How to digest 36 weekly podcasts without spending 36 hours listening | Tomasz Tunguz (Theory Ventures)

Tomasz Tunguz is the founder of Theory Ventures, which invests in early-stage enterprise AI, data, and blockchain companies. In this episode, Tomasz reveals his custom-built “Parakeet Podcast Processor,” which helps him extract value from 36 podcasts weekly without spending 36 hours listening. He walks through his terminal-based workflow that downloads, transcribes, and summarizes podcast content, extracting key insights, investment theses, and even generating blog post drafts. We explore how AI enables hyper-personalized software experiences that weren’t feasible before recent advances in language models. What you’ll learn: 1. How to build a terminal-based podcast processing system that downloads, transcribes, and extracts key insights from multiple podcasts daily 2. A workflow for using Nvidia’s Parakeet and other AI tools to clean transcripts and generate structured summaries of podcast content 3. How to extract actionable investment theses and company mentions from podcast transcripts using AI prompting techniques 4. A systematic approach to generating blog post drafts with AI that maintains your personal writing style through iterative feedback 5. Why using an “AP English teacher” grading system can help improve AI-generated content through multiple revision cycles 6. How to leverage Claude Code for maintaining and updating personal productivity tools with minimal friction — Brought to you by: Notion https://notion.com/howiai—The best AI tools for work Miro http://miro.com/—A collaborative visual platform where your best work comes to life — 25k giveaway:  To celebrate 25,000 YouTube followers, we’re doing a giveaway. Win a free year of my favorite AI products, including v0, Replit, Lovable, Bolt, Cursor, and, of course, ChatPRD, by leaving a rating and review on your favorite podcast app and subscribing to the podcast on YouTube. To enter: https://www.howiaipod.com/giveaway — Where to find Tomasz Tunguz: Blog: https://tomtunguz.com/ Theory Ventures: https://theory.ventures/ LinkedIn: https://www.linkedin.com/in/tomasztunguz/ X: https://x.com/ttunguz https://x.com/ttunguz?lang=en — In this episode, we cover: (00:00) Introduction to Tomasz Tunguz (03:32) Overview of the podcast ripper system and its components (05:06) Demonstration of the transcript cleaning process (06:59) Extracting quotes, investment theses, and company mentions (10:20) Why Tomasz prefers terminal-based tools (12:38) The benefits of personalized software versus off-the-shelf solutions (15:31) A workflow for generating blog posts from podcast insights (17:34) Using the “AP English teacher” grading system for blog posts (18:25) Challenges with matching personal writing style using AI (22:00) Tomasz’s three-iteration process for improving blog posts (26:13) The grading prompt and evaluation criteria (28:16) AI’s role in writing education (30:28) Final thoughts — Tools referenced: • Whisper (OpenAI): https://openai.com/research/whisper • Parakeet: https://build.nvidia.com/nvidia/parakeet-ctc-0_6b-asr • Ollama: https://ollama.com/ • Gemma 3: https://deepmind.google/models/gemma/gemma-3/ • Claude: https://claude.ai/ • Claude Code: https://claude.ai/code • Gemini: https://gemini.google.com/ • FFmpeg: https://ffmpeg.org/ • DuckDB: https://duckdb.org/ • LanceDB: https://lancedb.com/ — Other references: • 35 years of product design wisdom from Apple, Disney, Pinterest, and beyond | Bob Baxley: https://www.lennysnewsletter.com/p/35-years-of-product-design-wisdom-bob-baxley • Dan Luu’s blog post on latency: https://danluu.com/input-lag/ • GitHub CEO: The AI Coding Gold Rush, Vibe Coding & Cursor: https://www.readtobuild.com/p/github-ceo-the-ai-coding-gold-rush • Stanford Named Entity Recognition library: https://nlp.stanford.edu/software/CRF-NER.html — Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Speaker 00

  I have a list of 36 podcasts, but I don't have 36 hours every week to listen to 36 podcasts. So what I did is I created a system that goes through each of those podcasts every day and downloads the podcast files and then transcribes them.

• 0:14Claire Vo?

  Can you show us how it's actually built? Like, where do you get this feed? It sounds like you run it locally. How does this all work?

