Podcasts about Brain trust

In this episode of  Atlanta Business Radio, host Lee Kantor interviews Sherry Deutschmann, founder and CEO of BrainTrust. She shares her journey from cleaning bathrooms and being a single mom to building and selling a $40M company. Deutschmann created BrainTrust to help women entrepreneurs grow successful businesses through small peer groups (“Vaults”) where members openly […]

The reception to our recent post on Code Reviews has been strong. Catch up!Amid a maelstrom of discussion on whether or not AI is killing SaaS, one of the top publicly listed SaaS companies in the world has just reported record revenues, clearing well over $1.1B in ARR for the first time with a 28% margin. As we comment on the pod, Aaron Levie is the rare public company CEO equally at home in both worlds of Silicon Valley and Wall Street/Main Street, by day helping 70% of the Fortune 500 with their Enterprise Advanced Suite, and yet by night is often found in the basements of early startups and tweeting viral insights about the future of agents.Now that both Cursor, Cloudflare, Perplexity, Anthropic and more have made Filesystems and Sandboxes and various forms of “Just Give the Agent a Box” cool (not just cool; it is now one of the single hottest areas in AI infrastructure growing 100% MoM), we find it a delightfully appropriate time to do the episode with the OG CEO who has been giving humans and computers Boxes since he was a college dropout pitching VCs at a Michael Arrington house party.Enjoy our special pod, with fan favorite returning guest/guest cohost Jeff Huber!Note: We didn't directly discuss the AI vs SaaS debate - Aaron has done many, many, many other podcasts on that, and you should read his definitive essay on it. Most commentators do not understand SaaS businesses because they have never scaled one themselves, and deeply reflected on what the true value proposition of SaaS is.We also discuss Your Company is a Filesystem:We also shoutout CTO Ben Kus' and the AI team, who talked about the technical architecture and will return for AIE WF 2026.Full Video EpisodeTimestamps* 00:00 Adapting Work for Agents* 01:29 Why Every Agent Needs a Box* 04:38 Agent Governance and Identity* 11:28 Why Coding Agents Took Off First* 21:42 Context Engineering and Search Limits* 31:29 Inside Agent Evals* 33:23 Industries and Datasets* 35:22 Building the Agent Team* 38:50 Read Write Agent Workflows* 41:54 Docs Graphs and Founder Mode* 55:38 Token FOMO Culture* 56:31 Production Function Secrets* 01:01:08 Film Roots to Box* 01:03:38 AI Future of Movies* 01:06:47 Media DevRel and EngineeringTranscriptAdapting Work for AgentsAaron Levie: Like you don't write code, you talk to an agent and it goes and does it for you, and you may be at best review it. That's even probably like, like largely not even what you're doing. What's happening is we are changing our work to make the agents effective. In that model, the agent didn't really adapt to how we work.We basically adapted to how the agent works. All of the economy has to go through that exact same evolution. Right now, it's a huge asset and an advantage for the teams that do it early and that are kinda wired into doing this ‘cause you'll see compounding returns. But that's just gonna take a while for most companies to actually go and get this deployed.swyx: Welcome to the Lane Space Pod. We're back in the chroma studio with uh, chroma, CEO, Jeff Hoover. Welcome returning guest now guest host.Aaron Levie: It's a pleasure. Wow. How'd you get upgraded to, uh, to that?swyx: Because he's like the perfect guy to be guest those for you.Aaron Levie: That makes sense actually, for We love context. We, we both really love context le we really do.We really do.swyx: Uh, and we're here with, uh, Aaron Levy. Welcome.Aaron Levie: Thank you. Good to, uh, good to be [00:01:00] here.swyx: Uh, yeah. So we've all met offline and like chatted a little bit, but like, it's always nice to get these things in person and conversation. Yeah. You just started off with so much energy. You're, you're super excited about agents.I loveAaron Levie: agents.swyx: Yeah. Open claw. Just got by, got bought by OpenAI. No, not bought, but you know, you know what I mean?Aaron Levie: Some, some, you know, acquihire. Executiveswyx: hire.Aaron Levie: Executive hire. Okay. Executive hire. Say,swyx: hey, that's my term. Okay. Um, what are you pounding the table on on agents? You have so many insightful tweets.Why Every Agent Needs a BoxAaron Levie: Well, the thing that, that we get super excited by that I think is probably, you know, should be relatively obvious is we've, we've built a platform to help enterprises manage their files and their, their corporate files and the permissions of who has access to those files and the sharing collaboration of those files.All of those files contain really, really important information for the enterprise. It might have your contracts, it might have your research materials, it might have marketing information, it might have your memos. All that data obviously has, you know, predominantly been used by humans. [00:02:00] But there's been one really interesting problem, which is that, you know, humans only really work with their files during an active engagement with them, and they kind of go away and you don't really see them for a long time.And all of a sudden, uh, with the power of AI and AI agents, all of that data becomes extremely relevant as this ongoing source of, of answers to new questions of data that will transform into, into something else that, that produces value in your organization. It, it contains the answer to the new employee that's onboarding, that needs to ramp up on a project.Um, it contains the answer to the right thing to sell a customer when you're having a conversation to them, with them contains the roadmap information that's gonna produce the next feature. So all that data. That previously we've been just sort of storing and, and you know, occasionally forgetting about, ‘cause we're only working on the new active stuff.All of that information becomes valuable to the enterprise and it's gonna become extremely valuable to end users because now they can have agents go find what they're looking for and produce new, new [00:03:00] value and new data on that information. And it's gonna become incredibly valuable to agents because agents can roam around and do a bunch of work and they're gonna need access to that data as well.And um, and you know, sometimes that will be an agent that is sort of working on behalf of, of, of you and, and effectively as you as and, and they are kind of accessing all of the same information that you have access to and, and operating as you in the system. And then sometimes there's gonna be agents that are just.Effectively autonomous and kind of run on their own and, and you're gonna collaborate and work with them kind of like you did another person. Open Claw being the most recent and maybe first real sort of, you know, kind of, you know, up updating everybody's, you know, views of this landscape version of, of what that could look like, which is, okay, I have an agent.It's on its own system, it's on its own computer, it has access to its own tools. I probably don't give it access to my entire life. I probably communicate with it like I would an assistant or a colleague and then it, it sort of has this sandbox environment. So all of that has massive implications for a platform that manage that [00:04:00] enterprise data.We think it's gonna just transform how we work with all of the enterprise content that we work with, and we just have to make sure we're building the right platform to support that.swyx: The sort of shorthand I put it is as people build agents, everybody's just realizing that every agent needs a box. Yes.And it's nice to be called box and just give everyone a box.Aaron Levie: Hey, I if I, you know, if we can make that go viral, uh, like I, I think that that terminology, I, that's theswyx: tagline. Every agentAaron Levie: needs a box. Every agent needs a box. If we can make that the headline of this, I'm fine with this. And that's the billboard I wanna like Yeah, exactly.Every agent needs a box. Um, I like it. Can we ship this? Like,swyx: okay, let's do it. Yeah.Aaron Levie: Uh, my work here is done and I got the value I needed outta this podcast Drinks.swyx: Yeah.Agent Governance and IdentityAaron Levie: But, but, um, but, but, you know, so the thing that we, we kind of think about is, um, is, you know, whether you think the number 10 x or a hundred x or whatever the number is, we're gonna have some order of magnitude more agents than people.That's inevitable. It has to happen. So then the question is, what is the infrastructure that's needed to make all those agents effective in the enterprise? Make sure that they are well governed. Make sure they're only doing [00:05:00] safe things on your information. Make sure that they're not getting exposed. The data that they shouldn't have access to.There's gonna be just incredibly spectacularly crazy security incidents that will happen with agents because you'll prompt, inject an agent and sort of find your way through the CRM system and pull out data that you shouldn't have access to. Oh, weJeff Huber: have God,Aaron Levie: right? I mean, that's just gonna happen all over the place, right?So, so then the thing is, is how do you make sure you have the right security, the permissions, the access controls, the data governance. Um, we actually don't yet exactly know in many cases how we're gonna regulate some of these agents, right? If you think about an agent in financial services, does it have the exact same financial sort of, uh, requirements that a human did?Or is it, is the risk fully on the human that was interacting or created the agent? All open questions, but no matter what, there's gonna need to be a layer that manages the, the data they have access to, the workflows that they're involved in, pulling up data from multiple systems. This is the new infrastructure opportunity in the era of agents.swyx: You have a piece on agent identities, [00:06:00] which I think was today, um, which I think a lot of breaking news, the security, security people are talking about, right? Like you basically, I, I always think of this as like, well you need the human you and then there you need the agent. YouAaron Levie: Yes.swyx: And uh, well, I don't know if it's that simple, but is box going to have an opinion on that or you're just gonna be like, well we're just the sort of the, the source layer.Yeah. Let's Okta of zero handle that.Aaron Levie: I think we're gonna have an opinion and we will work with generally wherever the contours of the market end up. Um, and the reason that we're gonna have an opinion more than other topics probably is because one of the biggest use cases for why your agent might need it, an identity is for file system access.So thus we have to kind of think about this pretty deeply. And I think, uh, unless you're like in our world thinking about this particular problem all day long, it might be, you know, like, why is this such a big deal? And the reason why it's a really big deal is because sometimes sort of say, well just give the agent an, an account on the system and it just treats, treat it like every other type of user on the system.The [00:07:00] problem is, is that I as Aaron don't really have any responsibility over anybody else's box account in our organization. I can't see the box account of any other employee that I work with. I am not liable for anything that they do. And they have, I have, I have, you know, strict privacy requirements on everything that they're able to, you know, that, that, that they work on.Agents don't have that, you know, don't have those properties. The person who creates the agent probably is gonna, for the foreseeable future, take on a lot of the liability of what that agent does. That agent doesn't deserve any privacy because, because it's, you know, it can't fully be autonomously operated and it doesn't have any legal, you know, kind of, you know, responsibility.So thus you can't just be like, oh, well I'll just create a bunch of accounts and then I'll, I'll kind of work with that agent and I'll talk to it occasionally. Like you need oversight of that. And so then the question is, how do you have a world where the agent, sometimes you have oversight of, but what if that agent goes and works with other people?That person over there is collaborating with the agent on something you shouldn't have [00:08:00] access to what they're doing. So we have all of these new boundaries that we're gonna have to figure out of, of, you know, it's really, really easy. So far we've been in, in easy mode. We've hit the easy button with ai, which is the agent just is you.And when you're in quad code and you're in cursor, and you're in Codex, you're just, the agent is you. You're offing into your services. It can do everything you can do. That's the easy mode. The hard mode is agents are kind of running on their own. People check in with them occasionally, they're doing things autonomously.How do you give them access to resources in the enterprise and not dramatically increased the security risk and the risk that you might expose the wrong thing to somebody. These are all the new problems that we have to get solved. I like the identity layer and, and identity vendors as being a solution to that, but we'll, we'll need some opinions as well because so many of the use cases are these collaborative file system use cases, which is how do I give it an agent, a subset of my data?Give it its own workspace as well. ‘cause it's gonna need to store off its own information that would be relevant for it. And how do I have the right oversight into that? [00:09:00]Jeff Huber: One thing, which, um, I think is kind interesting, think about is that you know, how humans work, right? Like I may not also just like give you access to the whole file.I might like sit next to you and like scroll to this like one part of the file and just show you that like one part and like, you know,swyx: partial file access.Jeff Huber: I'm just saying I think like our, like RA does seem to be dead, right? Like you wanna say something is dead uhhuh probably RA is dead. And uh, like the auth story to me seems like incredibly unsolved and unaddressed by like the existing state of like AI vendors.ButAaron Levie: yeah, I think, um, we're, I mean you're taking obviously really to level limit that we probably need to solve for. Yeah. And we built an access control system that was, was kind of like, you know, its own little world for, for a long time. And um, and the idea was this, it's a many to many collaboration system where I can give you any part of the file system.And it's a waterfall model. So if I give you higher up in the, in the, in the system, you get everything below. And that, that kind of created immense flexibility because I can kind of point you to any layer in the, in the tree, but then you're gonna get access to everything kind of below it. And that [00:10:00] mostly is, is working in this, in this world.But you do have to manage this issue, which is how do I create an agent that has access to some of my stuff and somebody else's stuff as well. Mm-hmm. And which parts do I get to look at as the creator of the agent? And, and these are just brand new problems? Yeah. Crazy. And humans, when there was a human there that was really easy to do.Like, like if the three of us were all sharing, there'd be a Venn diagram where we'd have an overlapping set of things we've shared, but then we'd have our own ways that we shared with each other. In an agent world, somebody needs to take responsibility for what that agent has access to and what they're working on.These are like the, some of the most probably, you know, boring problems for 98% of people on, on the internet, but they will be the problems that are the difference between can you actually have autonomous agents in an enterprise contextswyx: Yeah.Aaron Levie: That are not leaking your data constantly.swyx: No. Like, I mean, you know, I run a very, very small company for my conference and like we already have data sensitivity issues.Yes. And some of my team members cannot see Yes. Uh, the others and like, I can't imagine what it's like to run a Fortune 500 and like, you have to [00:11:00] worry about this. I'm just kinda curious, like you, you talked to a lot like, like 70, 80% of your cus uh, of the Fortune 500, your customers.Aaron Levie: Yep. 67%. Just so we're being verySEswyx: precise.So Yeah. I'm notAaron Levie: Okay. Okay.swyx: Something I'm rounding up. Yes. Round up. I'm projecting to, forAaron Levie: the government.swyx: I'm projecting to the end of the year.Aaron Levie: Okay.swyx: There you go.Aaron Levie: You do make it sound like, like we, we, well we've gotta be on this. Like we're, we're taking way too long to get to 80%. Well,swyx: no, I mean, so like. How are they approaching it?Right? Because you're, you don't have a, you don't have a final answer yet.Why Coding Agents Took Off FirstAaron Levie: Well, okay, so, so this is actually, this is the stark reality that like, unfortunately is the kinda like pouring the water on the party a little bit.swyx: Yes.Aaron Levie: We all in Silicon Valley are like, have the absolute best conditions possible for AI ever.And I think we all saw the dke, you know, kind of Dario podcast and this idea of AI coding. Why is that taken off? And, and we're not yet fully seeing it everywhere else. Well, look, if you just like enumerated the list of properties that AI coding has and then compared it to other [00:12:00] knowledge work, let's just, let's just go through a few of them.Generally speaking, you bring on a new engineer, they have access to a large swath of the code base. Like, there's like very, like you, just, like new engineer comes on, they can just go and find the, the, the stuff that they, they need to work with. It's a fully text in text out. Medium. It's only, it's just gonna be text at the end of the day.So it's like really great from a, from just a, uh, you know, kinda what the agent can work with. Obviously the models are super trained on that dataset. The labs themselves have a really strong, kind of self-reinforcing positive flywheel of why they need to do, you know, agent coding deeply. So then you get just better tooling, better services.The actual developers of the AI are daily users of the, of the thing that they're we're working on versus like the, you know, probably there's only like seven Claude Cowork legal plugin users at Anthropic any given day, but there's like a couple thousand Claude code and you know, users every single day.So just like, think about which one are they getting more feedback on. All day long. So you just go through this list. You have a, you know, everybody who's a [00:13:00] developer by definition is technical so they can go install the latest thing. We're all generally online, or at least, you know, kinda the weird ones are, and we're all talking to each other, sharing best practices, like that's like already eight differences.Versus the rest of the economy. Every other part of the economy has like, like six to seven headwinds relative to that list. You go into a company, you're a banker in financial services, you have access to like a, a tiny little subset of the total data that's gonna be relevant to do your job. And you're have to start to go and talk to a bunch of people to get the right data to do your job because Sally didn't add you to that deal room, you know, folder.And that that, you know, the information is actually in a completely different organization that you now have to go in and, and sort of run into. And it's like you have this endless list of access controls and security. As, as you talked about, you have a medium, which is not, it's not just text, right? You have, you have a zoom call that, that you're getting all of the requirements from the customer.You have a lot of in-person conversations and you're doing in-person sales and like how do you ever [00:14:00] digitize all of that information? Um, you know, I think a lot of people got upset with this idea that the code base has all the context, um, that I don't know if you follow, you know, did you follow some of that conversation that that went viral?Is like, you know, it's not that simple that, that the code base doesn't have all the knowledge, but like it's a lot, you're a lot better off than you are with other areas of knowledge work. Like you, we like, we like have documentation practices, you write specifications. Those things don't exist for like 80% of work that happens in the enterprise.That's the divide that we have, which is, which is AI coding has, has just fully, you know, where we've reached escape velocity of how powerful this stuff is, and then we're gonna have to find a way to bring that same energy and momentum, but to all these other areas of knowledge work. Where the tools aren't there, the data's not set up to be there.The access controls don't make it that easy. The context engineering is an incredibly hard problem because again, you have access control challenges, you have different data formats. You have end users that are gonna need to kind of be kind of trained through this as opposed to their adopting [00:15:00] these tools in their free time.That's where the Fortune 500 is. And so we, I think, you know, have to be prepared as an industry where we are gonna be on a multi-year march to, to be able to bring agents to the enterprise for these workflows. And I think probably the, the thing that we've learned most in coding that, that the rest of the world is not yet, I think ready for, I mean, we're, they'll, they'll have to be ready for it because it's just gonna inevitably happen is I think in coding.What, what's interesting is if you think about the practice of coding today versus two years ago. It's probably the most changed workflow in maybe the history of time from the amount of time it's changed, right? Yeah. Like, like has any, has any workflow in the entire economy changed that quickly in terms of the amount of change?I just, you know, at least in any knowledge worker workflow, there's like very rarely been an event where one piece of technology and work practice has so fundamentally, you know, changed, changed what you do. Like you don't write code, you talk to an agent and it goes and [00:16:00] does it for you, and you may be at best review it.And even that's even probably like, like largely not even what you're doing. What's happening is we are changing our work to make the agents effective. In that model, the agent didn't really adapt to how we work. We basically adapted to how the agent works. Mm-hmm. All of the economy has to go through that exact same evolution.The rest of the economy is gonna have to update its workflows to make agents effective. And to give agents the context that they need and to actually figure out what kind of prompting works and to figure out how do you ensure that the agent has the right access to information to be able to execute on its work.I, you know, this is not the panacea that people were hoping for, of the agent drops in, just automates your life. Like you have to basically re-engineer your workflow to get the most out of agents and, uh, and that, that's just gonna take, you know, multiple years across the economy. Right now it's a huge asset and an advantage for the teams that do it early and that are kinda wired into doing this.