How a Frontier Team Can Help Your Company Keep Up With AI

Check out Gemini Audio: https://goo.gle/Every-Gemini-Audio Every time a new AI model drops, companies face the same dilemma: Figure out what’s new and how to use it, or focus on getting work done. Every solves this dilemma with a frontier team: a small group that tests new models and turns useful experiments into tools and workflows for the rest of the company. On this week’s episode of The Every Podcast, Natalia Quintero sits down with all seven members of Every’s frontier team to ask what they’re building—from a tabless browser that helps protect your attention to a personal agent orchestrator called Minga—and what they want to try next. Subscribe to Every (free for 14 days): https://every.to/youtube-every-offer?utm_source=podcast&utm_medium=audio&utm_campaign=companyagentepisode Links to resources mentioned in the episode: Follow Every: https://x.com/every Compound Writing plugin: https://every.to/guides/compound-writing Every’s vibe checks: https://every.to/vibe-check Follow Dan Shipper: https://x.com/danshipper Follow Natalia Quintero: https://x.com/NataliaZarina Follow Mike Taylor: https://x.com/hammer_mt Follow Jack Cheng: https://x.com/jackcheng Follow Arielle Shipper: https://x.com/ArielleShipper Follow Katie Parrott: https://x.com/kplikethebird Follow Jannik Jung: https://x.com/JannikJung 0:00 Introduction: Why every company needs a frontier team 2:42 Why the best frontier teams have pirates and architects 4:57 How Head of Evals Mike Taylor builds personal benchmarks 6:46 How Opus edited an explainer video using Slack messages and meeting notes 10:20 Working with AI means protecting other people’s attention 12:26 Why a frontier team needs a “wrangler” like Arielle Shipper 18:58 Why senior editor Jack Cheng built a tabless browser 24:37 How resident writer Katie Parrott teaches her AI writing plugin who the reader is 30:51 Inside engineer Jannik Jung’s personal AI orchestrator 35:41 Compound engineer Kieran Klaassen uses AI to build power tools

• 0:00Speaker 00

  You need a frontier team. Here's why. Every single person in your company is caught in this dilemma. Do I get my work done? Or do I stay up to date with AI and figure out what all these new tools and workflows mean for what work I should do? That's just crazy. It's so hard to figure out. Every single company is struggling with this right now. Because, I mean, on the one hand, you could ignore the frontier and that'll probably work for a little while until you get disrupted by some agent-native version of your product that you didn't see coming. Or you can keep up with the frontier and just chase shiny objects and never build anything that lasts. The reason why you need a frontier team is it separates things out. So you get this nice separation of concerns where you're both keeping up with what's

• 0:44Speaker 00

  going on on the frontier and you're actually getting your work done. And I had my co-host Natalia, welcome Natalia.

• 0:52Speaker 01

  Hey, Dan. Good to be here.

• 0:53Speaker 00

  Who is our head of enterprise AI adoption, come in and do a little bit of digging into our frontier team. So we've been running the frontier team at every for, I guess, a couple of months now, and it has been kind of transformative. And I think Natalia is one of the best people to come in and take a peek and be like, what are we actually doing?

• 1:16Speaker 01

  So actually, I might turn the tables a little bit to you because it was your idea to have a frontier team.

• 1:22Speaker 00

  Yeah, I mean, yeah, the frontier team, I think, has been a huge unlock and it's because of this separation that I've been talking about. I think there's so many people at every, like me, who just love playing with new things and that's super important. But if that's all you're doing, then you're not going to make progress as a business. Like, you actually do need to go execute on products and services, things that people can rely on. And it felt like we needed to choose one or the other, either just like constantly be playing with new stuff or make a product that we just build once and then we add features to and we support forever. And the frontier team was in a sort of an attempt to say, okay, what if we take all the people like me who love all the new stuff and we just unleash us to just run experiments?

• 2:04Speaker 00

  And at the, you know, at the low end, the experiments are just, they're just really good content. They just teach us something interesting and they become good tweets or YouTube videos or anything like that. And then on the high end, they, they get pushed up from, from the frontier into the products that we build into the services that we offer, without the rest of the company feeling like they always had to be paying attention to every single model that drops and every single new experiment that we're running. So I felt like it's allowed me and the other people on the frontier team the space to just figure out what the future looks like without forcing that on the rest of the company until it's actually ready for them to pay attention to it.