• 0:20Speaker 00

  I wrote this thing called the Parakeet Podcast Processor. And this podcast processor basically takes in a file. And what it'll do is it will read the file, it'll download it, and then it'll convert it via FFmpeg. And that will take the audio and convert it to text. So here's the podcast summaries for today. There's Lenny's podcast, the hosts, the guests, a comprehensive summary. So here's a conversation with Bob Baxley, key topics, and then key themes. The part that's most invaluable for me are these quotes. And those quotes, I'll read them. It'll suggest a bunch of actionable investment theses for a venture capital firm, which is put into the prompt like, okay, maybe we should be looking at AI-assisted design tools.

• 1:00Claire Vo?

  You've gotten not only the content you want, but the user experience you want. You control it end to end, and you can build this hyper-personalized software experience.

• 1:13Claire Vo?

  Welcome back to How I AI. I'm Clara Vot, product leader and AI obsessive here on a mission to help you build better with these new tools. Today I have Tom Tungus, a legend in the enterprise software business and founder of Theory Ventures, which invests in early-stage enterprise AI, data, and blockchain companies. Tom is followed by over a half a million folks on his blog and LinkedIn. And he's going to show us today how he uses AI to keep up with all the podcasts, including this one, and draft blog posts that would be approved by your AP English teacher. Let's get to it. This episode is brought to you by Notion. Notion is now your do-everything AI tool for work.

• 1:56Claire Vo?

  With new AI meeting notes, enterprise search and research mode, everyone on your team gets a note taker, researcher, doc drafter, brainstormer. Your new AI team is here, right where your team already works. I've been a longtime Notion user and have been using the new Notion AI features for the last few weeks. I can't imagine working without them. AI meeting notes are a game changer. The summaries are accurate and extracting action items is super useful. For standups, team meetings, one on ones, customer interviews, and yes, podcast prep, Notion's AI meeting notes are now an essential part of my team's workflow. The fastest growing companies like OpenAI, Ramp, Versal and Cursor

• 2:41Claire Vo?

  all use Notion to get more done. Try all of Notion's new AI features for free by signing up with your work email at notion.com/HowIAI. To celebrate 25,000 YouTube followers on HowIAI, we're doing a giveaway. You can win a free year to my favorite AI products, including V0, Replit, Lovable, Bolt, Cursor, and of course, ChatPRD by leaving a rating and review on your favorite podcast app and subscribing to YouTube. To enter, simply go to HowIAIPod.com/giveaway, read the rules and

• 3:25Claire Vo?

  leave us a review and subscribe. Enter by the end of August and we will announce our winners in September. Thanks for listening. Okay, Tom, I'm so happy to have you here because you're going to show us how you are solving a problem I'm creating for you. And the problem I'm creating for you is I am creating yet another piece of interesting content that you have no time to consume. Certainly the format that we get it out. And I know to you, content is a really interesting source of Ideas of trends of companies. So tell us what you built and why?

• 4:04Speaker 00

  Absolutely. Well, thanks for having me on. So I I don't I prefer to read than to listen because I can skip ahead. And I think there's a lot of information inside of podcasts that people share that I would love to know. And so I built, I guess, what I call a podcast stripper. And the idea is I have a list of 36 podcasts, this one included, that I really admire and I want I want to learn from, but I don't have 36 hours every week to listen to 36 podcasts. Right? So what I did is I created a system that goes through each of those podcasts every day and downloads the podcast files and then transcribes them using initially it was open

• 4:47Speaker 00

  source or OpenAI is open source whisper, which takes audio and converts it to text. And then there's a new version called Parakeet, which Nvidia released that runs really well on a Mac. And so I'll take that text and then I'll run it through a prompt and it will spit out a whole bunch of different things. It will spit out a high level summary or whatever I ask it to.

• 5:07Claire Vo?

  Okay, can you show us how it's actually built? Like, where do you get this feed? Do you it sounds like you run it locally? How does this all work?

