh no no no scrap that let's go so I just Jem like that uh here you can see everything and until I don't know and and I try to just add details everywhere I can until my brain is empty and then I stop the recording and and I I don't take it anywhere directly from that that's just step one that's really interesting so for people are who are listening basically like um what you did is you went you went and took a walk you uh you you just rambled off the top of your head but the way that you're rambling is um you're actually it's it's kind of wild how much detail you're able to give about what you want um which I think is really actually important and interesting like there's a lot of talk about how prompt engineering is dead and I think like or or will die and I think what's what's important to know is maybe like the I'll pay you $10,000 if you do give me a good answer is like going to die because like you know that's the model should just give you a good answer no matter what um but being able to say like hey I want um I want the back I want an app that does this and I want the background to look like this and I want the style of the button on the left hand side to look like this is actually um that's not going away um and that's that is is prompt engineering and that is really really important being able to know that um and so it it seems like that's what you're doing is is you have a you have a vision in your head of what you want you're you're walking and talking in as much detail as possible and you're not really worrying about whether or not um you're getting it right as you say it because you just like walk back and say actually I don't want that it's it should be like this um and then it sounds like you're so you're transcribing what do you what was that screen you were showing me what what did you transcribe it in yeah this this so what I do is I use voice memos and then I put it into Mech whisper which is a free free just whisper converter but actually now voice memos does transcription as well with the new iOS 18 so I use that once in a while as well um yeah so yeah I'll just use that and then from there I go into my choice of llm for the for the moment and start working on it more and converting this to like into a PRD most most of the time I say hey okay I have this idea um in cursor sometimes I add a a like a a notebook um and I create like an outline of files or like depending on what it is like if it's simple uh incl is great for artifacts but whatever I want to do after that I take it from there but it's a separate thing like that initial burst of inspiration does not matter where it goes let me let's get into the details on that so basically um you have the initial burst of inspiration you write down the prompt you transcribe it what is the what is your model of choice right now to make it into a PRD and and and for people who are listening like what is a PRD like what are the what are the um elements that that uh make that effective for moving into coding yeah what I use now is uh I just always trying to use the best model there is the the model that thinks more the the longest and the deest and currently that's 0 on Pro um but I have to say others do it great as well so Claud Sonet is great like there are no bad models anymore are you using o Pro a lot do you like it yeah oh yeah oh yeah yeah yeah I I think for like cursor most of the time for coding but o Pro for everything else and like yeah it's good it's slow like planning coding or what else yeah it's planning coding but also thinking through um thinking through strategies or like just doing some collaboration that's not coding just like as a partner like bouncing ideas uh or laying out options yeah I find myself using 01 all the time like that's my main model right now um and I have 01 Pro but I just um it takes so long and I think some sometimes it feels like it's a little Galaxy brained like it's it overthinks maybe the quicker response from 01 is actually better in in certain cases I haven't figured out like basically what where I use o1 Pro is a lot of the coding that I'm doing is sort of like you where it's like 90% AI generated but it's different from you in that I'm too lazy often to think about what the architecture should be because I don't think that most of the stuff that I'm doing is like not going to last beyond like the couple hours when I'm doing it um and sometimes right now like a lot of the coding assistants like I use either wind um or cursor composer they get stuck in like loops and like do weird stuff and so when it when it's getting tangled up I throw it into o Pro and it usually figures it out or I'll send the code to O Pro and be like um is there anything in here that I should be aware of like is it actually doing what I think it's doing um which is helpful but other than that I I tend to just use o1 so it's interesting that you're using it for like almost everything other than coding yeah I I use it for coding too uh but it very specifically if I know what I want and just say do it and then it does it perfectly um but the interesting part about using it is actually that it take so long like yeah you can say it's a bad thing but what I use it for like if I use it it also makes me chill a little bit because working with AI can be very like energizing but also a little bit stressful because it goes so quickly yeah and your brain really goes hard and it's kind of refreshing to have to just sit on a chair do nothing for three to five minutes once in a while so like I kind of embrac that do you find that be do you how how often do you actually look at its thought process never never because I would think that that would also be helpful too to look at that and be like do I agree with the way that it's thinking and you know do I think the output will represent this but I guess you can just go for it yeah so I never look at it because it's like a summary either way also why I use it is because it is the newest model I want to learn the most with it and the only one to really learn about a model is to use it that like that's how you get better is to use the model so it might also be that