‘cause [00:17:00] you'll see compounding returns, but that's just gonna take a while for most companies to actually go and get this deployed.swyx: I love, I love pushing back. I think that. That is what a lot of technology consultants love to hear this sort of thing, right? Yeah, yeah, yeah. First to, to embrace the ai. Yes. To get to the promised land, you must pay me so much money to a hundred percent to adopt the prescribed way of, uh, conforming to the agents.Yes. And I worry that you will be eclipsed by someone else who says, no, come as you are.Aaron Levie: Yeah.swyx: And we'll meet you where you are.Aaron Levie: And, and, and and what was the thing that went viral a week ago? OpenAI probably, uh, is hiring F Dees. Yeah. Uh, to go into the enterprise. Yeah. Yeah. And then philanthropic is embedded at Goldman Sachs.Yeah. So if the labs are having to do this, if, if the labs have decided that they need to hire FDE and professional services, then I think that's a pretty clear indication that this, there's no easy mode of workflow transformation. Yeah. Yeah. So, so to your point, I think actually this is a market opportunity for, you know, new professional services and consulting [00:18:00] firms that are like Agent Build and they, and they kind of, you know, go into organizations and they figure out how to re-engineer your workflows to make them more agent ready and get your data into the right format and, you know, reconstruct your business process.So you're, you're not doing most of the work. You're telling agents how to do the work and then you're reviewing it. But I haven't seen the thing that can just drop in and, and kinda let you not go through those changes.swyx: I don't know how that kind of sales pitch goes over. Yeah. You know, you're, you're saying things like, well, in my sort of nice beautiful walled garden, here's, there's, uh, because here's this, here's this beautiful box account that has everything.Yes. And I'm like, well, most, most real life is extremely messy. Sure. And like, poorly named and there duplicate this outdated s**tAaron Levie: a hundred percent. And so No, no, a hundred percent. And so this is actually No. So, so this is, I mean, we agree that, that getting to the beautiful garden is gonna be tough.swyx: Yeah.Aaron Levie: There's also the other end of the spectrum where I, I just like, it's a technical impossibility to solve. The agent is, is truly cannot get enough context to make the right decision in, in the, in the incredibly messy land. Like there's [00:19:00] no a GI that will solve that. So, so we're gonna have to kind of land in somewhere in between, which is like we all collectively get better at.Documentation practices and, and having authoritative relatively up-to-date information and putting it in the right place like agents will, will certainly cause us to be much better organized around how we work with our information, simply because the severity of the agent pulling the wrong data will be too high and the productivity gain of that you'll miss out on by not doing this will be too high as well, that you, that your competition will just do it and they'll just have higher velocity.So, uh, and, and we, we see this a lot firsthand. So we, we build a series of agents internally that they can kind of have access to your full box account and go off and you give it a task and it can go find whatever information you're looking for and work with. And, you know, thank God for the model progress, but like, if, if you gave that task to an agent.Nine months ago, you're just gonna get lots of bogus answers because it's gonna, it's gonna say, Hey, here's, here are fi [00:20:00] five, you know, documents that all kind of smell like the right thing. And I'm gonna, but I, but you're, you're putting me on the clock. ‘cause my assistant prompt says like, you know, be pretty smart, but also try and respond to the user and it's gonna respond.And it's like, ah, it got the wrong document. And then you do that once or twice as a knowledge worker and you're just neverswyx: again,Aaron Levie: never again. You're just like done with the system.swyx: Yeah. It doesn't work.Aaron Levie: It doesn't work. And so, you know, Opus four six and Gemini three one Pro and you know, whatever the latest five 3G BT will be, like, those things are getting better and better and it's using better judgment.And this sort of like the, all of these updates to the agentic tool and search systems are, are, we're seeing, we're seeing very real progress where the agent. Kind of can, can almost smell some things a little bit fishy when it's getting, you know, we, we have this process where we, we have it go fan out, do a bunch of searches, pull up a bunch of data, and then it has to sort of do its own ranking of, you know, what are the right documents that, that it should be working with.And again, like, you know, the intelligence level of a model six months ago, [00:21:00] it'd be just throwing a dart at like, I'm just, I'm gonna grab these seven files and I, I pray, I hope that that's the right answer. And something like an opus first four five, and now four six is like, oh, it's like, no, that one doesn't seem right relative to this question because I'm seeing some signal that is making that, you know, that's contradicting the document where it would normally be in the tree and who should have access.Like it's doing all of that kind of work for you. But like, it still doesn't work if you just have a total wasteland of data. Like, it's just not, it's just not possible. Partly ‘cause a human wouldn't even be able to do it. So basically if a, if a really, really smart human. Could not do that task in five or 10 minutes for a search retrieval type task.Look, you know, your agent's not gonna be able to do it any better. You see this all day long. SoContext Engineering and Search Limitsswyx: this touches on a thing that just passionate about it was just context engineering. I, I'm just gonna let you ramble or riff on, on context engineering. If, if, if there's anything like he, he did really good work on context fraud, which has really taken over as like the term that people use and the referenceAaron Levie: a hundred percent.We, we all we think about is, is the context rob problem. [00:22:00]Jeff Huber: Yeah, there's certainly a lot of like ranking considerations. Gentech surgery think is incredibly promising. Um, yeah, I was trying to generate a question though. I think I have a question right now. Swyx.Aaron Levie: Yeah, no, but like, like I think there was this moment, um, you know, like, I don't know, two years ago before, before we knew like where the, the gotchas were gonna be in ai and I think someone was like, was like, well, infinite context windows will just solve all of these problems and ‘cause you'll just, you'll just give the context window like all the data and.It's just like, okay, I mean, maybe in 2035, like this is a viable solution. First of all, it, it would just, it would just simply cost too much. Like we just can't give the model like the 5,000 documents that might be relevant and it's gonna read them all. And I've seen enough to, to start believing in crazy stuff.So like, I'm willing to just say, sure. Like in, in 10 years from now,swyx: never say, never, never.Aaron Levie: In, in 10 years from now, we'll have infinite context windows at, at a thousandth of the price of today. Like, let's just like believe that that's possible, but Right. We're in reality today. So today we have a context engineering [00:23:00] problem, which is, I got, I got, you know, 200,000 tokens that I can work with, or prob, I don't even know what the latest graph is before, like massive degradation.16. Okay. I have 60,000 tokens that I get to work with where I'm gonna get accurate information. That's not a lot of tokens for a corpus of 10 million documents that a knowledge worker might have across all of the teams and all the projects and all the people they work with. I have, I have 10 million documents.Which, you know, maybe is times five pages per document or something like that. I'm at 50 million pages of information and I have 60,000 tokens. Like, holy s**t. Yeah. This is like, how do I bridge the 50 million pages of information with, you know, the couple hundred that I get to work with in that, in that token window.Yeah. This is like, this is like such an interesting problem and that's why actually so much work is actually like, just like search systems and the databases and that layer has to just get so locked in, but models getting better and importantly [00:24:00] knowing when they've done a search, they found the wrong thing, they go back, they check their work, they, they find a way to balance sort of appeasing the user versus double checking.We have this one, we have this one test case where we ask the agent to go find. 10 pieces of information.swyx: Is this the complex work eval?Aaron Levie: Uh, this is actually not in the eval. This is, this is sort of just like we have a bunch of different, we have a bunch of internal benchmark kind of scenarios. Every time we, we update our agent, we have one, which is, I ask it to find all of our office addresses, and I give it the list of 10 offices that we have.And there's not one document that has this, maybe there should be, that would be a great example of the kind of thing that like maybe over time companies start to, you know, have these sort of like, what are the canonical, you know, kind of key areas of knowledge that we need to have. We don't seem to have this one document that says, here are all of our offices.We have a bunch of documents that have like, here's the New York office and whatever. So you task this agent and you, you get, you say, I need the addresses for these 10 offices. Okay. And by the way, if you do this on any, you know, [00:25:00] public chat model, the same outcome is gonna happen. But for a different kind of query, you give it, you say, I need these 10 addresses.How many times should the agent go and do its search before it decides whether or not, there's just no answer to this question. Often, and especially the, the, let's say lower tier models, it'll come back and it'll give you six of the 10 addresses. And it'll, and I'll just say I couldn't find the otherswyx: four.It, it doesn't know what It doesn't know. ItAaron Levie: doesn't know what It doesn't know. Yeah. So the model is just like, like when should it stop? When should it stop doing? Like should it, should it do that task for literally an hour and just keep cranking through? Maybe I actually made up an office location and it doesn't know that I made it up and I didn't even know that I made it up.Like, should it just keep, re should it read every single file in your entire box account until it, until it should exhaust every single piece of information.swyx: Expensive.Aaron Levie: These are the new problems that we have. So, you know, something like, let's say a new opus model is sort of like, okay, I'm gonna try these types of queries.I didn't get exactly what I wanted. I'm gonna try again. I'm gonna, at [00:26:00] some point I'm gonna stop searching. ‘cause I've determined that that no amount of searching is gonna solve this problem. I'm just not able to do it. And that judgment is like a really new thing that the model needs to be able to have.It's like, when should it give up on a task? ‘cause, ‘cause you just don't, it's a can't find the thing. That's the real world of knowledge, work problems. And this is the stuff that the coding agents don't have to deal with. Because they, it just doesn't like, like you're not usually asking it about, you're, you're always creating net new information coming right outta the model for the most part.Obviously it has to know about your code base and your specs and your documentation, but, but when you deploy an agent on all of your data that now you have all of these new problems that you're dealing withJeff Huber: our, uh, follow follow-up research to context ride is actually on a genetic search. Ah. Um, and we've like right, sort of stress tested like frontier models and their ability to search.Um, and they're not actually that good at searching. Right. Uh, so you're sort of highlighting this like explore, exploit.swyx: You're just say, Debbie, Donna say everything doesn't work. Like,Aaron Levie: well,Jeff Huber: somebody has to be,Aaron Levie: um, can I just throw out one more thing? Yeah. That is different from coding and, and the rest [00:27:00] of the knowledge work that I, I failed to mention.So one other kind of key point is, is that, you know, at the end of the day. Whether you believe we're in a slop apocalypse or, or whatever. At the end of the day, if you, if you build a working product at the end of, if you, if you've built a working solution that is ultimately what the customer is paying for, like whether I have a lot of slop, a little slop or whatever, I'm sure there's lots of code bases we could go into in enterprise software companies where it's like just crazy slop that humans did over a 20 year period, but the end customer just gets this little interface.They can, they can type into it, it does its thing. Knowledge work, uh, doesn't have that property. If I have an AI model, go generate a contract and I generate a contract 20 times and, you know, all 20 times it's just 3% different and like that I, that, that kind of lop introduces all new kinds of risk for my organization that the code version of that LOP didn't, didn't introduce.These are, and so like, so how do you constrain these models to just the part that you want [00:28:00] them to work on and just do the thing that you want them to do? And, and, you know, in engineering, we don't, you can't be disbarred as an engineer, but you could be disbarred as a lawyer. Like you can do the wrong medical thing In healthcare, you, there's no, there's no equivalent to that of engineering.Like, doswyx: you want there to be, because I've considered softwareJeff Huber: engineer. What's that? Civil engineering there is, right? NotAaron Levie: software civil engineer. Sure. Oh yeah, for sure. But like in any of our companies, you like, you know, you'll be forgiven if you took down the site and, and we, we will do a rollback and you'll, you'll be in a meeting, but you have not been disbarred as an engineer.We don't, we don't change your, you know, your computer science, uh, blameJeff Huber: degree, this postmortem.Aaron Levie: Yeah, exactly. Exactly. So, so, uh, now maybe we collectively as an industry need to figure out like, what are you liable for? Not legally, but like in a, in a management sense, uh, of these agents. All sorts of interesting problems that, that, that, uh, that have to come out.But in knowledge work, that's the real hostile environments that we're operating in. Hmm.swyx: I do think like, uh, a lot of the last year's, 2025 story was the rise of coding agents and I think [00:29:00] 2026 story is definitely knowledge work agents. Yes. A hundredAaron Levie: percent.swyx: Right. Like that would, and I think open claw core work are just the beginning.Yes. Like it's, the next one's gonna just gonna be absolute craziness.Aaron Levie: It it is. And, and, uh, and it's gonna be, I mean, again, like this is gonna be this, this wave where we, we are gonna try and bring as many of the practices from coding because that, that will clearly be the forefront, which is tell an agent to go do something and has an access to a set of resources.You need to be responsible for reviewing it at the end of the process. That to me is the, is the kind of template that I just think goes across knowledge, work and odd. Cowork is a great example. Open Closet's a great example. You can kind of, sort of see what Codex could become over time. These are some, some really interesting kind of platforms that are emerging.swyx: Okay. Um, I wanted to, we touched on evals a little bit. You had, you had the report that you're gonna go bring up and then I was gonna go into like, uh, boxes, evals, but uh, go ahead. Talk about your genetic search thing.Jeff Huber: Yeah. Mostly I think kinda a few of the insights. It's like number one frontier model is not good at search.Humans have this [00:30:00] natural explore, exploit trade off where we kinda understand like when to stop doing something. Also, humans are pretty good at like forgetting actually, and like pruning their own context, whereas agents are not, and actually an agent in their kind of context history, if they knew something was bad and they even, you could see in the trace the reason you trace, Hey, that probably wasn't a good idea.If it's still in the trace, still in the context, they'll still do it again. Uhhuh. Uh, and so like, I think pruning is also gonna be like, really, it's already becoming a thing, right? But like, letting self prune the con windowsswyx: be a big deal. Yeah. So, so don't leave the mistake. Don't leave the mistake in there.Cut out the mistake but tell it that you made a mistake in the past and so it doesn't repeat it.Jeff Huber: Yeah. But like cut it out so it doesn't get like distracted by it again. ‘cause really, you know, what is so, so it will repeat its mistake just because it's been, it's inswyx: theJeff Huber: context. It'sAaron Levie: in the context so much.That's a few shot example. Even if it, yeah.Jeff Huber: It's like oh thisAaron Levie: is a great thing to go try even ifJeff Huber: it didn't work.Aaron Levie: Yeah,Jeff Huber: exactly.Aaron Levie: SoJeff Huber: there's like a bunch of stuff there. JustAaron Levie: Groundhogs Day inside these models. Yeah. I'm gonna go keep doing the same wrongJeff Huber: thing. Covering sense. I feel like, you know, some creator analogy you're trying like fit a manifold in latent space, which kind is doing break program synthesis, which is kinda one we think about we're doing right.Like, you know, certain [00:31:00] facts might be like sort of overly pitting it. There are certain, you know, sec sectors of latent space and so like plug clean space. Yeah. And, uh, andswyx: so we have a bell, our editor as a bell every time you say that. SoJeff Huber: you have, you have to like remove those, likeswyx: you shoulda a gong like TPN or something.IfJeff Huber: we gong, you either remove those links to like kinda give it the freedom, kind of do what you need to do. So, but yeah. We'll, we'll release more soon. That'sAaron Levie: awesome.Jeff Huber: That'll, that'll be cool.swyx: We're a cerebral podcast that people listen to us and, and sort of think really deep. So yeah, we try to keep it subtle.Okay. We try to keep it.Aaron Levie: Okay, fine.Inside Agent Evalsswyx: Um, you, you guys do, you guys do have EVs, you talked about your, your office thing, but, uh, you've been also promoting APEX agents and complex work. Uh, yeah, whatever you, wherever you wanna take this just Yeah. How youAaron Levie: Apex is, is obviously me, core's, uh, uh, kind of, um, agent eval.We, we supported that by sort of. Opening up some data for them around how we kind of see these, um, data workspaces in, in the, you know, kind of regular economy. So how do lawyers have a workspace? How do investment bankers have a workspace? What kind of data goes into those? And so we, [00:32:00] we partner with them on their, their apex eval.Our own, um, eval is, it's actually relatively straightforward. We have a, a set of, of documents in a, in a range of industries. We give the agent previously did this as a one shot test of just purely the model. And then we just realized we, we need to, based on where everything's going, it's just gotta be more agentic.So now it's a bit more of a test of both our harness and the model. And we have a rubric of a set of things that has to get right and we score it. Um, and you're just seeing, you know, these incredible jumps in almost every single model in its own family of, you know, opus four, um, you know, sonnet four six versus sonnet four five.swyx: Yeah. We have this up on screen.Aaron Levie: Okay, cool. So some, you're seeing it somewhere like. I, I forget the to, it was like 15 point jump, I think on the main, on the