• 5:14Speaker 00

  So I initially downloaded the Whisper app and what I did is I wrote this thing called the Parakeet Podcast Processor. And this Podcast Processor basically takes in a file. And what it'll do is it will read the file, it'll download it, and then it'll convert it via FFmpeg, which is a library that converts different kinds of files. And that will take the audio and convert it to text. And then I use Gemma 3, which is really good at this, to actually clean up the transcript. So if we search for the Ollama model, basically what I'm doing is I'm just cleaning up the file here. Your transcript editor clean

• 5:57Speaker 00

  up this podcast while preserving all the content, keep the same length, remove the ums and the ahs, preserve all technical conversations, and that returns a clean transcript. And so on a given day, there might be five or six different transcripts that need to be transcribed. And then what I'll do is it runs through the Parakeet Podcast Orchestrator, actually, it's just a podcast orchestrator.

• 6:24Speaker 00

  Which is here. And so I'm storing each of the files that I'm transcribing in a local Ducky B. There's a little database that says, I processed this particular podcast on this particular day. And then I save the transcripts and I take all the transcripts on that particular day from the database, which is here. And then I send them through a prompt, which, let's see if we can find it, summarizes here, the daily summarizer. So it generates a daily summary document, which is here. It'll produce a file that looks like this. So here's the podcast summaries for today, June the 13th. So there's Lenny's podcast, the host, the guests, a

• 7:07Speaker 00

  comprehensive summary. So here's a conversation with Bob Baxley, key topics. So here he's talking about his philosophy, a company culture, and then key themes. And the key, the part that's most valuable for me are these quotes. And those quotes are then, you know, I'll read them. It'll suggest a bunch of actionable investment theses for a venture capital firm, which is put into the prompt, like, okay, maybe we should be looking at AI assisted design tools. And then that might kick off a market map. We're really thesis driven. So maybe that starts a conversation on the Monday and we decide to staff a market map. Then it'll produce these noteworthy observations, which are actually put into tweets. So here are the Twitter post suggestions.

• 7:53Speaker 00

  So I haven't done this yet. I'm still working on the prompt, but the idea is like, could we actually automate linking back to people who we really like? And then another part, this is a little out of order, but another part here is, are there startups that are mentioned within these podcasts that we should know? Right? So here's Airbnb, Google, Amazon, Stripe. We know all these guys. I don't know what this company is. And so this might go into our CRM. Right, to be enriched. And then the last is, we'll actually generate prompts for blog posts in the style that I write. And then this will go into a Python pipeline to actually machine generate a blog post.

• 8:31Claire Vo?

  So before, before we get to the, the machine automated AI blog post pipeline, I have a couple of questions about this process because I think you did a couple interesting things. One, I have a question is if you found higher quality by cleaning up the transcripts, like how much did that incremental input quality piece actually help your, your output?

• 8:57Speaker 00

  So it helped. So initially I was trying to get, the answer was initially a lot and then over time less.

• 9:05Speaker 00

  Because initially what I was trying to do was to find these companies. I was using named entity extraction algorithms from Stanford, the Python library. And it was having a really hard time. And so I was cleaning up, cleaning it up to try to get the performance to improve. And then I just put it to a really large, large language model and it spit it out much better. And so the cleaning is not that useful anymore.

• 9:29Claire Vo?

  Yeah, I was looking, because I was looking at it and you're focusing on like proper nouns, company names. And so I'm assuming if you want to extract something like Stripe, which has many, many meanings, getting it into a proper noun format, for example, would help with that extraction. But you're saying as you could just use as opposed to these kind of packaged libraries for specific machine learning use cases, instead just send it to an LLM. That ended up just meaning you could worry less about the input quality of, of your transcripts and more about that kind of prompting and structure here of the output.

• 10:02Speaker 00

  Yeah, that's exactly right. So my goal initially was to do everything locally.

• 10:07Speaker 00

  And so I was using Ollama, I was using that Stanford library, Parakeet is run locally. And then what I realized is particularly for the named entity extraction, more power from machines are much better.

• 10:19Claire Vo?

  Yeah. And so, and then I have to ask another question, which is, everybody's going to look at this and they're going to go, what the hell is he typing in? Like, we have a couple of people that are like, why in the terminal? So I'm just curious, you know, did you ever think about putting a UI on top of this? Do you just, you seem very comfortable in the terminal, so it seems to work for you? I'm just curious about where you decided to focus your user experience efforts on this personal.