where I'm not still like I'm still it's still a new model in my mind where I don't really understand uh or have a good feel for it so that's why I use it as well that's another reason Brandon what are you using these days I use primarily 301 I actually can't use uh Claud right now because it's not available in Nicaragua I have no idea why I I just like can't wrap my head around why but yeah so I'm like full open AI right now um and I just honestly I use whatever it defaults to which right now is 01 I was goingon to say I don't I don't do anywhere near as much coding as you guys but I did use it to make a a sort of a luxury personal app the other day and was blown away at how much better it it is since the last time I I tried to do that what was the app um I I'm still building products to help me learn Spanish better um and uh I just can't seem to find a flashcard product that works well because I really like you know I feel like my writing and my reading is far surpassing my listening and my speaking and I just want verbal flash cards what's a verbal flash card like it's it speaks to you I wanted to say the word and I want to respond with what you know um either way Spanish or English cool did you get that to work yeah yeah it was uh it was fun and it was like maybe it was three prompts um to like get the product to a place that like it kind of worked and then just have a bunch of error handling that was like very easy but I mean it was remarkable how quickly it got it to to work did you use the real time API or what did you what you build it with um first I just used like Google's uh audio API and it was awful um and now I'm switching it over to the real time API that's fascinating I love that it's still far underappreciated how easy it is for non-technical people or just even technical people to just like make something real like really quick like it hasn't filtered into public Consciousness yet yeah and and that's what like repli repet agent is going to be so important because getting stuff actually like hosted and pushed to a website that you can access it regularly so I can do whatever I want versus like going to need to run npm runev in the terminal which most people don't know what that is like that's really where luxury software and onetime software becomes possible um because like maybe 01 Pro 01 is the best at writing code but that's not what's hard anymore it's act what's hard is actually posting it all the environment stuff yeah have you used like cursor composer or wind surf um for this kind of thing because it'll run that all that stuff yeah but I should I should be getting a a 101 from from either of you at some point yeah that's been the that's been the nice thing for me is like with wind Surf and and Chris composer like they're now they can use the file system and so um they'll set up a lot of those things and then there's a because they run like let's say they run npm install or whatever they install all the dependencies um if it runs into an error it will see the error and then fix it automatically uh and that just has saved me tons and tons of time tons and tons of time where I'm I would usually be like banging my head against the problem and like Googling for like what this random error is and it just fixes it um I'm curious Kieran you're using curs composer mostly right yeah yeah that's my main uh yeah still main driver yeah I've used many others but it just works works best for me yeah do you have any tips for like effective curs composer coding yeah it's not a tool it's it's in your hand it's it's kind of like the the problem Brandon is describing like people think they can do it I love midwit response no it's it it's really it's like a friend of mine uh we spoke on Monday like two days ago and I was just saying to him like why are you not building stuff he like yeah but I'm not too Technical and blah blah blah blah blah like I hear it so many times and I said just try it just download composer just do a basic thing and I gave him a few instructions and yesterday he has been like texting me every hour I build another app luk and then with the video and like today he he said like I build an app for my daughter school this and that with a leaderboard and confetti and all kinds of things and like he he is on the like the sugar AI rush for sure like but but it's in their head like it's in your head and what works like what works is just go do it go feel that because if you've never felt that um it's hard to understand uh and yes you need to understand a few things um like what is the difference between chat or composer and agent mode and uh like which one should should you use so like it would be nice yeah like the limiting factor now is not knowledge it's just patience and like your own determination to actually like run into a problem then just literally put it back into also that like I don't even read the errors when I get an error I don't even read them and and sometimes I wonder like well is this bad because I'm not truly understanding what the problem is and then I'm just sort of like screw it like that world is over and also I'm never going to be a programmer so like my goal is to not understand this my goal is to just build a thing I agree I think like that's that's my big question for you Kieran is like I find myself like sort of like Brandon said like being almost like a copy paste monkey where I'm just like paste the error go back like and um and then I I think there's a there's a real question and I think it's a real actual like turning into a skill question which is um how do you know when to check the work of the model um and to get into the details versus is not and um I've been talking for a long time about this sort of like allocation economy thesis which is like we're moving from knowledge economy to an allocation economy where the the um previously like what you what you know was like how you were compensated and now it's like how well can can you allocate intelligence and the skill to allocating intelligence is a skill is sort of like the skills of human managers right now where a human manager always has to answer that question for