• 2:42Speaker 01

  Now, one of the things that you seem to have figured out pretty early in the formation of the frontier team is that you wanted to have both pirates and architects. Can you describe what that is?

• 2:53Speaker 00

  I think there's two archetypes that work really well together, pirates and architects. Pirates are people like me who are just like, I just want to like go really fast and I'm going to do stuff that's, it's kind of be a little bit sloppy, but I'm going to try like a billion things in the, in the space of a couple of days. And I'm going to figure out what's useful, but it's going to be a mess. Architects are people who are really good at being like, there's a whole big messy thing.

• 3:20Speaker 00

  What would it look like to compress it a little bit and form it into a shape that actually works, that, that we can actually use? Because what we try to do with, on the frontier team is we're experimenting with lots of stuff. Most of that stuff gets thrown out and some of it ends up getting pushed into the rest of the team to see if the rest of the team likes it. And at that point, like, there's a point, right before we do that, that an architect becomes really useful to come in and say like, this is messy, we can't actually maintain this and it wouldn't work for these five different ways for the, the people internally at the company. And helps turn it into a system that we can actually understand and build on instead of just being like a kind of one-off vibe-coded project.

• 4:02Speaker 01

  Dan, what do you think is, has been the most impactful thing you've seen about having a frontier team at every?

• 4:09Speaker 00

  I think it lets us, it lets us move incredibly quickly on what's new without distracting the whole team. And that has a deeply, it's like confidence building for the team because you feel like, hey, I'm going to know when things change, we're going to, we'll be able to handle it. And I'm not feeling crazy and frazzled and distracted all the time. And I think that is like the core important thing that affects the day-to-day experience of building and working and running a company in this environment.

• 4:42Speaker 01

  Absolutely. Thanks, Dan.

• 4:44Speaker 00

  Thank you.

• 4:57Speaker 01

  So Mike Taylor, welcome. We're so excited to learn about the work that you're doing on the frontier team as the head of evals.

• 5:06Speaker 01

  So can you tell us a little bit of what you're doing as part of the frontier team?

• 5:10Speaker 02

  Yeah, so it feels like it's different every week or maybe every day, sometimes every hour. But the, the goal of the frontier team is really just to kind of push the models to the limits and see what is now possible and like, what is a new way to work, given that the models are constantly getting better and there's still a lot of capability overhang. What I mean by that is the models are able to do much more than we have had time to try. And, and so we're trying to like find those edges.

• 5:45Speaker 01

  And specifically, what is your title as part of the frontier team?

• 5:49Speaker 02

  Yeah, so I made up my own job title, which is very me, but it's head of evals. So what that means, evals is short for evaluations. And so it's my job to kind of take the kind of vibe checks that we've been doing with models that are more like qualitative and then try and put some numbers behind them. So I've been working with a lot of the team to help them build their own personal benchmarks, including with you. And, you know, we're trying to roll that out as like more of an internal product initially to get more people involved with testing the models. And I could talk a bit more about that. But also just running more experiments, like when we say that AI is sycophantic, like,

• 6:34Speaker 02

  what do we mean by that? How do we define that? And can we test that? You know, those sorts of things. And then just also just like pushing it a little bit further. So.

• 6:43Speaker 01

  And so what are you most excited about now?

• 6:46Speaker 02

  Yeah, one of the things I've been finding more is that Opus is like very good at video editing. And this is, you know, maybe obvious to some people who have been testing it, but I've been testing AI on video editing for a while. I have a popular Udemy course and it's like the worst part of that side project is having to edit the videos afterwards. So for me, I've been testing a bunch and it's like finally working. And that's opening up a lot of, like, a lot that I can do that I couldn't previously have done. So one of the things I did recently was I made an explainer video for the checks product, for the personal benchmark product that we're making.

• 7:28Speaker 02

  I asked Opus to go back through all my Slack messages, go back through all my granola notes, and then pull the narrative of the video together with receipts, right? Like with references to the specific things that I'd said in Slack or in meetings. And then it like cut that whole video together and like then I had an explainer video. So I feel like that, that's opening up a lot for people who are like me, who are maybe too busy running experiments to ever like tell anyone what we're doing.

• 7:55Speaker 01

  So cool. Can you show us an example?