• 10:44Speaker 00

  Well, I love the terminal. I read this blog post by Dan Liu with two U's, where he was talking about latency and the latency between like the keyboard and the computer. And it turns out that the terminal is actually the application with the lowest latency. And the lower the latency, the less frustration you have using a computer. So during COVID, I decided to learn how to use a terminal. And since then, I've sort of lived in it. And so like my email client is a terminal-based email client. And I use that because it's really fast and then I can also script different things. So I can delete 10 messages at once, or I can call an AI to actually automatically respond to an email or add a company to a CRM. So that was really important. But at a high level, like I think it's, I've just become really comfortable with it. It's really fast.

• 11:29Speaker 00

  And then the last thing I'll say is, I think Claude Code is an amazing product. And the great part about what Claude Code does is I have about 2,000 blog posts. I can just go into Claude Code and say, modify the files in this way, or change the blog post theme. Or recently, I launched a blog post generator, which takes all of the content that I have on the blog and you can ask it a question. It will write a blog post for you about your particular question. And I did that all using Claude Code.

• 11:59Claire Vo?

  Yeah, I mean, I have two sort of thematic things that I think of while observing this, this workflow and your love for the terminal. I agree, Claude Code is an amazing product and it's a really well-designed, terminal-based product. I love it. I love that. You have this constrained surface area in which to like communicate progress and latency and changes. And I think it's really thoughtfully designed. So for anybody out there building dev tools in particular, learn how to design in the terminal. And so, so important because you make really fabulous products for, I guess, people like you and me that say things like, I picked up the terminal over COVID as my hobby. The second thing that I was thinking

• 12:40Claire Vo?

  about is since generative AI has become mainstream, every single person has said, somebody make a podcast digest application. Every single person I know is like, it was one of the first projects I made. I made my kids a podcast digest, their favorite podcasts, and it made little quizzes about the topics that they could answer. Super cute. So I think it was a very common use case. But what I was thinking is, no startup is going to be like, you know, it's going to be huge TAM company, a terminal-based podcast transcript processor and thematic extraction generation engine. And I think this is such a perfect

• 13:21Claire Vo?

  example of like, yeah, there's probably something off the shelf that could do something like this. But you've gotten not only like the content you want, but the user experience you want. You control it end to end. And you can build this like, hyper personalized software experience, which I just, it was not possible. Or it wasn't efficient to do, I would say, until very recently.

• 13:46Speaker 00

  Yeah, it fits, it fits the workflow, my workflow like a glove, right? And anytime something comes up and changes, like maybe there's a section that's out of order, like we found, I can just go into plot code and update it. And it'll be done in 15 to 30 seconds. Right? And, you know, I really wanted an email of this every day. And that was straightforward. So I agree with you. I think we're at a place where the marginal friction to achieving a glove-like fit with little utilities that maybe you wouldn't have paid for in the past is now, it's just so, it's so quick, right? Like you just entering a couple of emails and it'll be done.

• 14:20Claire Vo?

  Yep. You've seen the doom and gloom headlines. AI is coming for your job, but the reality is a little bit brighter. In Miro's latest survey, 76% of people say AI can boost their work. It's just that 54% still don't know when to use it. As a product leader and a solo founder, I live or die by how fast I can turn fuzzy ideas into crisp value propositions, roadmaps, and launch plans. That's why I love Miro's innovation workspace. It drops an AI co-pilot inside the canvas, so stickies, screenshots, and brainstorm bullets can become usable diagrams, product briefs, and even prototypes in minutes.

• 15:04Claire Vo?

  Your team can dive in, riff, and iterate. And because the board feels like a digital playground, everyone has fun while you cut cycle time by a third. Miro lets humans and AI play to their strengths so that great ideas ship faster and happier. Help your teams get great done with Miro. Check out Miro.com to find out how. That's M-I-R-O dot com. Okay, so you have taken all this content, including amazing content from the Lennies Podcast Network, and you're processing it, you're extracting themes, you're extracting

• 15:43Claire Vo?

  quotes, you're finding companies that may be interesting to reach out to, you're at least drafting Twitter posts. We will see if those actually get posted in production. And then let's talk about your second workflow, which is you extract insights that might be interesting for you to write about or add your perspective on. And then you actually turn those into drafts using AI.