overall,swyx: yes.Aaron Levie: And it's just like, you know, these incredible leaps that, that are starting to happen. Um,swyx: and OP doesn't know any, like any, it's completely held out from op.Aaron Levie: This is not in any, there's no public data which has, you know, Ben benefits and this is just a private eval that we [00:33:00] do, and then we just happen to show it to, to the world. Hmm. So you can't, you can't train against it. And I think it's just as representative of. It's obviously reasoning capabilities, what it's doing at, at, you know, kind of test time, compute capabilities, thinking levels, all like the context rot issues.So many interesting, you know, kind of, uh, uh, capabilities that are, that are now improvingswyx: one sector that you have. That's interesting.Industries and Datasetsswyx: Uh, people are roughly familiar with healthcare and legal, but you have public sector in there.Aaron Levie: Yeah.swyx: Uh, what's that? Like, what, what, what is that?Aaron Levie: Yeah, and, and we actually test against, I dunno, maybe 10 industries.We, we end up usually just cutting a few that we think have interesting gains. All extras, won a lot of like government type documents. Um,swyx: what is that? What is it? Government type documents?Aaron Levie: Government filings. Like a taxswyx: return, likeAaron Levie: a probably not tax returns. It would be more of what would go the government be using, uh, as data.So, okay. Um, so think about research that, that type of, of, of data sets. And then we have financial services for things like data rooms and what would be in an investment prospectus. Uhhuh,swyx: that one you can dog food.Aaron Levie: Yeah, exactly. Exactly. Yes. Yes. [00:34:00] So, uh, so we, we run the models, um, in now, you know, more of an agent mode, but, but still with, with kinda limited capacity and just try and see like on a, like, for like basis, what are the improvements?And, and again, we just continue to be blown away by. How, how good these models are getting.swyx: Yeah, I mean, I think every serious AI company needs something like that where like, well, this is the work we do. Here's our company eval. Yeah. And if you don't have it, well, you're not a serious AI company.Aaron Levie: There's two dimensions, right?So there's, there's like, how are the models improving? And so which models should you either recommend a customer use, which one should you adopt? But then every single day, we're making changes to our agents. And you need to knowswyx: if you regressed,Aaron Levie: if you know. Yeah. You know, I've been fully convinced that the whole agent observability and eval space is gonna be a massive space.Um, super excited for what Braintrust is doing, excited for, you know, Lang Smith, all the things. And I think what you're going to, I mean, this is like every enter like literally every enterprise right now. It's like the AI companies are the customers of these tools. Every enterprise will have this. Yeah, you'll just [00:35:00] have to have an eval.Of all of your work and like, we'll, you'll have an eval of your RFP generation, you'll have an eval of your sales material creation. You'll have an eval of your, uh, invoice processing. And, and as you, you know, buy or use new agentic systems, you are gonna need to know like, what's the quality of your, of your pipeline.swyx: Yeah.Aaron Levie: Um, so huge, huge market with agent evals.swyx: Yeah.Building the Agent Teamswyx: And, and you know, I'm gonna shout out your, your team a bit, uh, your CTO, Ben, uh, did a great talk with us last year. Awesome. And he's gonna come back again. Oh, cool. For World's Fair.Aaron Levie: Yep.swyx: Just talk about your team, like brag a little bit. I think I, I think people take these eval numbers in pretty charts for granted, but No, there, I mean, there's, there's lots of really smart people at work during all this.Aaron Levie: Biggest shout out, uh, is we have a, we have a couple folks at Dya, uh, Sidarth, uh, that, that kind of run this. They're like a, you know, kind of tag tag team duo on our evals, Ben, our CTO, heavily involved Yasha, head of ai, uh, you know, a bunch of folks. And, um, evals is one part of the story. And then just like the full, you know, kind of AI.An agent team [00:36:00] is, uh, is a, is a pretty, you know, is core to this whole effort. So there's probably, I don't know, like maybe a few dozen people that are like the epicenter. And then you just have like layers and layers of, of kind of concentric circles of okay, then there's a search team that supports them and an infrastructure team that supports them.And it's starting to ripple through the entire company. But there's that kind of core agent team, um, that's a pretty, pretty close, uh, close knit group.swyx: The search team is separate from the infra team.Aaron Levie: I mean, we have like every, every layer of the stack we have to kind of do, except for just pure public cloud.Um, but um, you know, we, we store, I don't even know what our public numbers are in, you know, but like, you can just think about it as like a lot of data is, is stored in box. And so we have, and you have every layer of the, of the stack of, you know, how do you manage the data, the file system, the metadata system, the search system, just all of those components.And then they all are having to understand that now you've got this new customer. Which is the agent, and they've been building for two types of customers in the past. They've been building for users and they've been building for like applications. [00:37:00] And now you've got this new agent user, and it comes in with a difference of it, of property sometimes, like, hey, maybe sometimes we should do embeddings, an embedding based, you know, kind of search versus, you know, your, your typical semantic search.Like, it's just like you have to build the, the capabilities to support all of this. And we're testing stuff, throwing things away, something doesn't work and, and not relevant. It's like just, you know, total chaos. But all of those teams are supporting the agent team that is kind of coming up with its requirements of what, what do we need?swyx: Yeah. No, uh, we just came from, uh, fireside chat where you did, and you, you talked about how you're doing this. It's, it's kind of like an internal startup. Yeah. Within the broader company. The broader company's like 3000 people. Yeah. But you know, there's, there's a, this is a core team of like, well, here's the innovation center.Aaron Levie: Yeah.swyx: And like that every company kind of is run this way.Aaron Levie: Yeah. I wanna be sensitive. I don't call it the innovation center. Yeah. Only because I think everybody has to do innovation. Um, there, there's a part of the, the, the company that is, is sort of do or die for the agent wave.swyx: Yeah.Aaron Levie: And it only happens to be more of my focus simply because it's existential that [00:38:00] we get it right.swyx: Yeah.Aaron Levie: All of the supporting systems are necessary. All of the surrounding adjacent capabilities are necessary. Like the only reason we get to be a platform where you'd run an agent is because we have a security feature or a compliance feature, or a governance feature that, that some team is working on.But that's not gonna be the make or break of, of whether we get agents right. Like that already exists and we need to keep innovating there. I don't know what the right, exact precise number is, but it's not a thousand people and it's not 10 people. There's a number of people that are like the, the kind of like, you know, startup within the company that are the make or break on everything related to AI agents, you know, leveraging our platform and letting you work with your data.And that's where I spend a lot of my time, and Ben and Yosh and Diego and Teri, you know, these are just, you know, people that, that, you know, kind of across the team. Are working.swyx: Yeah. Amazing.Read Write Agent WorkflowsJeff Huber: How do you, how do you think about, I mean, you talked a lot about like kinda read workflows over your box data. Yep.Right. You know, gen search questions, queries, et cetera. But like, what about like, write or like authoring workflows?Aaron Levie: Yes. I've [00:39:00] already probably revealed too much actually now that I think about it. So, um, I've talked about whatever,Jeff Huber: whatever you can.Aaron Levie: Okay. It's just us. It's just us. Yeah. Okay. Of course, of course.So I, I guess I would just, uh, I'll make it a little bit conceptual, uh, because again, I've already, I've already said things that are not even ga but, but we've, we've kinda like danced around it publicly, so I, yeah, yeah. Okay. Just like, hopefully nobody watches this, um, episode. No.swyx: It's tidbits for the Heidi engaged to go figure out like what exactly, um, you know, is, is your sort of line of thinking.Sure. They can connect the dots.Aaron Levie: Yeah. So, so I would say that, that, uh, we, you know, as a, as a place where you have your enterprise content, there's a use case where I want to, you know, have an agent read that data and answer questions for me. And then there's a use case where I want the agent to create something.And use the file system to create something or store off data that it's working on, or be able to have, you know, various files that it's writing to about the work it's doing. So we do see it as a total read write. The harder problem has so far been the read only because, because again, you have that kind of like 10 [00:40:00] million to one ratio problem, whereas rights are a lot of, that's just gonna come from the model and, and we just like, we'll just put it in the file system and kinda use it.So it's a little bit of a technically easier problem, but the only part that's like, not necessarily technically hard, it is just like it's not yet perfected in the state of the ecosystem is, you know, building a beautiful PowerPoint presentation. It's still a hard problem for these models. Like, like we still, you know, like, like these formats are just, we're not built for.They'reswyx: working on it.Aaron Levie: They're, they're working on it. Everybody's working on it.swyx: Every launch is like, well, we do PowerPoint now.Aaron Levie: We're getting, yeah, getting a lot, getting a lot of better each time. But then you'll do this thing where you'll ask the update one slide and all of a sudden, like the fonts will be just like a little bit different, you know, on two of the slides, or it moved, you know, some shape over to the left a little bit.And again, these are the kind of things that, like in code, obviously you could really care about if you really care about, you know, how beautiful is the code, but at the end, user doesn't notice all those problems and file creation, the end user instantly sees it. You're [00:41:00] like, ah, like paragraph three, like, you literally just changed the font on me.Like it's a totally different font and like midway through the document. Mm-hmm. Those are the kind of things that you run into a lot of in the, in the content creation side. So, mm-hmm. We are gonna have native agents. That do all of those things, they'll be powered by the leading kind of models and labs.But the thing that I think is, is probably gonna be a much bigger idea over time is any agent on any system, again, using Box as a file system for its work, and in that kind of scenario, we don't necessarily care what it's putting in the file system. It could put its memory files, it could put its, you know, specification, you know, documents.It could put, you know, whatever its markdown files are, or it could, you know, generate PDFs. It's just like, it's a workspace that is, is sort of sandboxed off for its work. People can collaborate into it, it can share with other people. And, and so we, we were thinking a lot about what's the right, you know, kind of way to, to deliver that at scale.Docs Graphs and Founder Modeswyx: I wanted to come into sort of the sort of AI transformation or AI sort of, uh, operations things. [00:42:00] Um, one of the tweets that you, that you wanted to talk about, this is just me going through your tweets, by the way. Oh, okay. I mean, like, this is, you readAaron Levie: one by one,swyx: you're the, you're the easiest guest to prep for because you, you already have like, this is the, this is what I'm interested in.I'm like, okay, well, areAaron Levie: we gonna get to like, like February, January or something? Where are we in the, in the timelines? How far back are we going?swyx: Can you, can you describe boxes? A set of skills? Right? Like that, that's like, that's like one of the extremes of like, well if you, you just turn everything into a markdown file.Yeah. Then your agent can run your company. Uh, like you just have to write, find the right sequence of words toAaron Levie: Yes.swyx: To do it.Aaron Levie: Sorry, isthatswyx: the question? So I think the question is like, what if we documented everything? Yes. The way that you exactly said like,Aaron Levie: yes.swyx: Um, let's get all the Fortune five hundreds, uh, prepared for agents.Yes. And like, you know, everything's in golden and, and nicely filed away and everything. Yes. What's missing? Like, what's left, right? LikeAaron Levie: Yeah.swyx: You've, you've run your company for a decade. LikeAaron Levie: Yeah. I think the challenge is that, that that information changes a week later. And because something happened in the market for that [00:43:00] customer, or us as a company that now has to go get updated, and so these systems are living and breathing and they have to experience reality and updates to reality, which right now is probably gonna be humans, you know, kinda giving those, giving them the updates.And, you know, there is this piece about context graphs as as, uh, that kinda went very viral. Yeah. And I, I, I was like a, i, I, I thought it was super provocative. I agreed with many parts of it. I disagree with a few parts around. You know, it's not gonna be as easy as as just if we just had the agent traces, then we can finally do that work because there's just like, there's so much more other stuff that that's happening that, that we haven't been able to capture and digitize.And I think they actually represented that in the piece to be clear. But like there's just a lot of work, you know, that that has to, you just can't have only skills files, you know, for your company because it's just gonna be like, there's gonna be a lot of other stuff that happens. Yeah. Change over time.Yeah. Most companies are practically apprenticeships.swyx: Most companies are practically apprenticeships. LikeJeff Huber: every new employee who joins the team, [00:44:00] like you span one to three months. Like ramping them up.Aaron Levie: Yes. AllJeff Huber: that tat knowledgeAaron Levie: isJeff Huber: not written down.Aaron Levie: Yes.Jeff Huber: But like, it would have to be if you wanted to like give it to an Asian.Right. And so like that seems to me like to beAaron Levie: one is I think you're gonna see again a premium on companies that can document this. Mm-hmm. Much. There'll be a huge premium on that because, because you know, can you shorten that three month ramp cycle to a two week ramp cycle? That's an instant productivity gain.Can you re dramatically reduce rework in the organization because you've documented where all the stuff is and where the answers are. Can you make your average employee as good as your 90th percentile employee because you've captured the knowledge that's sort of in the heads of, of those top employees and make that available.So like you can see some very clear productivity benefits. Mm-hmm. If you had a company culture of making sure you know your information was captured, digitized, put in a format that was agent ready and then made available to agents to work with, and then you just, again, have this reality of like add a 10,000 person [00:45:00] company.Mapping that to the, you know, access structure of the company is just a hard problem. Is like, is like, yeah, well, you just, not every piece of information that's digitized can be shared to everybody. And so now you have to organize that in a way that actually works. There was a pretty good piece, um, this, this, uh, this piece called your company as a file is a file system.I, did you see that one?swyx: Nope.Aaron Levie: Uh, yes. You saw it. Yeah. And, and, uh, I actually be curious your thoughts on it. Um, like, like an interesting kind of like, we, we agree with it because, because that's how we see the world and, uh,swyx: okay. We, we have it up on screen. Oh,Aaron Levie: okay. Yeah. But, but it's all about basically like, you know, we've already, we, we, we already organized in this kind of like, you know, permission structure way.Uh, and, and these are the kind of, you know, natural ways that, that agents can now work with data. So it's kind of like this, this, you know, kind of interesting metaphor, but I do think companies will have to start to think about how they start to digitize more, more of that data. What was your take?Jeff Huber: Yeah, I mean, like the company's probably like an acid compliant file system.Aaron Levie: Uh,Jeff Huber: yeah. Which I'm guessing boxes, right? So, yeah. Yes.swyx: Yeah. [00:46:00]Jeff Huber: Which you have a great piece on, but,swyx: uh, yeah. Well, uh, I, I, my, my, my direction is a little bit like, I wanna rewind a little bit to the graph word you said that there, that's a magic trigger word for us. I always ask what's your take on knowledge graphs?Yeah. Uh, ‘cause every, especially at every data database person, I just wanna see what they think. There's been knowledge graphs, hype cycles, and you've seen it all. So.Aaron Levie: Hmm. I actually am not the expert in knowledge graphs, so, so that you might need toswyx: research, you don't need to be an expert. Yeah. I think it's just like, well, how, how seriously do people take it?Yeah. Like, is is, is there a lot of potential in the, in the HOVI?Aaron Levie: Uh, well, can I, can I, uh, understand first if it's, um, is this a loaded question in the sense of are you super pro, super con, super anti medium? Iswyx: see pro, I see pros and cons. Okay. Uh, but I, I think your opinion should be independent of mine.Aaron Levie: Yeah. No, no, totally. Yeah. I just want to see what I'm stepping into.swyx: No, I know. It's a, and it's a huge trigger word for a lot of people out Yeah. In our audience. And they're, they're trying to figure out why is that? Because whyAaron Levie: is this such aswyx: hot item for them? Because a lot of people get graph religion.And they're like, everything's a graph. Of course you have to represent it as a graph. Well, [00:47:00] how do you solve your knowledge? Um, changing over time? Well, it's a graph.Aaron Levie: Yeah.swyx: And, and I think there, there's that line of work and then there's, there's a lot of people who are like, well, you don't need it. And both are right.Aaron Levie: Yeah. And what do the people who say you don't need it, what are theyswyx: arguing for Mark down files. Oh, sure, sure. Simplicity.Aaron Levie: Yeah.swyx: Versus it's, it's structure versus less structure. Right. That's, that's all what it is. I do.Aaron Levie: I think the tricky thing is, um, is, is again, when this gets met with real humans, they're just going to their computer.They're just working with some people on Slack or teams. They're just sharing some data through a collaborative file system and Google Docs or Box or whatever. I certainly like the vision of most, most knowledge graph, you know, kind of futuristic kind of ways of thinking about it. Uh, it's just like, you know, it's 2026.We haven't seen it yet. Kind of play out as as, I mean, I remember. Do you remember the, um, in like, actually I don't, I don't even know how old you guys are, but I'll for, for to show my age. I remember 17 years ago, everybody thought enterprises would just run on [00:48:00] Wikis. Yeah. And, uh, confluence and, and not even, I mean, confluence actually took off for engineering for sure.Like unquestionably. But like, this was like everything would be in the w. And I think based on our, uh, our, uh, general style of, of, of what we were building, like we were just like, I don't know, people just like wanna workspace. They're gonna collaborate with other people.swyx: Exactly. Yeah. So you were, you were anti-knowledge graph.Aaron Levie: Not anti, not anti. Soswyx: not nonAaron Levie: I'm not, I'm not anti. ‘cause I think, I think your search system, I just think these are two systems that probably, but like, I'm, I'm not in any religious war. I don't want to be in anybody's YouTube comments on this. There's not a fight for me.swyx: We, we love YouTube comments. We're, we're, we're get into comments.Aaron Levie: Okay. Uh, but like, but I, I, it's mostly just a virtue of what we built. Yeah. And we just continued down that path. Yeah.swyx: Yeah.Aaron Levie: And, um, and that, that was what we pursued. But I'm not, this is not a, you know, kind of, this is not a, uh, it'sswyx: not existential for you. Great.Aaron Levie: We're happy to plug into somebody else's graph.We're happy to feed data into it. We're happy for [00:49:00] agents to, to talk to multiple systems. Not, not our fight.swyx: Yeah.Aaron Levie: But I need your answer. Yeah. Graphs or nerd Snipes is very effective nerd.swyx: See this is, this is one, one opinion and then I've,Jeff Huber: and I think that the actual graph structure is emergent in the mind of the agent.Ah, in the same way it is in the mind of the human. And that's a more powerful graph ‘cause it actually involved over time.swyx: So don't tell me how to graph. I'll, I'll figure it out myself. Exactly. Okay. All right. AndJeff Huber: what's yours?swyx: I like the, the Wiki approach. Uh, my, I'm actually