themselves too is like someone did some work um do I micromanage and get into the details or do I fully delegate and then like how do I know when to do that and I'm curious for you like what is you you said earlier like you you really understand the code that's being written is that because you're actually reviewing most of the code that gets written or is it because you are architecting the code before the AI writes it so you you're pretty confident you understand how the system works like yeah how are you how are you dealing with with the kind of get into the details versus delegate yeah that's a really good question so for a Kora it's different than for like an app that I just quickly do for fun like there are differences and um for cor it's also different because I use technology that I've been using for like 15 16 years already so I know it very well it's just it's just different if you know something this is Ruby on Rails um HTML which I know know for like very long that's what we use and like it's different if you use technology you know because you look at it and you have an opinion or you have a feeling or there is there's feedback there so I can use that do you need to um that's a good question maybe not so for me the most important part is actually it's not the code that's written um but where things go wrong if things go wrong it's always because the idea or like the problem is not clear if I do something that writes uh where a cursor writes codes that like is not good it just means it's not clear what it should do like I'm not clear in how to structure things and think think of it like uh like do like models for example where like we we use emails so email we need to Define what what is an email like what kind of states can an email be in and if I don't understand all those aspects it's very hard for a cursor to do the right thing and it will fill in details and when it's filling in these details sometimes it goes Rogue into different directions that are contrary and that's not good so you need to be very clear on like a direction and uh yeah how do you deal with like filling it in on the details cuz like one one thing that I noticed and again I'm mostly using this for like oneoff apps is like when I create the app I'll make all these decisions let's say I use like superbase as the database as a simple example and then um that for that composer uh session it like remembers that and then the next time I use it if I open up a new session um it'll forget a lot of that stuff and then it will make new or different decisions like it'll be like oh uh uh let's you let's let's assume that the database is a local a local hosted P psql postgress like database and I'll connect to that um and I'll be like no no no it's super base and then it's like well where's the N file and I'm like here it is or whatever um or it'll go like I'll ask it to build something new and it will like uh go delete something old as it's building the new thing um so there's all this like weird stuff are you like continually um creating like a context file for it for to know for it to know certain things or like how are you making sure it remembers the decisions that You' you've made and and and not messing things up yeah there are a few things um so for people who are watching you're in you're in cursor we're looking at um you have your your cursor settings is open and you're going through the file system keep going yes so there's this file uh that you can create in your uh project called do cursor rules and you can write stuff uh this is linked to the current project so normally what I do is when when I um see things go wrong like what you said where use something wrong I just go in here and edit and it's very simple so for example for controllers I like to say hey actually there are two helpers always present that you can use so basically you're putting Like incursor rules at the top you have like a heading that says controllers and then yeah underneath that you have like uh some information about controllers in your code that you want it to follow is that that's basically how it's structured yeah yeah and and mostly these things come from um things that go wrong or like things that like oh like it did something and then I say oh but can you actually do it like this and I'm like okay let me add that instruction already in the cursor rules so I don't have to say that every time uh and it just do you do that manually or do you say add this to cursor rules in yeah I I don't know if it probably can edit it now but it's an interesting idea yeah yeah um wait so I I know that you put the every style guide in there so one of the one of the things that's been really interesting is like you know at at our core we're uh we're a media company full of writers and editors who care a lot about language and so all of the copy for all of our apps gets like carefully copy edited um which can take a little bit of time and I know you put the the every style guide in your cursor rules so that hopefully we can get some of the copy editing out of the way is it does it work like is cursor composer able to apply that style guide to copy in the app uh I think so so I've been I've been opening emails and apps and like what I do is like hey can you apply the every style guide to this especially so like I try to like reference it a little bit so uh it doesn't better um so far it has been changing uh like how we write things a little bit but like in the end we'll see how many uh like uh notes come on the copy wait can we try this can we try this together like I I really want to see this so basically like I'm going to uh I'm sending you a link to a like a very very drafty section of an essay I'm writing can you like throw it in as a text file into this project and then just ask cursor to like copy edit it I want to see if it it'll work uh yes wait here's the chat uh Studio chat because oh yeah because honestly if this works this like changes a lot like we're gonna have all of our editors start to use cursor now people have been writing novels in cursor so I know it's possible but that's great I put it in I put it in the studio chat