• 16:08Speaker 00

  There's a lot of stuff that's happening in the ecosystem. And every once in a while, I like to write about what somebody said in a podcast, right? And I think today, like, I was looking, the GitHub CEO is actually interviewed. And so Matt Turk interviews, who's at another venture firm, interviews Thomas. And he talks about how AI encoding is the future. And so what I really want to do here is let's suppose I really wanted to have a blog post that was tied to this. So what I can do is I say like, okay, I have this podcast generator and I'll show it to you in a second. And what I'll do is I'll take as context the transcription of that podcast, which is here.

• 16:49Speaker 00

  And then I'll define an output file and then I'll give it a little prompt, which is like, you know, he said this quote, which is actually within the podcast summary. Everything that I can easily replace with a single prompt is not going to have any value. It will have the value of the prompt and the inference and the tokens, but that's often a few dollars. And I'll tell it, okay, go look for podcasts that are related to this and I've categorized them as AI. And then here, actually, there's a bug. So demo fail. I was trying to fix it before I got on the video, but the searching for the relevant blog posts is failing and I need to figure that out. It's run through LanceDB vector embedding this database. Okay. And then it'll generate a blog post and I'll share the prompt in a second.

• 17:34Speaker 00

  And the best, well, one of the techniques that I found the most effective when generating blog posts is to ask it to grade it like an AP English teacher. And this goes back to my history. I remember not really loving to write until I took a class with an army veteran and she taught me to really love to write and he was my AP English teacher. And so I really like receiving feedback in that way. Grade it on a letter grade and then tell me what I could improve and then I'll iterate with the model until I get to an A minus.

• 18:06Claire Vo?

  Got it. And so just before we go into the actual writing, and I'd love to see a little bit of this AP English prompt, are these two pieces connected? Your podcast summaries, do those go into this vector DB that can then be searched through for relevant other podcasts if you're writing on a topic? Like, how does this all come together?

• 18:25Speaker 00

  Yeah, so right now it's just the blog posts that I've written in the past, the 2,000 blog posts or so that go in. And the major reason I add those as context is I'm trying to capture my style. And I have to tell you, like, that's really hard. Like, I have fine-tuned OpenAI. I have fine-tuned Gemma models. And getting the voice, and you'll see it in the output. It sounds like a computer when it writes, even without additional context. And it doesn't. The other thing that I have not been able to figure out is, I think it's really important in one blog post to link to other blog posts that I've written. Just because the knowledge builds on itself, and obviously outside as well. But I haven't been able to figure out how to get it to link effectively.

• 19:08Claire Vo?

  Well, I think this is a common feeling with AI-generated writing. No one is satisfied with style. Even when style is exceptional, I think I've seen examples, especially of some of the newer commercial models, actually writing really lovely prose and really lovely language. It's just, it's so personal, what your style is and how you would write something, the rhythm in which you would write it, how would you punctuate and break line? All that kind of stuff is so personal that I have, like you, had a very, very hard time getting it to write like me. And I think even harder, which is why I appreciate that you're not yet posting this. It cannot, it can't tweet like me. I can't, I cannot.

• 19:51Speaker 00

  No.

• 19:52Claire Vo?

  The short ones, the short ones are the hardest, you know? I guess they say that about, about writing, writing generally. Have you felt like any of the models have done better or worse at writing like you? Or is it just like, they only get 70, 80% there and I just accept the fact that I'm gonna have to rewrite things?

• 20:11Speaker 00

  Well, they have different voices. I don't think any of them are close. Like, I think Gemini is more clinical, is the way that I put it.

• 20:22Claire Vo?

  I agree.

• 20:22Speaker 00

  Claude is more warm and verbose. Yeah, very, very garrulous. Like, just wants to keep talking and wants really long sentences and really long paragraphs. And OpenAI, I think the models each have slightly different personalities. So there, I don't think there's like a single characterization. So I've been, I think I've been iterating to, I used to use Claude 3.5 a ton. And I uploaded all of my blog posts in a project and I, and then I'd have it iterate there. Now I can kind of do it with Claude code or using this prompt. So that's a little less useful. But what I've found is,

• 21:03Speaker 00

  You really need to add your own voice and then you need to tell the AI to keep the things that are wrong, right? Like, it's kind of a funny thing to say, but as you were saying, Claire, before, the way that you punctuate, I really like ampersands, right? And I like adding spaces before colons. And I like starting certain sentences with, or having little incomplete clauses, because I think they keep the reader moving. But an AI won't do that. An AI will only deliver you a grammatically perfect specimen.