Ed, Rob, and Jeremy took some time from Wednesday's BBMS to share their reactions to Scott Boras' kind words about the Orioles ownership group and GM Mike Elias. Considering those will be the guys he has to negotiate deals with, do the words ring more true or more hollow?

Welcome back to the pod!Really excited for this episode and to introduce you all to Michael Coldwell, CEO & Co-Founder of Braintrust.  A former professional stand‐up comic, a three-time published novelist, and former executive director of corporate communications for Caesars Palace, he brings more than 20 years of experience to the world of marketing.Michael speaks at many global seminars and summits focusing on brand building and marketing. He has shut down Times Square for red carpet openings, arranged celebrity events, rang the bell on the New York Stock Exchange, and earned a client's place in the Guinness Book of World Records on three occasions. He has negotiated original programming deals with networks such as NBC, CBS, and the Travel Channel, and has organized and executed marketing programs at the Toronto International Film Festival, Cannes Film Festival, and the Academy Awards.Living near Nashville, TN, with his wife, Michael serves his community as a volunteer firefighter and is a nationally registered emergency medical responder. He is an elected representative that serves many parts of his community.Listen in to gain insights, perspectives and Michael's thoughts!Contact & Follow Cindy! Follow on Instagram at cindy_novotny, Facebook and LinkedIn for every day inspirational posts.Email at cindynovotny@masterconnection.com