and and please please don't judge the terrible writing um uh you can still see cursor right Sharon still see cursor so uh for people who are listening so basically I sent Kieran a uh draft of a essay I'm writing or part of a draft and he's saving it as a markdown file in his Kora um Kora project I guess we we should make sure this doesn't get committed um and now basically he's gonna take the cursor rules that that he has which um have copy editing suggestions and ask cursor to um to edit based on our our our copy editing style guide and he's saying can you review and apply the every copy style guide and that's it um guide without without an e um it doesn't matter it doesn't matter yeah greed and it's saying I often review and edit the text according to the provided style guide let me analyze the content and make the necessary changes if this works I'm gonna be so happy um like I I think people don't understand how interesting and important this agent interface is and how common it's going to be for every kind of um workflow it's starting with code but like this is going to happen everywhere it's going to happen in word processing it's going to happen like in in all parts of like our lives and I've started to use this actually for like whoa for for like note taking and stuff it's been really cool uh this is really interesting so it gave it says I've applied the style guide rules to improve the writing here are the key changes made tile case for headlines and section headings interesting um I'd have to like really look at this but based on what I can see I would guess that it's not um it's missing things and you what what youd need to do is ask it to go rule by rule through the entire file yeah MH um yeah it doesn't know how to do that yet and and also if we want to lean into it more like what you could do is you could create a notepad with the Styles so you can reference that note not pads and say hey everything in this notepad go line by line or you can say uh just go through it once and then do the other yeah there there are other ways to do this as well um like clearly this is not set up to do this but the cool part is like yeah it's a hecky thing but like the cool part is like okay we we so let's let's say this this is it but also you can say uh can you create a promotion email using the core of this idea to link to the full block post then I say that's interesting yeah so like you're basically using it to you're using this as as a Content creation tool um that isn't just creating the content it's also like putting it into your whole system into the code um it's writing the code for it and yeah I think people don't understand the like how powerful that actually is having everything integrated together yeah and it can run things on your computer like the beautiful thing working cursor is like you can access everything and just rethinking that this content now you can use to write a landing page or wait something I want to see what happens so you're saying can you create a promotional email using the core of this idea to link to the full blog post um and we'll see if it actually works so let's let's do it here so we we take this this uh we'll just go here and we say can you use this copy um to write the email from there and what it will do now is it will look at my other email that I already have and it's editing the template yeah which we don't I don't think you want see this is an example of like this is what what we don't want okay I just I just go back so create a new email uh gold this is why you have to keep your eye on your agents cuz they'll go off do things that you might not want um and basically what you're doing is you're just going you're you're noticing it and then you're editing the original prompt rather than like waiting for it to to do something and now you've redone it you've said create a new email it's now saying like Okay I'm going to go create a new mail or template and it's like basically rewriting the email and creating a new template and um what's what's the uh how can we teach what we cannot Define is the is the subject line which is only funny to me because I wrote this piece and you guys have no idea what this is about but uh it's very very funny um I love this I think this is really cool my my last question for this is like C if you ask it to go line by line through the St God can it do that like let's let's let's try that so uh let's go to the cursor we're inventing things as we go yeah we are so you're going back into cursor rules and you're what are you doing you're oh you're GNA I'm trying to create a notebook so or notepads so notepads are these piece pieces of uh like prompts or whatever you want it to be it could be a PRD that you can inject in the composer or anywhere else so it knows like it it doesn't need to always know about it uh you can put it here but if you want to inject it it can go here so C rules is like always follow this always use this and notepads are like use it in specific cases where I I specifically ask you to use it yeah go through the um items items one by one so what I'm doing is uh quick and dirty every style guide uh it says always use the following sty Bel go through the items one by one and uh suggest edits so okay so these are lots of lines let's go um I'm going back into composer command I reset um what I do is I go to notepad and say this one it's called new notepad I'll rename so you're basically going back you're adding a new compo composer window you're adding not your new notepad in the composer window or you're going to you're basically going to rename it so seems you're adding the notepad in in your composer window and then saying can you apply the style guide um let's see what it does and a cool thing is like currently we're using claw 3.5 but if you want to try a different model like every model out there is here so you can just switch to another model and you have the same interface you can just see how that goes that's I think this is not it's not quite working yet I found that like AI models are not uh the current like version of llm models are uh are not that good at taking a rule and then applying