• 21:36Claire Vo?

  Yeah, we're gonna have one, one very nerdy English language moment, which is, I like to start paragraphs with a conjunction. I love a "and" or a "but".

• 21:46Speaker 00

  Yeah, it pulls you in.

• 21:49Claire Vo?

  So, okay, you and I are gonna work, we'll, we'll build like a, a, a micro SaaS on good, good writing models and prompts that, that people can use. So, okay, so, we accept that it's not gonna write exactly like you, but you've created this grading process to say, well, it's at least good. And so I'd curious, can you walk us through how it gets to an A minus 91?

• 22:16Speaker 00

  Yeah.

• 22:16Claire Vo?

  As an A plus student, I don't know, a 91 would really stress me.

• 22:23Claire Vo?

  Tell me how you kind of wrote the prompt and then why you picked like A minus as, as your bar.

• 22:29Speaker 00

  Yeah, for sure. Okay, so, the way I wrote the prompt, I told it what I wanted. And I asked an AI to critique, I think I asked Gemini to critique Claude's output. So it's kind of using a student teacher critique model. And then what it does is, we'll walk through the prompt in a second, but it goes through three grading attempts. So it reads a file, gives it a grade and a score. And then the things that are the most important that I found particularly for readers are the hook, which is the first few sentences, or the lead, you might call it. And then the last is the conclusion and making sure it ties back, because then you have a complete, you have a complete post. And so it goes through this three times, right? And so you can actually see, like here, it gave itself a 90 and then a 91.

• 23:12Speaker 00

  And then at that point, it basically was good enough, it was satisfied with the hook. So, if we, uh, let's see, if we read the blog post generator...

• 23:25Speaker 00

  You can see what it does at a high level, right? So it finds the blog post, it generates an initial blog post, grades it like an AP English teacher, improves, and then auto-generated a URL-friendly slug, so it actually writes it in the right format. And then it can use OpenAI or Ollama. And then the prompt is here. "You are an expert blog writer specializing in technology and business content." And then here I add in the blog posts, and it kind of shows the patterns. What it also does is it dynamically calculates the number of paragraphs from relevant posts and uses Ollama to summarize the stylistic patterns of those related posts.

• 24:05Speaker 00

  So I might write a little bit differently when I'm targeting a Web3 or a crypto audience than say I might, when I'm analyzing the public disclosures of a company, a snowflake just announced earnings, let's say. And so it's dynamically injecting that here. It shows a bunch of different examples, and then, you know, here's what I think makes my blog post tick, right? 500 words or less, like 49 seconds with a reader, no section headers. I ran an analysis of dwell time as a function of how many headers there were, and it turns out headers were terrible for dwell time, people just bailed. Flowing paragraphs, each paragraph transitions smoothly to the next.

• 24:45Speaker 00

  Actually, the AI consistently critiques my transitions and says they're too harsh. And going back to the A minus point that you made before, I think I lose five or six points because of my transitions, because they're abrupt. And then, you know, limit each paragraph to at most two long sentences. And then the structure of the blog post.

• 25:05Claire Vo?

  I think this is a really interesting story at the top, and I want to make sure people don't miss it. I've seen this before, which is like, take this example and describe it back to me and use it. And so you're saying, "I'm writing on this topic, go find the blog posts like this topic, analyze them for format. Like, what is, what is the structure? How am I writing things? And match, stylistically, match this subset of my blog posts, because I do vary style by topic."

• 25:34Speaker 00

  Exactly right. Exactly right.

• 25:36Claire Vo?

  Okay, and then two sentences. I was not expecting this two sentences per paragraph thing. I like it.

• 25:42Speaker 00

  Yeah.

• 25:43Claire Vo?

  I have one more question for you as somebody who did take AP English. So this is

• 25:49Claire Vo?