On this episode of The Weekly Scroll Podcast, Ryan sits down with award-winning game designer, editor, and publisher WILL JOBST to talk Good Luck Press, cons, podcasts, editing, Plasmodics, and our shared love of all things Adam Vass. Find Good Luck Press here: https://goodluckpress.co/ 0:00 Start0:25 The big reveal01:29 Shot out Dark Wizard02:05 Who the heck is Will Jobst04:35 Adam Vass stan talk7:50 Con talk 10:55 Stuff from Will16:55 How did you get into TTRPGs?23:45 Starting the Brain Trust with Adam25:30 Discussion of the space28:10 Starting Good Luck Press33:45 Wearing the editor hat42:30 Digging into Plasmodics55:50 Adventures and supporting your games1:06:20 The solution to Crowdfunding1:10:15 Where can people find Will JobstAll our links here: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://linktr.ee/theweeklyscroll⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YouTube: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://www.youtube.com/@theweeklyscroll⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Twitch: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://www.twitch.tv/theweeklyscroll⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Instagram: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://www.instagram.com/the.weekly.scroll⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Bluesky: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://bsky.app/profile/theweeklyscroll.com⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Discord: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://discord.gg/SQYEuebVab⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠At-Coast Merch: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://www.bonfire.com/store/the-weekly-scroll/⁠⁠

Martin Casado speaks with Ankur Goyal, founder and CEO of Braintrust, about where engineering actually matters in AI and where it doesn't. They cover the open source vs closed source model cycle, why Chinese models are gaining ground faster than spending suggests, whether AI demand will eventually saturate, and the Bash vs SQL benchmark that challenges the "just give it a computer" approach to agents.Follow Martin Casado on X: https://twitter.com/martin_casadoFollow Ankur Goyal on X: https://twitter.com/ankrgyl Check out everything a16z is doing with artificial intelligence here, including articles, projects, and more podcasts. Please note that the content here is for informational purposes only; should NOT be taken as legal, business, tax, or investment advice or be used to evaluate any investment or security; and is not directed at any investors or potential investors in any a16z fund. a16z and its affiliates may maintain investments in the companies discussed. For more details please see a16z.com/disclosures. Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