• 7:58Speaker 02

  So this is the one I was talking about. So this prompt goes back a really, really long way. But I went back and forth with, with Opus on this. And initially it was in UltraCode, which if you don't know, is like one of the settings that, that is like the highest effort setting. And so it will use hundreds of agents, basically, that it's orchestrating to do the task. And the reason I chose UltraCode for this is I knew that had a lot of context that I wanted it to read. And like one model can't read all of that context. So what it does is it sent hundreds of agents, you know, one agent per meeting that I had,

• 8:42Speaker 02

  and then pulled everything back into this like library, essentially.

• 8:47Speaker 02

  All these are all the sources, right? So you can see all the different calls I had with different people and it found all the ones that are relevant, right? But now, now we have it all. We have this big library of sources. But it didn't just do that, right? Like it, it also then created this story spine, which is like, it tried to boil it down to what is the narrative? Like if someone doesn't know the checks product, what is checks? And it boiled it down to like these 12 sentences. So like personal benchmark is a small set of your own real work saved so that AI models can run on it again. So that's the definition I just gave you earlier. But now we have like the receipts, right? Like I can click in and see like, where did that sentence come from? Back to the insight card and then from the insight card back to the specific things I said in meetings.

• 9:31Speaker 02

  So it's all auditable. And then, and then, you know, it puts everything together and then we have, we have this explainer video, right? Yeah, so.

• 9:42Speaker 02

  So the interesting thing is, so like, see all these screenshots? Like, it went and found those screenshots from my Slack. These are things that I shared, you know, and then like it put everything together. It annotated the screens. It did the voiceover. I used Google Gemini. I gave it a Gemini API key. And so these are the 12 sentences, but, but like shown in video form. And that is, again, pretty amazing. And then I can share that with the rest of the company. And then now they understand like, oh yeah, a score is a count of yeses. Right. So like now they understand the checks product.

• 10:20Speaker 01

  So maybe last question for you would be, you know, as head of emails, you're evaluating a bunch of models. You're seeing what actually works, what the new capabilities are. What is like the cheat sheet that you could give someone? I know it's like late October 2026, so this might be outdated in a matter of days. But what's the, can you give us a cheat sheet for what, what we should know about using models today?

• 10:44Speaker 02

  Yeah. So, so what is my cheat sheet? So I think one thing that people are not doing enough of is just giving all their context over to AI. I think previously, if you've tried this in the past and you've asked AI to look through your call notes, or, you know, maybe been hesitant to give it access to your Google Drive or whatever. And I was that person, like earlier in the year, I didn't have it cooked up to my Gmail or my Slack. And living within the every community, like being in the team, it's, it's like now I'm like full on like AI has access to everything. And I would say like, just make that leap because it's amazing how good it is at picking out good context. Once you give it access. So I'd say like, that's gotten so much better and people need to do more of that.

• 11:28Speaker 02

  And you can trust it more to use its judgment in what it brings into that task. The second thing is that I feel like it's your job. Like now that you're producing a lot more, hopefully if you're, if you're using AI more, it's your job now to protect other people's context. So I'm like regularly accused of saturating the company LinkedIn. Like every channel I'm posting in, it's like, Mike, Mike, Mike. And, and I'm really conscious of that. So creating that video, you know, creating more videos like that, making the work that I'm doing more digestible, I think is now actually my job. And, you know, I'm giving, I'm coming up with good ideas. I'm giving it to Claude. Claude's finding those ideas more automatically for me when I've said them.

• 12:13Speaker 02

  But now I'm like flooding people with new ideas. So that's the other part that I'm working on. I think that that's where a lot of people's jobs are going to go.

• 12:21Speaker 01

  Super cool. Thanks so much for joining us, Mike Taylor.

• 12:23Speaker 02

  Yeah, yeah. Good to talk to you.

• 12:26Speaker 01

  So, welcome Ariel. So excited to have you. And can you tell us what your role is as part of the frontier team at every?

• 12:33Speaker 03

  Yes, I'm officially the frontier wrangler, which means that I help make sure that our experimentation is in some ways organized enough for us to then harvest and synthesize learnings and digest it for the outside world and direct our exploration internally. So I work on the systems and processes that allow us to do that internally. And I partner closely with Dan on that. And then I'm also running my own experimentation. So unlike other folks on the team, I'm less technical, but I'm an operator. And so there's a lot of interesting opportunity for practical systems

• 13:16Speaker 03

  that we can experiment with, using some of these new tools and techniques on the inside that I'm playing around with pretty consistently.

• 13:25Speaker 01

  Why does the frontier team need a wrangler?