  Did you actually, do they publish the AP English like grading standards for the tests? Like, did you integrate any of that? Is it just sufficient enough to say AP English teacher? I'm just curious how deep you went.

• 26:00Speaker 00

  Yeah, I just said AP English teacher. I figured there are enough people leaking.

• 26:06Speaker 00

  Either like the scoring rubrics or essays that scored fives or whatever it was.

• 26:11Claire Vo?

  Got it.

• 26:12Speaker 00

  There's good underlying data.

• 26:13Claire Vo?

  Okay, so this is for writing it. And then what about for grading it? Do you have that prompt?

• 26:19Speaker 00

  Here's the grading prompt. So you're an experienced English teacher. Here's a letter grade numerical score. And then here are the evaluations. The hook, which, you know, argument clarity, evidence and examples, paragraph structure, conclusion strength, overall engagement.

• 26:37Claire Vo?

  Got it. And have you ever gotten Bs and Cs?

• 26:41Speaker 00

  Yeah, for sure.

• 26:42Claire Vo?

  Like getting like 91%. I always wonder about this because I do think these models are positively inclined towards telling you you've done good work. I've found that consistently. I've always had to say, be more harsh, be more critical, call out where I'm doing things wrong. So I'm curious, do you actually get high variability in these in these gradings? Or, you know, what has been your experience?

• 27:05Speaker 00

  Yeah, absolutely. So another, so this is one pathway for, I mean, the podcast to blog posts. Data pipeline is one pathway for generating blog posts. Another one is just an idea comes to me. And so then what I'll do is I'll just literally dictate. I'll dictate, I'll put it in and I'll pass it into the blog post generator and then have it grade and there I've seen C minuses, right? Yeah.

• 27:27Claire Vo?

  So it's easier when it's grading itself and a little harder when it's grading you. This is super interesting. And then in the, you do it three loops. Do you also get high variability between the loops? Do you find that that three time process is actually additive to the evaluation?

• 27:44Speaker 00

  I do. I think I often see the first one, like a 91, and then the second one will dip into the BB plus range and then it'll pop back up.

• 27:54Claire Vo?

  Yep.

• 27:54Speaker 00

  So it's a little bit explore, exploit. And again, most of the time for me, it's around those transitions. And most of the time, the verbiosity of those transitions that the AI injects is just catastrophic. I mean, it doubles the length of the blog post. And then the third, the third iteration tends to then kind of reinforce the brevity.

• 28:16Claire Vo?

  Got it. And my kids are too small for AP English to be something that I have to worry about yet. But meta question, you know, everybody's so worried about students using AI to write. This seems like such a more fair way to evaluate writing. I'm curious, do you think we're going to see more and more of this type of evaluation in academic setting? And do you think teachers could benefit from, you know, checking their own work when they're grading these things that are a little harder to put quantitative or qualitative feedback against?

• 28:49Speaker 00

  Yeah, I think it's a great first pass filter. 80% of the work, what's going on grammatically? Are you using sentences and conjunctions and dangling modifiers and all that stuff? I think that the rote analysis of the logic of that language should be handled by an AI. And then I think there's this other part, which is the stylist. I mean, you look at, I was reading E. E. Cummings poems last week. And you look at the creativity of some of those poems.

• 29:21Speaker 00

  And I, you know, I think it only comes after you have the mastery of the language. But you'd want, you'd want teachers to be free to.

• 29:30Speaker 00

  Champion that or encourage it. I think it's really just as important.

• 29:34Claire Vo?

  Yeah. So for the students listening, you know, I still think it's good to learn to write, to read a lot, to learn to write, to write yourself. And if you're looking for a place to practically apply AI to your writing work, maybe it's as a first pass grade. Say, if you were my teacher, how would you grade this? And what feedback would you give me? As opposed to if you were me, how would you write this? Maybe that's the right way to get students starting to use AI in a practical way that still allows you to develop these hard skills that I think are going to be, continue to be super relevant.

• 30:07Speaker 00

  Could not agree with you more. I mean, oftentimes, I don't know about you, but I'll run into writer's block, or I'll have an idea that I really want to convey, but it's just a soup in my mind. And there, an AI will help you iterate and refine. And often, it will give you the germ of an idea, and then you'll take it and add your specific lens to it. But yeah, I think it's a wonderful learning tool because you have the feedback so quickly.