it in every instance where it's violated in a piece of text they find a couple um the only one that's good at this is 01 but 01 is not in any of these agent interfaces because it doesn't have tool tool calling yet but that's coming like it's definitely it'll come out like this quarter I'm sure and I think that will like totally change how this works um yeah and and I so I went to normal because we we don't really need an agent for this because this is kind of a one uh one shot so yeah it's a little bit hard to understand but normal and agent the difference is the agent can think in steps and normal is more like you say something and then it says something back it can still create files or do things um so that part is not the agent like thing it can create files but it cannot see what the error is an agent can run codes on your computer and see oh there's an error oh let me fix the error and then you don't need to do anything with the normal one it just creates the files you have to do it yourself and then say Oh there's an error can you fix it so that's the normal but you can use 01 in normal which is still good the agent basically it runs in a loop and just tries to finish the task for you and chat like tells you what to do it's sort of like having chat gbt in your in your cursor um and and you have to kind of manually apply each change um and so so so it can do that iterally based off of the problems that it encounters but it can't it doesn't yet work within a single propt like it's not going to work iteratively inside of a single prompt it's not going to like based on one based on your initial prompt it's not just going to keep running until it it it thinks it's finished the entire task it will just respond with all of the responses and then you apply the changes and then you can say like okay like let's let's keep going um yeah yeah and there's also the chat which is like the most simplistic version um one other way we could try it out is like selecting one section and then do command K and then say I think that would probably work better yeah think about what our editing team would actually do and yeah until it's until it's agentic I don't think they're going to do this no no no yeah but I think there might be a way to instruct the agent to think in a loop there might be yeah there might be we just need to like go through it like I'm pretty sure you can do it um but it doesn't work as simply so yeah it need some work okay well I want to I want to we're we're we're getting close to time and so I just want to like take it back to like the interesting one of the interesting things to me about getting to do this kind of podcast is we get to take people along in our journey to build these businesses which are it's like a new generation of business under a new kind of structure we have multiple different products multiple different businesses Under One Roof um and we're you know figuring it out as we go along and I think the more we can bring people into that process of figuring things out the better um I'm curious like let's talk about the the main problems right now right like we launched Kora we have the weit list there's 7,000 people on the weight list which is amazing um we've started to take people off the wait list um and we've done that in just like you know we send it sends an email uh to them and saying here off the weit list and then also Brandon has put the team on his back and is doing a lot of manual onboarding um like your whole schedule today is like I think filled with with doing manual onboarding with people which is amazing it's the super style of onboarding and we decided to do this because um it's just like signing up with your email and and letting something have access to your email is like a really it can be really stressful um it's it's a high high pressure thing and having the kind of like overthe shoulder onboarding uh allows us to identify problems so that we can um guide the initial people through it and then fix the problems um and but I want to talk about like what are what what are the main problems that we're trying to solve right now like what are how are we approaching okay we're going from here to um The Next Step which is like we can probably uh we can we can launch it publicly um but there's a there's a lot of steps to that um so yeah what are we thinking about right now I I have before we get into that I I just I think I can share what the hardest part about this is which is that we just have a bias to use the products that we make and sometimes I feel like that can make us feel like the products are working because we use them even though we may be convincing ourselves that some of the problems that we're encountering aren't real problems because we want to be using the product um and that is it's like an impossible question to answer uh if we're doing if we're doing it or not because it's hard to um recognize that for some types of problems so I feel like onboarding manually helps us get a sense of like what are people's real concerns or apprehensions specifically with a product that's going to manage such a critical part of your work life and I feel like that is is I mean that's one problem that we're all very aware of right now which is Kora archives your emails it makes it so you don't see stuff that people may be sending to you that is important and the debate that we had this morning was like none of us feel this problem but we've onboarded some of the people some people that have and how big of a problem really is it are those people our ideal customers or are they not our ideal customers because we seem to not have that problem but are we convincing ourselves that we don't have that problem so I think navigating through that is um this is sort of like a big overarching theme of how to prioritize I do think that's a great point and and yeah one of the things I love about the products we're able to build is we build products for ourselves and I think that's a great place to be um but I think that the the potential downside is you get one moment when a product first you you first use a product where all of the like I'm unfamiliar