In dieser Folge des »Mehr ist möglich«-Podcasts taucht Alex Rusch tief in eines seiner 15 wichtigsten Erfolgsprinzipien ein: das Braintrust-Prinzip. Viele unterschätzen dieses Instrument oder kennen es gar nicht. Für Alex hingegen ist es einer der entscheidenden Schlüssel hinter grossen Erfolgen wie der Zeitschrift »Noch erfolgreicher!« und dem Aufsteiger-Verlag. Dieses Prinzip – auch bekannt als Mastermind, »Bund kluger Köpfe« oder Dream-Team – basiert auf einer kraftvollen Idee: Wenn sich zwei oder mehr starke Köpfe systematisch zusammentun, entsteht eine dritte Kraft. Oder wie Alex es auf den Punkt bringt: 1 + 1 = 11. In dieser Episode erfährst Du: • Praxisbeispiele von Weltstars: Wie das Imperium von »Chicken Soup for the Soul« durch einen strategischen Braintrust von Jack Canfield und Mark Victor Hansen überhaupt erst möglich wurde. • Struktur statt Kaffeekränzchen: Warum ein echter Braintrust ein klares System braucht – und wie Alex Rusch seine Meetings konkret strukturiert. • Die verschiedenen Arten: Vom wöchentlichen »Power Braintrust« über den Telefon-Braintrust bis hin zum »Forum Braintrust« mit 6 bis 20 Personen. • Persönliche Insights: Alex erzählt von seinen Anfängen 1999 mit Ferris Bühler – und warum die Wahl des richtigen Partners entscheidend ist, selbst wenn ihr sehr unterschiedlich seid. Nutze diesen oft unterschätzten Konkurrenzvorsprung. Denn nur wenige wissen wirklich, wie man dieses Prinzip systematisch und konsequent anwendet. Erwähnte Links: ·        Online-Lehrgang »1 + 1 = 11 – das Braintrust-Prinzip«: https://alexruschinstitut.com/braintrust-prinzip/ ·        »Mehr ist möglich!«-Intensivprogramm: www.mim-intensivprogramm.com ·        Rusch-Millionen-Mastermind: www.millionen-unternehmer.com ·        »Rusch-Erfolgsstrategien Super-Umsetzer-Programm«: www.alexruschinstitut.com/super-umsetzer ·        »Alex Rusch Insider«-Podcast: www.alexruschinstitut.com/insider-podcast ·        »Rusch-Insider«-Newsletter: www.alexrusch.com/insider ·        Portal »Rusch-Gratis«: www.rusch-gratis.com

En este episodio exploramos por qué la armonía superficial es más tóxica que el conflicto abierto. A través de casos como Nokia, donde el miedo a dar malas noticias aceleró su caída, y Theranos, donde el silencio organizacional puso vidas en riesgo, examinamos el costo invisible de la paz falsa. Contrastamos esto con el modelo de Pixar y su Braintrust, donde la crítica honesta es institucionalizada sin destruir relaciones. El episodio incluye tres herramientas prácticas para crear seguridad psicológica y canalizar el conflicto productivamente: el Pre-mortem de Consenso, la técnica del Desacuerdo Obligatorio, y el Termómetro de Seguridad Psicológica.  Puntos Clave: • La armonía genuina viene después del desacuerdo; la conformidad tóxica lo reemplaza • Nokia cayó no por falta de talento, sino por incapacidad de decir la verdad internamente • El conflicto de tareas (sobre ideas) es productivo; el conflicto de relaciones es corrosivo • La paz falsa es deuda organizacional que acumula intereses • La seguridad psicológica se construye con acciones consistentes, no con declaraciones 

Atlanta Falcons President of Football Matt Ryan speaks about the excitement beginning a new era of Atlanta Falcons football with the recent hires, the process that ultimately led to the decision to bring aboard Ian Cunningham, what's different for interviewing a GM versus a head coach, hiring someone to do the job versus someone to work alongside with, where the Falcons are in terms of building a competitive winner, how he views the current tram compared to when he joined the franchise as a rookie, Chicago GM Ryan Poles knowing how important Ian Cunningham was to the Bears turnaround, and being able to change what he wears now with most press conferences out of the way.

Hour 1 of BMitch & Finlay features JP, BMitch, and callers debating whether they trust the Commanders' front office?

The Lions hired former Giants interim head coach Mike Kafka as a high-level offensive assistant

6:00 HOUR: The Lions upgrade the offensive braintrust, Nobody wants to coach the Cleveland Browns anymore

Ulf Granberg was a giant in the Phantom community as both a writer and editor but perhaps even more as a historian and Phantom-lore builder who added structure to the loose lore established by Lee Falk. Sadly, he recently passed, and Dan Fraser and Jermayn Parker talked about his legacy and reminisced about our chat with him almost a decade ago.At the end of us talking and remembering a legend, we include some snippets from our 3-hour chat with him from XEpisodes 97A and 97B.Ulf Granberg (born 1945) was the editor responsible for the Swedish Phantom comic book, Fantomen, from 1972 to 2012, a duty that also included heading the Team Fantomen production of Phantom stories. He had also written almost 40 Phantom stories.Granberg became the 12th editor of Fantomen in 1973, succeeding Per-Anders Jonsson, and continued until 1987, being succeeded by Mats Jönsson. In 2003 he returned as editor, succeeding Petter Sjölund. He did, however, remain in charge of the production between his two periods as an editor, serving as editor-in-chief.He retired from his Phantom duties with Fantomen 9/2012, after a total of 1001 issues. He was succeeded by Mikael Sol as editor for Fantomen and by Claes Reimerthi and Hans Lindahl as editors for the Team Fantomen production of stories.What this bio doesn't include is the behind-the-scenes stuff that many of us take for granted.He was important in the hiring of several key creators from around the world, including Cesar Spadari, Norman Worker, Jamie Vallve, Carlos Crus, Hans Lindahl, Claes Reimerthi, Dai Darell, Donne Avvenell, Felmang, Ferri, Joan Boix, Tony DePaul, Paul Ryan, Graham Nolan, David Bishop, Georges Bess, Kari Leppanen, Lennart Moberg, Sal Velluto, Bob McLeod, and Dick Giorando.He added to the lore of the Phantom and filling in the gaps.He created the first timeline of all 21 Phantoms. Even giving Lee Falk the list.He created the first Phantom map of Bangalla and the countries around Bangalla. The Bangalla map was very much liked by Lee Falk who asked for a copy.He added to the first Phantom adventures on how he got the skull ring and how he became known as the man who cannot die.He oversaw the origin of Devil.He oversaw the creation of Dogai Singh, perhaps the most dreaded Singh pirate, and of course Sandal Singh.He created the ‘Brain Trust' or Team Fantomen which was a group of creators who would meet once a year and map out the theme of stories for the next year or period of time.He oversaw the Lubanga storyline, which was controversial but also impactful, which saw Luaga lose the presidency of Bangalla. In 1999 after Lee Falk's death, the newspaper strip almost was cancelled. He pushed the continuous nature of it and suggested Paul Ryan and Tony DePaul/Claes Reimerthi to take over.You can email us at chroniclechamber@gmail.com or chat with us via our social media profiles on Facebook, Twitter, and/or Instagram. We love comments and feedback from the Phantom phans from around the world. Make sure you stay with us, and do not forget to subscribe and leave a review on our podcast on our YouTube Channel.Support the show

Kendra Bracken Ferguson built companies that invented the creator economy before Instagram and TikTok — and she tells the part founders unusually hide: when the shiny acquisition stops working, the earn-out math gets ugly, and you have to choose between protecting your title or protecting your team…We get into trust as a system (including her very controversial co-founder test), buying a company back, building BrainTrust into a studio + fund backing Black beauty & wellness founders, and why corporate partners suddenly got nervous about “Black founder” the second it became inconvenient.01:36 Meet Kendra Bracken Ferguson: Builder, Operator, Dealmaker02:22 The Thanksgiving Idea That Sparked Digital Brand Architects04:03 How DBA Helped Invent The Creator Economy Before Instagram07:04 Knowing When To Walk Away—And Start Over08:10 Why “Trust” Became The Non-Negotiable Business Principle14:20 Inside The CAA Acquisition18:36 When The Deal Looks Good—But The Reality Doesn't20:52 The Moment Everything Had To Change21:20 Redefining Failure: Pivots, Pressure, And Perspective22:41 Journaling, Self-Awareness, And Founder Survival Tools24:32 Rebuilding With Intention: The Real BrainTrust Vision25:12 From Agency To Studio To Fund26:39 Corporate Partnerships, Power Dynamics, And Hard Truths29:57 New Ventures, New Partners, And Building With Exit In Mind35:39 From Hustle To Harmony: Success, Sleep, And The Next Chapter

Join Las Vegas Raiders on Senior SI Beat Writer Hondo Carpenter and family discussing the Silver and Black on the most recent Ridin' with the Carpenters on PFI, Pro Football Insiders. Learn more about your ad choices. Visit megaphone.fm/adchoices

Steiny & Guru wonder what the Warriors have on the table of options for the present and future after losing one of their superstars, Jimmy Butler for the entire season and likely most of next year.

This throwback episode was originally recorded live from the main stage at Voices of Dentistry 2022 where the original Dental Hacks—Dr. Alan Mead and Dr. Jason Lipscomb—reunite for a hilarious and nostalgic session. The duo kicks things off by catching up on life since their "breakup" and going head-to-head in a competition to determine who has endured the worst patient horror story of the pandemic era. Later in the show, the classic Brain Trust format returns as Dr. Mark Costes and Dr. Justin Moody join the stage for a round of "Ask Us Anything." The panel covers a wide range of topics, including their surprising hobbies outside of dentistry, pandemic takeaways, and critical advice regarding practice startups versus acquisitions for the next generation of dentists. Join the Very Dental Facebook Group using one of these passwords: Timmerman, Bioclear, Hornbrook, Gary, McWethy, Papa Randy, or Lipscomb!  The Very Dental Podcast network is and will remain free to download. If you'd like to support the shows you love at Very Dental then show a little love to the people that support us! I'm a big fan of the Bioclear Method! I think you should give it a try and I've got a great offer to help you get on board! Use the exclusive Very Dental Podcast code VERYDENTAL8TON for 15% OFF your total Bioclear purchase, including Core Anterior and Posterior Four day courses, Black Triangle Certification, and all Bioclear products. Crazy Dental has everything you need from cotton rolls to equipment and everything in between and the best prices you'll find anywhere! If you head over to verydentalpodcast.com/crazy and use coupon code "VERYSHIP" you'll get free shipping on your order! Go save yourself some money and support the show all at the same time! The Wonderist Agency is basically a one stop shop for marketing your practice and your brand. From logo redesign to a full service marketing plan, the folks at Wonderist have you covered! Go check them out at verydentalpodcast.com/wonderist! Enova Illumination makes the very best in loupes and headlights, including their new ergonomic angled prism loupes! They also distribute loupe mounted cameras and even the amazing line of Zumax microscopes! If you want to help out the podcast while upping your magnification and headlight game, you need to head over to verydentalpodcast.com/enova to see their whole line of products! CAD-Ray offers the best service on a wide variety of digital scanners, printers, mills and even  their very own browser based design software, Clinux! CAD-Ray has been a huge supporter of the Very Dental Podcast Network and I can tell you that you'll get no better service on everything digital dentistry than the folks from CAD-Ray. Go check them out at verydentalpodcast.com/CADRay!  