• 13:28Speaker 03

  I think one of the cool things about working with folks in the org is that everybody is a meta thinker. People are so creative and they're so excited to just sort of chase the next thing. And that's great. We need people like that. And then we also need a organizational layer to say like, what are we learning from this? And, and how can we actually digest everything that's, that's coming out of these experiments for our audience? And so I think it's pretty important to have a layer that basically looks at everything that people are doing,

• 14:06Speaker 03

  maps it to digestible themes and tries to find some of the meaning in all of this experimentation. And then creates a layer that allows us to turn it into content and products and even concepts that we're teaching in consulting. So it's a way of like harvesting all of this and then translating it into other areas of the business.

• 14:29Speaker 01

  So what are you working on now?

• 14:31Speaker 03

  With all of these models coming out constantly, the frontier of AI capability keeps pushing forward. And that's really exciting. That also means that there's so much to play with and experiment with that we are constantly burning through tokens like wildfire. And that's an important investment in our business and experimentation. But also understanding at a meta level, like what experimentation are we doing? How much money are we spending on that? And what are we getting out of it in return is, is pretty important.

• 15:01Speaker 01

  Can you show us an example of kind of like a recent like insight or maybe process that you've tried to apply lately in, as in your job as a wrangler?

• 15:13Speaker 03

  Yeah, definitely. So this is what the usage dashboard looks like. Some of this is going to be a retrospective because we don't have a full month of spend for October yet. But what this basically allows us to do is understand like, what is the total dollar value that we've spent? What are the tokens? Like, what's the token count that we've spent it on? And then there's actually a breakdown by person. So we created a skill that, that looks, you know, across all of the different harnesses that you're using on your computer to harvest. These are the tokens that you used across each of these harnesses.

• 15:53Speaker 03

  You can also click in and see there's, we're collecting data in real time. So it gives you the actual like model and effort level. And this dashboard also includes a workflow that basically looks across all of your sessions and categorizes at a high level what you spent those tokens on and then runs it by you for approval. So that you can see, you know, both the percentage share of the work, of the token spend that's gone to each different work bucket. And then what the estimated dollar value of those tokens are.

• 16:34Speaker 03

  So you can make a sort of quick calculation of like, oh, like, was that worth it or not?

• 16:39Speaker 01

  All right. And Ariel, maybe last question for you. What are you most excited about next as the frontier team wrangler?

• 16:46Speaker 03

  Um, I, I think what I'm most excited about is as these models get smarter and smarter, my ability to actually build, like the capacity for that grows. It's not a power that I've had before and it feels magical and it feels really exciting. And being able to take some of the ideas that I have and, and will them into existence is actually a totally new thing. So in my previous life as an operator, I would have waited, had to wait for different model companies to add this kind of tracking capability that I'm looking for. Or I would have had to partner with an engineer to do any of this. And now I actually have the ability to create some of it myself. So what I'm looking forward to is as these models get better and better,

• 17:31Speaker 03

  my capacity to, to actually build systems to do this work for us gets better and better. And I'm really excited about diving into that.

• 17:41Speaker 01

  I'm excited to see you, our guest. Thanks for joining us, Ariel.

• 17:44Speaker 03

  Cool. Thanks so much.

• 17:45Speaker 00

  One of the great things about working with AI is you can just talk to it now. If you're interested in groundbreaking voice experiences, you need to check out Gemini Audio. Gemini Audio is the new voice models from Google DeepMind. Gemini 3.5 Transcribe turns speech into clean formatted text. If you say, let's meet Tuesday, no Wednesday, it'll detect the correction and handle it automatically and remove filler words. There's less cleanup between a rough thought and something you can actually use. And now with Gemini 3.8 Live Extended Thinking, you can talk through more complex work.

• 18:28Speaker 00

  It can reason and speak simultaneously, which keeps conversations going while it's working in the background on your behalf. You can even ask follow up questions and give feedback as you go on together. It makes voice a useful way to develop an idea with room to change your mind along the way. You should check out the link in the description and learn more about Gemini 3.5 Transcribe and Gemini 3.8 Live Extended Thinking. And now back to the episode.

• 18:58Speaker 04

  Yeah. So, um, yeah. So I'm, I'm Jack Chang. I'm a senior editor at every. And yeah, part of the frontier team. What, I, I think like my role on the frontier team. I think we're all figuring out what our roles are on the frontier team. And, you know, I've definitely been testing more of the early access models that, that we've been getting. And something I've really started doing more of there is basically just like creating these like interactive experiences and games and things like that. And to just really like try to push at like, what is even capable now?