with this problems come up um and then once you've been using it for a couple weeks you like forget what those are and uh and only through contact with more initial users do you like start to start to remember like oh this is like what it's like to go through this from a Blank Slate um and you need to take those those really seriously but then you also have to figure out like well if we've only done a couple onb boardings and PE and the people we did the onb boardings with like didn't like the onboarding experience or didn't like the product like what does that mean how do we Square their feedback with like our sense that this is a good product and I don't know about I don't know about you all but like I my feeling is like you just need more data basically um and and and just trying to get uh more people through the pipeline so instead of having two people to rely on we have like 30 uh you start to like zoom out and and sort of pattern match and be like well they fit into these different buckets and some people like love it and like let's just let's focus on those people for now or like everyone has this problem it's clear that we need to fix something um but I think that's that's that's what people are talking about when they talk about the startup roller coaster is um you get early data from a couple people and then you extrapolate and then that's like really either emotionally like really exciting or it's like really emotionally like draining um and the more data you have the the more even you can be about your assessment yeah one other thing also is you you can focus on what are the biggest problems to solve um or you can say what works very well and what can we make even better because it's kind of flipping it a little bit because that's kind of what we do we know we have a lot of problems we need to solve that is kind of like not there but we also have something that works very well and like people use it and think like holy \[ \_\_ \] this is like this feels amazing like people after one day of using it just think this is special or people that tried 20 tools before that kind of does the same thing they're like ah but yours is different or like yeah I can't do many things and certain things are very annoying today but I love the idea or the why or like what you have already so that's another way to look at it like just be very good at one thing because then it will forgive you for the rest yeah yeah it feels like right now the the core problem that we're solving is Kora is just a different way of managing her email and we all maybe have a bias to be open to this different way of managing our inbox like this and the question that we need to solve right now is are millions of other people interested in in handling their inbox like this um that feels like the main thing that we need to solve right now and then you know there's a thousand other problems that get thrown in there that sort of muddle our view of of solving that that core problem or distract us from solving that core problem yeah and and and I like I like that that framing or that flip um because I think one of the uh one of the problems that early startups can run into especially if tackling something as big as email is to say well in order to like truly know if we've we're solving the problem we need to like build um a full email client and we need to like get get to table Stakes with Gmail for example before we maybe even before we launch and I think like that's always a losing battle because what you what you want to build early on is something that's so good for a certain type of person it's like 10 times better for a certain type of person such that they will use it even though it's not at feature parody with other like email products or whatever pick your pick your competitor um and and I think that's that's what we're doing with with briefs like yeah it would be great eventually if cor was like a full-blown email client but for now our job is to make it so \[ \_\_ \] good at the one thing that it does that even though it's not a full email client yet people still love it uh and and also to figure out who those people are right like it's not going to be it's it's not going to be amazing for everyone off the bat and nor should it be um the question is is there a core group of people who \[ \_\_ \] love it and my theory is we it's too early to say but my theory is like so like where the product is right now the answer is yes 100% and it'll be a really sticky really amazing experience for those people but you never know like you never know if you're just drinking your own Kool-Aid because like we came up with it we built it and we like it you know um but we'll find out yeah yeah I'm like sitting here thinking like I don't want to go back to Gmail or super oh my God and then and then you say that and I'm like but maybe I would I don't really like it's hard to it's hard to really know I don't think that that's true I think that I would be a very disappointed on a pmf me too like can you imagine like it's like going back to the Dark Ages no I mean I just don't think about email anymore and it's ridiculous to me to think about how email basically mimics a physical mail inbox right now there's a bunch of spam that I'm going to delete without opening is exactly what happens with my physical mailbox and there's some mail that I'm going to open and then be confused about like do I need to respond to this why this is like tricking me and um this cord just like completely turns it on his head so I I think that we've nailed that but this this I feel like what what I'm feeling right now and what we're circling around is like the core problem that feels like it shouldn't exist when you're developing software cuz software is very binary either it works or it doesn't work but the problems that we're solving are very very mushy and you it feels like the way to like solve that is to have a perspective but then to just keep iterating on stuff one of the biggest problems you know we sort of have two challenges ahead of us one is like fantastic product Market fit represented by a product that solves real real problems with a