Happy New Year, and welcome to our first episode of 2026. I'm Josh Cooperman with Convo By Design and have bee hosting Doctoring Up Design, the official podcast of Design Hardware. If you haven't been into the showroom before, or its been a while, please come back and see all of the new updates and additions to this remarkable space, where we host industry education events, like the one you are going to hear today. This is a throwback to the first Environment Check event held in the showroom back in 2022. It has been a year since the catastrophic fires in Pacific Palisades and Altadena. What have we learned? I would say we have learned a lot, but much of it isn't new. So, periodically, in addition to all the new content we create here at Design Hardware, we are going to add some throwbacks that make sense. Like the program you are going to hear on this episode of Doctoring Up Design.Design Hardware hosted a vital forum on how the intersection of gray water reclamation, native landscaping, and green building policy is no longer a luxury, but a necessity for human survival.We, gathered a "Brain Trust" of sustainability experts at the Design Hardware showroom in Los Angeles. The conversation moves past the surface-level "crunchy granola" stereotypes of eco-design and dives into the hard science of urban resilience.From the "double waste" of California's current water infrastructure to the vanishing craft of climate-appropriate landscaping, the panel explores how designers and architects must act as "Building Scientists." The consensus is clear: awareness and education are the only tools powerful enough to shift policy from a reactive "whisper" to a proactive “scream." And that “scream” was heard loud and clear a year ago. Let's explore ways to minimize this in the future. This feels like a good way to do that. Listen to a few hot talks from the following conversation and see if they don't resonate. Because this was a conversation from 2022.Participants:Josh Cooperman | Convo By DesignDesign Hardware | DesignHardware.comCassie Aoyagi | Form LA LandscapingLeigh Jerard | Greywater CorpsTim Barber | Tim Barber ArchitectsBen Stapleton | USGBC California

Costarring Errick Greenlee, Michael Lamerique & Marcus RobinsonOn January 8, 2016, I released the first episode of Hyphen Nation. Recorded from the parking lot of a local Morgantown Kroger with a laptop and a headset mic, never did I dream that my little podcast would be at 200+ episodes and still active 10 years later but here we are!To celebrate, I recruited the Brain Trust aka the Diamond Dogs Handsome Bane, Lam, and Marc Rob to celebrate with me. In the first half, we talk about Will Smith's career taking it's downturn, how no one has replaced Twitter despite multiple efforts, relive some 2016 things, and many more alleys and detours.In the back half, Handsome Bane carved out some time so he could still contribute more than just a visit, and we talk about the death of Hulk Hogan, where he's finding joy in professional wrestling these days, and God.Here's to another 10 years? Maybe? Who knows. Thanks y'all.IMPORTANT LISTENING INFO: I apologize for the quality of my microphone in the second half. I hooked my condenser mic up to Zoom and even after all these years, they don't like each other.

In this episode of Wine After Work, Bryce sits down with Adam Jackson, CEO and founder of Braintrust, the world's largest user-owned talent network and the company behind Braintrust AIR, the first end-to-end AI recruiting platform built to benefit both companies and talent. Adam shares his entrepreneurial journey—from founding telemedicine giant Doctor on Demand to building Braintrust—and unpacks how AI is fundamentally changing hiring. We dive into what Braintrust AIR actually does, why now is the moment for AI in recruiting, and how technology can finally make hiring faster, fairer, and more human. Plus, we talk misconceptions around AI, how leaders should approach change, and Adam's unexpected creative outlet: running a wine label called Asymmetric. If you're curious about the future of recruiting, talent acquisition, or how AI can work with people instead of replacing them, this episode is a must-listen. What we cover: Adam's career journey and the origin story of Braintrust The vision behind a user-owned talent network What Braintrust AIR is and how it reduces time-to-hire from months to days How AI can improve outcomes for hiring managers and job seekers Common myths about AI in recruiting (and what's actually true) How to lead through technological change Entrepreneurship, creativity, and wine

It's that time of year again! Where Ben and Nate take a brief break and give you an episode from our bonus list. If you want to hear this stuff when it comes out rather than over a year (or 2) later, sign up for your patreon! $3 gets you our entire bonus episode library and we're planning on releasing even more this coming year. Check us out!Support the showBlue Sky - https://bsky.app/profile/wordsaboutbooks.bsky.socialDiscord - https://discord.gg/6BaNRtcP8CThreads - https://www.threads.net/@wordsaboutbookspodcastInstagram - https://www.instagram.com/wordsaboutbookspodcastBlog - https://blog.wordsaboutbooks.ninja/

The Goods is a new series that delivers wisdom for personal and professional growth. In today's episode, Blake steps inside Pixar's Braintrust to show how radical candor without authority turns rough early cuts into remarkable films. Learn how keeping decisions with the builders, critiquing the work (not the worker), and scheduling the next messy version can supercharge any team's results.Enjoy Episode 50 of The Goods. #BeNEXT