• 19:43Speaker 04

  With, you know, each new model release, like what can it do that it maybe like wasn't good enough? Like it wasn't good enough that I would even think to try with a model before. And so lately that's kind of meant I'm just like creating video games and things like that. And then the other piece of it is just actually like making my own applications. So, you know, I was finding that I was really getting overwhelmed by my browsers, like tabs and being constantly forced to like context switch. And I was like, well, wouldn't it be nice if I had a browser that didn't have tabs? And that you could like turn off the tabs?

• 20:28Speaker 04

  Um, and I think before I would have maybe like built a Chrome extension or something like that. And but now like the models are so good that I was like, no, I can, I can just build my own. So here is um my browser, basically. Yeah, like I mentioned, it's a tabless browser. And that was the originally like intent is to, you know, have this browser where I'm not sort of like tempted to, you know, switch tabs and open things in the background and like never, you know, get to them. But like, once I had this going, I was like, well, you know, a lot, in order for me to use this day to day,

• 21:06Speaker 04

  I have like, you know, my whole editing workflow that I normally like use um uh ChatGPT in the browser for. So basically, I added this agent pane um that could let me like pick any, you know, any model provider and use any model for editing, which, um, you know, I couldn't really even do with Claude and and the Gemini models because their plugins for Chrome weren't, weren't as good. But there are things like, you know, like just in sort of daily use, I'm like, oh, there are times when I actually do need to like peek at something. And so the latest thing I added was sort of this kind of like peak mode where I could like very quickly temporarily open up a page.

• 21:49Speaker 04

  And then like, you know, like, like look up something and then go back to my document.

• 21:55Speaker 04

  And I, I think like what I'm starting to learn with this is just the way that like, you know, I think we had this concept of like plugins and extensions and, and, and for a while. But like those things never really let you get close to the actual like application and changing how the application worked. And now with sort of the latest generation of like frontier models, it's really like possible to build this like, you know, fully like personalized to you or personalized to your team and, and their workflows, um, application um that, that you couldn't, yeah, you couldn't do before.

• 22:35Speaker 01

  All right. I think maybe a good closing question might be, um, what are you most excited about building next?

• 22:44Speaker 04

  I think, um, I think I'm most excited about um building more things that help basically like protect my attention. And I think, you know, like with all this, um, like, like, first of all, it's like I, I have, uh, you know, I have ADHD, um, have a diagnosis of ADHD. And that's always just been a huge challenge throughout my life. And I've kind of had to come up with like these like adaptive strategies throughout the years in order to manage it. And, and I think like now, you know, it's even more kind of like tempting to kind of just like try to do a million things.

• 23:26Speaker 04

  And, um, and, and yeah, and I do feel like I, I am like doing much, so much more now. But at the same time, I've never felt such strain on my ability to focus and ability to like keep my attention um on something for long enough that, you know, that um it's, it's sort of, yeah, for, for long enough that I think it, it makes a meaningful difference uh in my life. And, you know, experimenting and experimentation is definitely like important to me. But I think there's also this other side of me that's like, yeah, you know, I want to build things that like help me write more, help me like create more beautiful things in the world.

• 24:12Speaker 04

  I want to build things that, you know, connect me closer to like my local community. And so really like thinking about it, not as just like building something for creativity's sake, but like doing it in a way that like also helps, um, you know, reinforce and, and serve and deepen my values.

• 24:35Speaker 01

  Wonderful. Thank you so much for joining us, Jack. Welcome, Katie. Uh, so excited to be back on the pod with you and to be talking about your role as part of the frontier team. What do you do in the frontier team?

• 24:48Speaker 05

  Yeah, so there are a couple of different things that I do on the frontier team. Number one, I'm on the, you know, is I'm on the, the testing team for the new frontier models that come out from OpenAI, Anthropic, Gemini, Gemini, Grok. We, um, you know, we are on the test where we get early access to these models. We're putting them through our workflows and just seeing, okay, what is it like to use this model? So we can turn around and pass that information along to the people who read our vibe checks. So that's kind of one of my lanes. The other lane is writing the vibe checks themselves and in other ways, kind of like sharing out what we're learning on the frontier team.

• 25:28Speaker 05

  So I'm kind of like the resident writer embedded inside the frontier team to write about what the frontier team is learning. And then I'm building stuff myself and that's where stuff like my plugin, Compound Writing, comes in. That's um where you, using new models um that are fine tuned for writing comes in. And that also includes um crash test driving, being a crash test dummy for some of the things that other people on the frontier team are building, like Kiran and um Mike as well.