certain perspective and then the other problem is like getting a shitload of people to know that cor even exists and um figuring out how to prioritize on either one like that's where the mushiness of building a product comes in because you have to make a decision ultimately um and yeah I I find it emotionally sometimes hard to uh to like give things up we yeah we've been talking that about that a lot like one of our uh one of our uh q1 or just 20 2025 in general questions is like what are what do you want to sacrifice um because I think we're as an organization very all of us just love doing lots of things and we don't want to give anything up um but giving something up is often the best way to like make progress on the things you care about um and yeah I think I think you're right though like that that's the place where I think we're heading which is um if you believe what's coming out of like open AI is like we're we're basically getting to AGI in the next like one to two years and and I I think and by some definition of AGI um and I think that that's probably likely to happen but the really important or interesting thing about that to me is um all the big labs are concentrating on getting AI that can solve problems step by step where you can verify the solution to each step which is something like coding problems or math problems um and I think what what will become apparent once that is done is how few problems in the world are actually like that and how often problems are much much more squishy and are not able to be reduced into stepbystep um Solutions like that where where each where each step is verifiable and that's where you get down into like taste and intuition and pattern matching or whatever which llms are also quite good at but they're not good at um we can't optimize those problems in the same way with the same feedback loop as we can for like provable problems because the feedback loop is always going to be uh do something get data from the world like come up with new ideas come up with new ways of seeing that data and then try something again and see how that works and I think that that's that's sort of like an inescapable thing but that's also like really beautiful and it and it uh it's I for me it's the most fun part of building I I agree it's it's the most fun part and it's also the most sometimes anxiety inducing because there's just so much to be done and you want to be at a completion state but the reality is that completion State doesn't exist it exists when you're writing code and you're building a feature maybe but for building a company building a product it's like really enjoying the journey and and um sort of embracing the suck of it embracing the messiness um it's it's very uh I'm a I'm a big type two fun person which is maybe why um I enjoy doing this stuff but it's really type two fun you need to enjoy the suck of difficult decision making and also collaboration just working with people that push your brain further like ask difficult questions yeah like it's the best when you when you feel like ah \[ \_\_ \] that's a good question it's great yeah so Kieran and I Kieran and I have uh we we we go back and forth a lot um you know I I think sometimes I get with like let's talk about everything that needs to be done and let's get really detailed about everything that needs to be done and Kieran is so good at just being like that doesn't matter and I have really big problems to solve right now and let me solve these problems and we can deal about that with that later and that's been a really fun thing fun is maybe an interesting word to use but like it's been a very healthy thing for us to like navigate in our relationship personally and then also just like with how we actually built Kora and I think um you know if we're two like sort of stubborn rocks we are definitely like rubbing against each other and like polishing a diamond um that is Kora so ultimately it's like a really really good good thing um I have a total aside a total tangent that we may want to cut but do you guys see that um I guess open Ai and Microsoft's deal ends when open AI has proven that it can build a product that can generate a hundred billion dollars yeah because they couldn't Define AGI so they said AGI was two hearts yeah I know I just feel like this is like the best negotiation for Microsoft to be like once you do that like we're all \[ \_\_ \] anyway so yeah I think it's I think it's it's a really interesting lesson in um how often um I think the sort of UT utopian vision for company building can really help people like get excited and how often uh when you create exotic business structures to like match that utopian Vision um it it ends up you end up being like actually the the regular business structure is like probably better like open a has like the the nonprofit then they have the cap profit then they have like the the Microsoft investment and crazy all this complexity where Microsoft is finally like \[ \_\_ \] it like once we get1 billion you're free to be a nonprofit or or whatever it is you want to do um and uh and I think there's something parallel to that with just like AI in general I've been doing a lot of reading about um the history of AI and um all the different like waves of it and I think we're we're in this place where I'm sitting here being like I think we'll get AGI in like a year or two or whatever and um and I think we've all felt those those feelings of like GB when GB 3 released or chat BT released we like wow like everything is going to change and it's going to be like completely different from here on out um and sometimes that's a feeling of like Dread it's like whoa like where are we even going and I think what's interesting to know is that um that has happened in every single AI wave every single AI hype cycle um like when when when they first started working on AI in the 50s they were like yeah we we'll get it done in a summer um and then there were all these other waves in the 60s and the 70s where they're like yeah we had we made this breakthrough it's coming um and what's been interesting is there's always uh a new frontier that opens once