• 30:28Claire Vo?

  Yep, exactly. Okay, so you have shown us, just taking Zoom back, thirty something podcasts you process on a daily basis. You create summaries, you extract themes, you extract tweets, you extract topics. Those topics then go into another Python script that writes a blog post based on some other relevant blog posts in your own blog, writes the blog post, on-demand AP English teacher to grade you three times, and then you take the final pen, and then his AI posts, like, do you have it just like an agent going, "Bada, bop, send hit"?

• 31:07Speaker 00

  That I don't. That would be awesome. But no, that's still done the artisanal way, point and click.

• 31:15Claire Vo?

  You are still copying and pasting with your human fingers.

• 31:19Speaker 00

  Yeah.

• 31:19Claire Vo?

  Okay, this is a great, super practical process. I'm even thinking about ways I can do this to identify future podcast guests or topics that people might want to see. So you've given me some inspiration. I'm going to ask you two wrap-up questions and then get you out of here, back into your terminal. First question, I was reading your 2025 predictions, and you said this is going to be the year we see thirty-person, hundred million. Dollar company. And I'm curious, when you, in your mind's eye, when you imagine that company, what is it, who's in it? Like, what are they doing? How are they operating? What do you imagine that company looks like?

• 31:55Speaker 00

  Yeah, I think it's probably, there's a CEO who's a product person, there's an engineering team of 12 to 15, and then there's probably a couple of customer support slash dev rel people. And maybe there is a salesperson, maybe who's closing some of those bigger contracts, and then a solutions architect is a function of the kind of company. But it will be predominantly software engineering. And then I think the go-to-market motion is PLG bonza, just massive adoption.

• 32:24Claire Vo?

  And do you think the software engineers are largely still focused on product building? Or do you imagine that those software engineers are also enabling the company with tooling and automations and figuring out how one salesperson can do the work of 20? I'm just curious how you think that's going to shake out.

• 32:40Speaker 00

  Oh, absolutely. I think that's right. I mean, you, we were, we were kind of talking about this, but like the ability of a person to come up with a demo and then use AI to critique the demo and test is now so fast. And the ability to take that code and basically move it into production really quickly is also incredibly fast. So I do think there will be a pretty significant like internal platforms enablement function. And whether that's kind of 20% time for a bunch of engineers or a dedicated team of two or three people, a huge amount of leverage there.

• 33:12Claire Vo?

  Yeah, I completely agree. Okay. And then last question. When your AI is grading you unfairly, or writing terribly, or making very long transitions that do not sound like you, what is your prompting technique to get AI to listen?

• 33:29Speaker 00

  I have two AIs duke it out.

• 33:32Speaker 00

  And so I have like a little example of like, this is the input, this is the output that you gave me, this is the output that I want. And then I have Gemini and Claude duke it out and finally kind of decide on, and I'll use a little script to do that, where they'll finally polish a script. It doesn't work all of the time, but I do think switching models helps a ton. It creates a level of generalizability that I haven't been able to replicate as a human.

• 33:56Claire Vo?

  I agree. And I will give you a how I AI tip from a previous guest, Hillary, who like nags the models to each other. So they're like, Gemini, look at this garbage.

• 34:08Speaker 00

  No way.

• 34:08Claire Vo?

  How to, and then they're like, Claude, look at this trash OpenAI gave me. Like, surely you can do that. That's where she calls it Mean Girls. She's like, I mean girls, models, and get them to compete with each other. So maybe you can create a Python-based terminal script to do that and then share it with our audience. Open source that thing.

• 34:29Speaker 00

  Great, great idea for a weekend project this Saturday.

• 34:32Claire Vo?

  Well, this is so helpful. Where can we find you? How can we be helpful to you?

• 34:37Speaker 00

  Oh, I'm on tomtunguz.com. And if you're starting a company within the AI ecosystem, I'd love to hear from you.

• 34:42Claire Vo?

  Great. Well, thank you so much for being here.

• 34:44Speaker 00

  Thanks for having me, Claire.

• 34:46Claire Vo?

  Thanks so much for watching. If you enjoyed this show, please like and subscribe here on YouTube, or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiaipod.com. See you next time.