• 26:02Speaker 01

  And can you give us an example of something that you're working on now?

• 26:06Speaker 05

  Yeah, so right now I am, I'm continuing to build out Compound Writing. And so for folks who don't know, that is my plugin that sort of takes you through the writing process from ideation through planning and outlining, through drafting to finalization. Uh, and the whole thing is up to this point has been built around two core documents. The voice guide, the captures how your voice sounds on like a sentence level and like the word choice that you use. And then style dot M D, which covers um what you, what you write about, how you like to talk about your subject matter. And right now what I'm doing is I'm adding a third document, which actually in hindsight feels very obvious to the writing process.

• 26:51Speaker 05

  And that is audience dot M D. So that, so who is the reader that is ultimately going to be receiving this content? And so I'm adding that to my plugin and saying, okay, how does this change? The, the experience of using this plugin doesn't make it more, more useful. So I can share my screen.

• 27:09Speaker 01

  And so for anyone who's not familiar with uh Katie Parrott's Compound Writing plugin, you can find it on our GitHub and you can just point your AI of choice to the page and you can download it and it'll take you to this. Yes. And so what are we seeing here?

• 27:27Speaker 05

  So this is me setting up my audience dot M D for my column, Working Overtime, which is where I write about my misadventures and regular adventures, um, you know, applying AI in my own working life. So I wanted to set up an audience dot M D folder for, for that work that's specific to this column. And it gives me this readout of who the working overtime audience is. So the, what the territory it covers, you know, the main reader being a combination of like the early seeker who's kind of AI curious, and then that operator who's looking for like practical applications to their day to day work. Something I kind of baked into um how the audience dot M D is structured

• 28:12Speaker 05

  is the idea of the hero's journey, uh, which I really like. Every piece of reading should take the reader on their own hero's journey in some form or other. You're looking to enact some kind of transformation in them. And so I wanted to include that in my audience M D. Um, and then what that unlocks for us in Compound Writing, I went ahead and did a pre bake where I just asked uh it to review my most recent working overtime draft for Audience Fit, which was my piece about how I accidentally made all of my context worse by trying to make it better. Um, and it's using, um, it's using the audience M D that I updated today to then give like an overview of what already works. So it says it's clear, context gets an explanation.

• 28:58Speaker 05

  The fix is personal, not um universal, which is something that I've said that I don't like to just prescribe things. I like to describe things. Um, and then um here is um where it loses the seeker side. So this is really good feedback. It's like, where am I not being accessible to people on the earlier side of that spectrum that I might want to be reaching? So this is really good stuff that I'd want to engage with. And then some smaller operator notes, like what was the damage? Like, what was the cost to me, to me when like I wasn't getting the results I wanted out of AI? So this is the kind of like higher visibility, like higher detail feedback and like high, and like,

• 29:40Speaker 05

  like more value that I think we can bring to tools like Compound Writing to help empower people like make better writing.

• 29:47Speaker 01

  Do you have a sense of what your next experiment might be?

• 29:51Speaker 05

  My next experiment, um, so well, I'll be working with Kiran uh on every type, which is his bid to get us all to stop using Google Docs. So I'll be sort of like test driving that and being very annoying in my feedback and my particular preferences as a writer. I'm also kind of like building my own word processor. I always, I joke, it's like a rite of passage, like everyone at a certain point decides to vibe code their own word processor. So I'm like building my own word processor, Wordbetter on the side, just to, because it's easier for me to articulate what I want in a tool, just to build at this point, to just build it myself. And then I can show it to Kiran and say, here's what makes more sense to me.

• 30:34Speaker 05

  So that is kind of what I'm doing now. It's like, I'm just on that part of my journey where I feel like I can build a better word processor than Kiran, so.

• 30:44Speaker 01

  Fantastic. I love it. Well, thank you for Compound Writing. I've personally really enjoyed using it and thank you for joining us. So welcome, Yannick. So excited to have you. And can you tell us, what is your role as part of the frontier team?

• 30:57Speaker 06

  Um, yeah, sure. Like, I'm mostly working as like an architect on some of the projects. Um, I took over a lot of projects from Dan. Um, like, I think my first project here was like working on proof, getting it production ready, um, getting it back to life, I would say. And nowadays, I'm mostly focusing on like compounding, um, basically working on Kate Bench, um, having like a skill which tries to replicate uh the judgment and taste of our editor in chief to, yeah, reduce some of her work, basically.