you once you get to a certain level you realize how much complexity is still left and it reminds me a lot of um I don't know if you guys have ever been to Zion National Park um did you go did you do the angel Landing um uh hike yeah um so curious where this is going I'm curious if you had this experience but like basically when I I went to I went to Angel's landing and I hiked it um with uh with an ex-girlfriend and there's a point at the angel angel Landing hike where you do you do a bunch of switchbacks and then you're kind of like um shimmying or I don't know if the right word is shimmying Brandon you probably know where you're basically like um facing a wall and you're kind of moving like across the wall and you're like almost like walking on a tight RPP and there's like a cliff face that's like you know 500 foot drop that you're trying to like get across and I was doing that and and my girlfriend at the time was like I don't want I don't want to do that like I'm scared of heights and I was like cool it's fine like I can see the peak right there like I'm just going to go get to the peak and then I'll come right back and what was interesting is I got to the peak and as soon as I got there I realized there was like another Peak and I was like oh like I can now I see this new Peak like I'm just going to go get to that one um and then I'll go back and like that just kept happening every time I got to like a peak like a new one appeared until it had been like two hours and I finally got to the end of the hike and I was like wow this is amazing this view is awesome but my ex was like what the \[ \_\_ \] you like you like left me and then your girlfriend broke up with you and I think like AI is like the way progress works is a lot like that like you see a peak you're like I can get there and you get there and then you're like oh actually there's um there's this whole other Peak that I didn't even realize was there but is has clearly been there the whole time um and and that's how I feel about AI it's like um we're going to probably get there to by some definition in the next couple years and then but it's going to reveal how much complexity there is still to be done and all of the utopian things and then all of the Doom things are going to like feel sort of I think irrelevant or or the reality is going to be much more complex um and that makes honestly that makes me excited I like that so this is you're describing what's called a false peak in the biz there you go um and I have another visual that like really makes me um that this reminds me of that I saw at some point which is um saw some visual that was like this is the ho of human knowledge and by the way for people who are listening so Brandon has opened up a figma file and he is uh real time whiteboarding his uh his Vision here so all of this is all of human knowledge that it's a circle in the middle in a big circle and then so like one way to think about what's happening in AI right now is like it feels like it's this huge like important big thing that's like changing the world but the reality is like if you zoom in like it's this so now I've just zoomed in to like one you know the the the um edge of the circle I've zoomed in a lot and there's like a little blip there and like what this is going to do is I can't do this bigma but like this is just going to expand the circle like ever so slightly and now that little blip will be like inside the circle and then it'll move you know it'll move slightly over here and then it'll just keep expanding like that slowly over time and it's important to just remember that whatever we're learning right now like it's I just it's easier to have a it's easy to have a Doomer mindset that like AGI is just going to take over like everything and we won't have jobs anymore and we won't be able to be creative but the reality is the human reality is it will just open the door to something else yeah and and yeah I think to bring it back to to Kora like that's one of the been then the things that I've realized about Kora is there's all this like Doomer stuff about like well what happens when it's just AI is emailing each other and no one's no one's emailing and what what I found with using Kora is um like my inbox now is only humans the only people I have to respond to are humans and then the AI is summarizing all the other stuff and it's it's incredible how much other stuff I get that's not even AI generated but it's like some combination of like a person who doesn't care and like some automated marketing email or whatever that um that I get in my inbox all the time anyway and what the AI is actually doing is presenting all that other automated stuff to me in a way that's more consumable and allowing me which gives me a lot more time to like focus on the people in my inbox who matter and I think that's actually great and it's something that doomers just miss yeah it's interesting maybe Kora is the most human way to email I think it is um all right well this is uh this has been a great conversation any final thoughts uh Kieran or Brandon before we sign off join the wait list core. computer I love that yeah join the wait list we're on boarding every day also if you are every subscriber you might have a little bump here and there that's true uh every subscribers you get access you get early access to Kora uh you'll get bumped off the wait list it's 7,000 people so you get to cut the line and then you get access to all the other products we make and all the writing uh and other things that we do um and we will do another core update hopefully uh hopefully soon hopefully we'll have more stuff to talk about um but until then thanks for joining this is awesome uh I'm super excited for the future of Kora and to get to do it with both of you thanks for having us Dan thank you oh my gosh folks you absolutely positively have to smash that like button and subscribe to Ai and I why because this show is the epitome of Awesomeness it's like finding a treasure chest in your backyard but instead of gold it's filled with pure unadulterated knowledge bombs about 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