• 31:34Speaker 01

  And maybe tell us a little bit about that because I think a lot of people, uh, you know, have tried vibe coding something, building a product, and then it can break in all kinds of ways. You're the person that gets brought in to kind of clean up the mess and see what's really there. So what's that experience like?

• 31:52Speaker 06

  I think AI is really good at like bringing something to life. Um, just making assumptions, uh, looking up what to use and just build something that that looks good and potentially also works for that demo case or initial implementation. Um, but I think, I think there's like still need for like the architect role who has like that background knowledge, um, into like knowing how to build stuff that's reliable, um, that's like maintainable over time. Um, how you should like structure code, what libraries to use, um, how to deploy it. Um, know like what's important on like the software side, um, yeah,

• 32:36Speaker 06

  to make it ready for the future, I would say.

• 32:38Speaker 01

  Now, can you give us an example of something you're working on now?

• 32:42Speaker 06

  Sure, I think like, um, I'm currently working on like two work streams. Um, one is compounding with like Kate Bench, I mentioned earlier, and the other one is, um, more explorative where I see how should we work with AI? Alright. So this is my orchestrator, um, it's called Minger. And what I can do here is, uh, create a project. For example, I created a new project called Reply Guy. Um, the idea is that we give, uh, a colleague Becky a tool which she can use to like explore what's trending on Twitter and basically reply to it with one of our new vibe checks, for example.

• 33:27Speaker 06

  And the main goal for this tool was I wanna take the work to like a higher level. So I wanna work on the, on the level of like goals and like a plan, but not focus too much on the individual like coding sessions itself. And

• 33:49Speaker 06

  we have an orchestrator agent here, um, that's like my main interface. So I can talk to that agent, um, discuss what we're trying to build, um, tell it like the requirements, what text like I wanna use. Um, and it can take all of that and break it down into the individual tasks of a plan, basically. And this plan has like uh, separate steps. It shows the dependencies, what needs to happen, in which order. And, um, it has like some autonomy to kickoff work in the background. Um, so it's like implementing it and whenever it needs me, it can ping me for like a decision, um, where it needs my input. It can show me like, um,

• 34:34Speaker 06

  drafts or markups of some UIs where I can give my input on. And I just give it my feedback and it continues working basically by itself.

• 34:43Speaker 01

  Super cool. Um, thanks for sharing. Uh, what do you think your next experiment might be?

• 34:49Speaker 06

  Like for this week, I'm probably gonna focus on this orchestration, uh, idea. There are like some, some, uh, questions I wanna explore. Um, for example, the idea is that this could be like multiplayer as well. So you could invite other people from your team, um, or potentially even the whole company and have like a shared context of what you're working on. And everybody can bring their strength. So like the pirate and architect, um, ideas, like the pirate can bring his ideas and what he wants to experiment on. And the architect can bring like the technical knowledge, um, but like at the same time. So we don't have to like hand off the work after one is done, but we can, yeah, like build the same project at the same time with a shared context.

• 35:34Speaker 06

  Um, and everybody brings in their expertise.

• 35:37Speaker 01

  Great. Thank you so much, Yannick. Really good to see you.

• 35:40Speaker 06

  Thank you.

• 35:41Speaker 01

  So, welcome, Kiran. So excited to be talking about the work that you're doing as part of the Frontier team. What are you doing on the Frontier team?

• 35:51Speaker 07

  Yeah, it's, it's really cool. I love the Frontier team because I basically, when I started with Every, I started building Cora and experimenting with stuff and out of that came combat engineering and so many more things and I just felt this team was already there, but we never gave it a name. And now saying, hey, we're the Frontier team. We're allowed to do experiments to, um, figure out what might work and what might not work. Uh, yeah, it's great. So what I'm doing now is, um, I'm just trying out what we can build with AI today and that changes every time a new model comes out.

• 36:35Speaker 07

  I'm, I'm running an experiment every week, at least one, most of the time, multiple, and I learn something. And the big part is then to share what I learned with the team, uh, with every subscribers to make sure they can adopt or they can like direct whatever they do in the direction that I learned from. So that's the biggest part. Inspire the team to do bigger things, to be more ambitious and it's a little bit less scary if someone already did it and said, yeah, it's actually working. This is a good pattern. Or someone says, this is not a good pattern. You should go this other direction. So

• 37:17Speaker 07

  that's really my job to, yeah, go wide, but also go deep. It's, it's both.

• 37:25Speaker 01

  And I'm, I'd be curious, Kiran, you know, when you started playing with, uh, with the models, kind of like really testing what was possible, could you give us maybe just a could we back up and could you share an example of like how the capabilities have evolved in terms of like what you were testing, say, G P three four, you know, uh, G P T five four, Opus four eight four versus what you are now doing with the models that you have access to?

• 37:50Speaker 07

  Yeah, it's, it's every time something new and, and the whole point is to see it fail. Like it's, it's like, how far can you push it, uh, until it fails? Like, a lot of models are very good and they do a lot of things. So like the hard part is like, how do we test even whether it's good or not and how far can it go? And in the beginning, it was like, can it write code? Wow, it can write code. G P T four suddenly could like write pretty good code. And that was like the first unlock. And then we had Sonnet three five that could write like code across multiple files pretty well, like multiple pieces of code together, um, UI, like you could like create UI with it. Then

• 38:37Speaker 07

  we went a little bit further and started to see agentic work, like models could pass work along, like before it was just like a prompt in and then something came out and then you iterate on it. And the, the agentic work with three seven, Opus three seven with four, four one, like suddenly the agents could do work. And with Opus four five, it shifted again to doing more complicated work. Like we, we could suddenly create, um, like text editors with C R D T and like real time editing and all of that, like which is very complicated, but suddenly an AI

• 39:22Speaker 07

  could just do that in a week. And, and you saw Dan make proof. This was like the proof era, like G P T five five. So suddenly it was like, oh, like we can be more ambitious. We can create bigger things without handholding too much. And especially with Fable now, uh, with Fable five one is that like you have a model that can run even longer, even more deep. Uh, you can trust even more. Like I'm a musician, so I I always try to build a D A W. So I started maybe a year ago and every time a new model comes out, I just try it again and say, hey, can you like, can we work more on it?

• 40:04Speaker 07

  And we're now at a point where I can just do that, which is insane. So maybe I should do a video editor because that's what we need. Yeah.

• 40:13Speaker 01

  Could you tell us a few examples of things that you've built recently? So you are doing a lot of video stuff, for example.

• 40:19Speaker 07

  Yeah, like, yeah, my favorite is the video stuff. So I do a video editor, but it's not just a video editor. It's also like, uh, uh, live streaming, uh, like meeting recorder, like the whole thing that we have so many people at every that say and has such interesting ideas, but like they get lost in meetings. So this is also a way to record all of that, but also give that into a format that editors know, like, uh, but also agent native, obviously. So everything agent native. And the other is, um, an editor, uh, for, uh, writing. So this is also similar to, uh, like proof, but we're like,

• 41:01Speaker 07

  I'm just experimenting. Can we make the next version of proof? Or can we make it better? Can we do even more?

• 41:07Speaker 01

  For anyone else who is on a Frontier team, hey, maybe at their, at their company, right? Maybe it's a startup, maybe it's a large enterprise team. What is one tip that you would have for them about how to succeed as someone who's operating at the frontier embedded in a larger organization?

• 41:27Speaker 07

  Yeah, I think the most important thing of a Frontier team is that you inspire your team, but also you listen to your team. If you do a hundred experiments and don't let it land and don't integrate it, it doesn't work. You need to listen to your team, get inspired by your team and then do stuff and then make sure that some things will be adopted. So it's really about integration. Yes, you should be free and like have the freedom to do everything, but in the end it is about integration and actually bringing it back to the actual organization. So I would urge everyone, make sure people get what you do and don't get overwhelmed because it's very easy to overwhelm the entire organization by just

• 42:11Speaker 07

  dumping hundred experiments in a channel. Make sure some stick. Make sure people understand what you do. Like that's your job as a Frontier team.

• 42:21Speaker 01

  Amazing. Thanks so much, Kiran.

• 42:23Speaker 00

  If you like this video, you should check out every dot T O. We have a two week free trial for anyone who's watching or listening at the link in the description. Every is the only subscription you need to stay at the edge of AI. It is the one subscription that if you're super AI pill and you wanna learn how to use it to do the best work of your life, it's got everything you need. It has education and equipment. On the education side, we review every new model that drops and tell you what's good. On the equipment side, we have software tools specifically made for you, like an agent that helps you AI pill your whole company, all bundled together under one subscription. So get two weeks free now at the link in the description.