Most writers start revision by re-reading their manuscript from page one — but that's the least effective way to improve a book. In this episode, Jenny explains a clearer, more strategic way to revise using the Blueprint and the 3D Revision Process. You'll learn how to step back, see your book with fresh eyes, and create a plan that actually moves your manuscript from good to great. We also invite you to join the upcoming Blueprint Sprint.In this episode you'll learn:* Why a full-manuscript read is often the wrong first step in revision* The mindset shift every writer needs before diving into revisions* How to use the Blueprint to create a clear, confident revision plan before touching your pagesJoin the Blueprint SprintStarting January 12 and rolling though February, KJ Dell'Antonia and Jennie Nash will lead you through the 14 foundational questions that every writer should ask of themselves and their book, whether you're just getting started, are mid-draft or starting on on the whatever-number revision with weekly assignments, live events, workbooks and updated access to all the Blueprint resources. All you need to do is be a paid subscriber and stay tuned—we'll let you know how to get signed up.I NEED a January Blueprint!What if you want even MORE? Then you could be one of a very few #AmWriting subscribers who join our first ever Blueprint Sprint cohort. 6 weeks of working together and write-alongs, 5 group-only live sessions, which will be recorded for anyone who can't attend and a members-only community dedicated to helping you create a Blueprint that leads you to the book you want to write, ending with direct feedback from me and from Jennie on your flap copy and 3 page Inside-Outline.We're keeping this small on purpose—we max out at 10 and we might drop that down—so applications to join this group open today and will be evaluated on a first-come, first serve basis. Once we have 10 people, we will close down the application, so get yours in early! Early-bird pricing is $1000 until December 22, after that the price goes up to $1200 (if there are spaces left by then).What are we looking for? 10 writers who are prepared to commit to the process and to the cohort, who do what they set out to do when they set out to do it, who welcome constructive feedback and are willing to do what it takes to build a blueprint for the book they want to create. Writers who know that sometimes you must look a hard truth in the face and cut your losses, that what goes in the scrap heap is rarely resurrected but that the scrap heap is a necessary part of the work. Writers who won't take no for an answer, but can hear “not this” and feel both disappointment and a burning determination that the next effort will be the one that gets there.Also: no a******s.What will you need to apply? We want to hear about your professional and publishing backgrounds, but no publishing experience is necessary. We want to know where you are with this current project, but “still noodling” is a fine answer. The primary requirements are first, a readiness to do the work and second and more ephemerally, our sense of what makes a cohesive cohort.If that sounds like you, here you go—the time to apply is now.Links & Resources* Learn more about the Blueprint tools* Substack about how each genre has a different primary goal in the Blueprint * #amwriting Episode about the Blueprint origin story and why it's such a powerful tool: Transcript Below!#AmWriting is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber.“Revision means stepping back, thinking big picture, and being brave enough to rebuild.”SPONSORSHIP MESSAGEHi writers, the Winter Blueprint Challenge 2026 is on, and I can't wait to do it, and I can't wait to tell you about it. Okay, so this time around, we're going to have two ways to play. First, we'll run the Blueprint for supporters, 10 weeks of Blueprint assignments, live events, and encouragement starting January 12, 2026—or, and this is the big news, apply to join our very first Blueprint cohort—10 of you will become a small group that receives direct feedback from me and from Jennie on flap copy and the three page Inside-Outline, and joins five group only live sessions and becomes a part of a members-only community dedicated to helping you create a blueprint that leads you to the book you want to start and finish. Applications to join this group open December 15, 2025 and will be evaluated on a first come, first-serve basis. Once we have 10 people, we're going to close down the application. So get yours in early. Early-bird pricing for the small cohort is $1,000 until December 22 after that, the price goes up to $1200 (if there are even spaces left by then). I am so excited about this. So get your application in early. The regular Blueprint will run for supporters at the usual supporter pricing, but this other cohort is going to be really special details on how and where to apply are in the show notes, or they're going to be pretty prominently displayed at AmWriting podcast.comEPISODE TRANSCRIPTMultiple SpeakersIs it recording? Now it's recording. Yay! Go ahead. This is the part where I stare blankly at the microphone. Try to remember what I'm supposed to be doing. All right, let's start over. Awkward pause. I'm going to rustle some papers. Okay. Now, one, two, three.Jennie NashHey everyone, it's Jennie Nash, and this is the Hashtag AmWriting Podcast the place where we help you play big in your writing life, love the process, and finish what matters. Today, I want to talk about why most writers approach revision the wrong way, and how to use the Blueprint to do it right. Most people think revision starts with reading the whole manuscript, but the truth is I think that's the last thing you should do. Before we dive into why I think that, and what I think you should do instead, I want to talk a little bit about what I call the “revision mindset.”When you finish a manuscript, it's really tempting to think, okay, I've got it, I did it, I'll just polish it up a little and be done. But real revision requires openness—being open to seeing the strengths and the weaknesses and the changes that you need to make in the manuscript to take it from good to great. This can feel really vulnerable. I know for me, at this point, I worry that changing one thing is going to break everything else. You feel so close to the finish line that you don't want to touch anything. But holding that tightly—that kind of clenching—is exactly what stops the revision process from working. It's important to remember that revising is big-picture work. It's not line editing. Revising is stepping back, seeing what's really on the page, and being willing to reshape it. So a “revision mindset” is that openness and that willingness to look at it, to be real about what's there and what you want it to be, and to be willing to do what it takes to get it there. So a good revision is going to start with that mindset. And if we start there, you can begin to see why doing a full manuscript read-through from page one, marching straight through all the way to the end, is going to lead to trouble. There are two particular things that happen if you approach revision in that way.The first problem is when you go to read the book from page one chronologically all the way through—maybe you wrote it that way, maybe you didn't—but in any case, if that's how you approach revision, what tends to happen is that you fall into line editing instead of big-picture thinking. You begin to think, oh, this line is really great, or maybe I should fix that line, or maybe the flow here is a little off from this line to the other. You stay in the weeds, and you lose sight of structure and purpose and the big arc of your story or argument. The second problem with starting revision with a full manuscript read is when you ask somebody else to do that reading for you. Basically, what you're doing is handing over your power to somebody else. You're saying you look at this, tell me what you think, tell me how to fix it, tell me what's wrong. And the problem with that is the tendency to get feedback and then just do everything they ask without thinking strategically through what you want to do or what you want your revision to accomplish. And a corollary of that problem is that usually when people are doing that full manuscript read for you, they're just dumping all this stuff on you. They're giving you this long litany of things that they see in the manuscript, or things that they think you should fix, and that list might include small things and big things and important things and not important things. It's so easy to just get overwhelmed with the process.As a book coach, that's what I see all the time. People get into revision, they get overwhelmed, they freeze up, they don't know what to do first. It's so easy to feel defeated. And that's the moment when so many writers stall out and shelve the project. They put it in a folder on their desktop—the proverbial drawer—and it's just away, and they're done, and they can't face it. And then the idea of going back to that huge amount of work and trying to figure it out becomes too daunting, and they just don't. So I don't recommend starting your revision with the full manuscript read.I have a different approach that I teach book coaches at Author Accelerator, and it's called the “3D revision process.” It has three parts. The first is a process of inquiry. We use the Blueprint to ask key questions about the project. The second step is mapping everything out using the outline at the end of the Blueprint in a specific way. And the third step is strategizing. We look at that outline and we prioritize what changes need to be made using the stoplight strategy. I'm going to explain all these things in a minute, but the point is that this process gives you clarity, confidence, and a specific, actionable plan for approaching your revision—which is the dream.Okay, so let's walk through it. Step one is this process of inquiry, and using the Blueprint to walk us through that. In an earlier episode, which I'll link to in the show notes, I talked about why I created the Blueprint and why I refer to it as a process of inquiry, rather than a story structure method. The process of inquiry allows the writer to look at the foundational aspects of what they're writing and to look at the work from this big-picture angle that usually they skip. There are 14 questions no matter which genre you're working on, but they all start with these really basic questions, like, why are you writing this book? What's your point? Who's your reader, and what do they want? And are you giving it to them?Using the Blueprint to start a project, and answering these questions before you begin, is a really powerful way to think about what you want to do in the book, and a powerful way to get your vision clear. But when you have a finished manuscript and you go back to these questions, it's a whole different ball game. It's almost like a test. Can you answer these questions clearly and confidently based on what you know is there? Have you, in other words, put on the page the vision that you had in your head? So you go through the 14 questions honestly, answering them based on what you actually have, and it becomes this kind of assessment or challenge or test, like, did I do what I wanted to accomplish? And it's really easy in those 14 questions to see if you didn't. If you can't confidently answer one of the questions, you know that that's pointing toward a potential weakness in the book.If I give the 14 Blueprint questions to somebody who has written a manuscript that they love and that is close to the vision that they had for it, they're able to knock those questions out and answer them with such authority and power, and it's just an amazing thing to see. And when they can't, and they're coming to the questions with that openness I talked about before, then it's like, okay, look, we still don't have this piece nailed down. We still have to figure out this part of the story or the argument that you're making, so it becomes a first pass at what is really there and what strengths and weaknesses are on the page.The second step in the “3D revision process” is to map out what you have, and we do this with the outline that is at the end of each of the Blueprints. If you've gone through the previous questions in the Blueprint, you're looking at those foundational aspects, the structural elements of the story, all the things that hold up what you've written, and then the outline is, okay, here's what I've actually written. If you're at the start of a project, you want that outline to be no more than three pages. I'm very strict about this, and there's a reason for that. It's because we need to contain or constrain the creative process so that we can see what it is you're wanting to make or to build. If someone goes on and on at that stage of the writing process, they're not making good decisions and they're not thinking about the big picture. But when you keep it to three pages, you're forced to do that, and it's a really awesome process.With revision, I loosen those rules, and the reason is that for revision, I want this outline to be what I call an “as-is outline.” So this is not what you intend to write, or what you hope to write, or what you plan to write, which is what it is at the beginning of a project. Now it's what is actually there. So the as-is outline is capturing what you actually wrote, not what you intended to write. So you use the manuscript, obviously, to get this information and to pin down an outline of what is actually there. And there's still a constraint. I suggest that you keep this as-is outline to about 10 pages, and you absolutely need to follow the rules of the genre that I outline in the Blueprint. Each of the genres has a specific outline and a specific thing that we're looking for in that outline, and I designed that to solve for the things that people most often get wrong in that genre.I wrote a Substack post, which I'll link to in the show notes, which explains what each of those things are, and I'll link to that in the show notes. But you want to follow the rules of the outline, so that you make sure you're not making the foundational problems of that genre. But then you have these 10 pages to capture what you've actually done on the page, and this as-is outline is where the big insights happen. When you step back and you look at this as-is outline, you can see where the momentum drops, where scenes or chapters repeat themselves, where your structure might be broken, where a subplot might take over, or, in nonfiction, where you veer off in some other direction. You can see where two memoir scenes are doing the same emotional work, or where a nonfiction chapter doesn't drive towards the outcome that you're leading your reader to. You can see so much in this outline, and that's why this process is so powerful. The outline becomes a kind of X-ray of what you've actually written on the page.And that leads us to step three of the “3D revision process” which is you're going to analyze that outline. You're going to bring some strategic thinking to what you have there. Each of the Blueprints has a checklist for their particular outline, and you want to go through those checklists and really ask yourself, have I done this? Have I done that? Have I done the other? The kinds of questions that checklist asks are things like, am I giving the reader what they want and expect? Does my outline include the essential elements of my genre or category? What's missing, what's out of order, what's unclear, what's unnecessary? So it's strategic thinking about the material that you have created.One of my favorite books about the creative process is Creativity, Inc., by Ed Catmull. It's the story of the creation of Pixar, the company, and in that book, he talks about the Brain Trust, which is a very small group of writers who help each other to create the best possible stories. And they have this process in the Brain Trust that's called giving good notes. And good notes are clear, they're factual, they're strategic, and that's what you're doing here for yourself. You're giving yourself good notes. And if at this point you want to bring in a trusted partner to help you brainstorm and to help you look at your material and look at your notes and help you brainstorm solutions, this is a great time to bring in somebody to help you brainstorm and to look at your as-is outline and look at the notes that you've made for yourself, because instead of just handing the job over to somebody else, you're saying, I have done this work of looking at my work in a strategic way. I know what I've done well, I know what my weaknesses are, and now I'm ready to solve those problems.So a great critique partner or a trusted beta reader or a book coach…obviously, are great people to bring in at this stage of the process. And what's awesome is you're not asking them to sit down and spend 15 or 20 hours reading a whole manuscript and trying to figure out what you want or what you were trying to do, or how it all lands for them, and giving you this info dump of information. You're asking them to look at your Blueprint, to look at your answers to the 14 questions, and your as-is outline, and your analysis of that outline. And what you'll be doing, either on your own or in partnership, is prioritizing what needs to happen in the revision.The tool that I teach coaches to do this is called the “stoplight strategy.” And what we're doing is we're trying to categorize the problems that we see in a manuscript by their severity. So red light problems are major structural issues, yellow light problems are medium-level issues, and green light problems are line-level edits. I designed the stoplight strategy because so many writers think that revision is about green light issues. So many of them start with line-level edits. And as I spoke about before, the tendency if you're doing a full manuscript read is to fall into that rhythm of just seeing the green light things, or maybe a few yellow light things. But it's very hard to see the red light things, which are the things that are going to bring your book down. They're the fatal flaws, and most writers never find the time to actually look at those things.So they might be things like, I've got to start this novel in a totally different place, or I have to chop off five chapters of my memoir, or I have to restructure my entire nonfiction argument in a different way to make it land. But if you've approached the process that I'm explaining with that openness, that revision mindset, and that curiosity about how can I make this better, and if you've gone through it in this systematic way, and you found some red light issues, they tend not to sting quite so much. They tend to feel manageable. Okay, I can fix this one big thing. And if I fix this one big thing, the next thing that I need to fix is probably going to be obvious, and then the next one is going to be obvious. So you're leading yourself to a prioritization of what needs to happen in the revision, rather than looking at everything in the same way, meaning every little green light issue has the same weight as the yellow light issues and the same weight as the red light issues.When we step out of doing the work chronologically, and we approach it in this more strategic way, we tend to focus on the red light issues. And again, they just tend not to feel quite so awful.So the next step in the process is you take that as-is outline, and you turn it into a “what's-next outline,” a map of what the book is going to become in revision. On that outline, you mark what gets cut, what gets moved, what needs to be added, what shifts are you going to make because of the big changes, and you actually make them in the outline, so that the outline reflects where you're going with your revision.And that's how we close the gap between what you've written and what you want to write. That's where you get closer to your vision of what you want this book to be. And that's why this process is so powerful, because now you have a clear map of what you need to do in revision. You have a clear plan for how you're going to go execute those things, so you're not guessing and you're not lost in overwhelm. You have this what's-next outline that you're going to go in and follow. And if you want to start at the beginning and make all the revisions in chronological order, you can. Or if you want to go in and fix the big red light issues first, you can. And you can use this what's-next outline as a kind of external hard drive to hold all the changes that you want to make in your revision, so that you're not holding them all in your head.Doing the revision in this way might actually mean going in and working on, let's say, chapter 10, 11, and 12, and not touching anything else. It might mean going in and working on chapters 13 and 27 and not touching anything else. It's not necessarily a chronological process. You're going to follow the what's-next outline and do what needs to be done in the manuscript.And once you do that, now is the time when a full manuscript read can make a lot of sense. Now you can go through from beginning to end knowing that you don't have any big structural issues. There are no red light issues in this manuscript anymore. There are no yellow light issues. You don't have to think about those or worry about those. You can go through and do the thing that most people do at the beginning of their revision process, which is polishing the prose and making everything sing and working on the line-by-line writing. You've already done the heavy lifting.If you're excited about using the Blueprint in your revision and you want to work through it with a community of other writers who are doing it too, we'd love to have you join our upcoming Blueprint Challenge. You're going to go through the Blueprint step by step along with people who are revising their books or people who are starting from scratch. It's the same 14 questions, and people will be working on fiction, they'll be working on memoir, and they'll be working on nonfiction. KJ is going to be leading the charge of this Blueprint, and she's going to be doing some write-alongs and AMAs and different things to support people while you work through those Blueprint questions. And I'm going to be in there a few times as well.This is the fourth time we've done the Blueprint Challenge at the Hashtag AmWriting Podcast, and it gets better and better every time as more and more people do it. And you can find critique partners in there to help you with your Blueprint questions, maybe to look at your as-is outline, because they understand the process. They understand what's going on. They understand what this is all about. And it's just a really fun and powerful way to approach either a new book or the revision of a book that you want to work on.You can check the show notes for details on how to sign up for the Blueprint Challenge. This challenge works if you have a new idea that you want to work through, or a new-ish idea. You can be a little bit into it, and the Blueprint process is still really effective. And it also, of course, works really well if you're revising something, or maybe you're stuck revising something, or overwhelmed by the revision process that you're in.You can start at the beginning of the Blueprint process and go through what I've just described here, and at the end of the challenge, be in a really great place to move forward with your project. We'd love to have you join us. So again, check the show notes for details.We give everyone who joins the Blueprint Challenge a downloadable copy of the Blueprint book and a workbook to work through. But if you're not able to do the challenge at this time and you want to go through this process yourself, you can just grab a copy of my Blueprint book at any bookstore and work through those 14 questions and your outline at the end. However you do it, we're excited to support you on your way.So until next time, keep your butt in the chair and your head in the game.NarratorThe Hashtag AmWriting Podcast is produced by Andrew Perrella. Our intro music, aptly titled Unemployed Monday, was written and played by Max Cohen. Andrew and Max were paid for their time and their creative output, because everyone deserves to be paid for their work. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit amwriting.substack.com/subscribe

A familiar menagerie of Badlands Media hosts drops in for another unscripted OnlyLands hangout, where nothing is off-limits and everything is up for discussion. Episode 35 drifts effortlessly from behind-the-scenes show chatter and tech hiccups into broader conversations about current events, online narratives, and the strange cultural moment everyone seems to feel but can't quite define. The hosts riff on news of the day, community moments, personal observations, and the ongoing challenge of staying grounded while the information cycle spins faster by the week. With plenty of humor, side quests, and real-time reactions to chat, this episode captures the loose, late-night energy that makes OnlyLands a favorite, less a show, more a digital living room where Badlands voices collide, decompress, and connect.  

Children's Wisconsin is off the hook after mistakenly throwing out a donated brain. This, after a Milwaukee County judge dismissed a lawsuit filed by the donor's parents. In this episode of Open Record, how the family is reacting to that decision. FOX6 Investigator Bryan Polcyn explains how we got here, the issue at the center of it all, and what happens next. Learn more about your ad choices. Visit podcastchoices.com/adchoices

In this episode of the Medical Sales Podcast, Samuel sits down with Dan Docherty, partner at BrainTrust and co-author of NeuroSelling 2.0, to explore what it truly takes to become a world-class communicator in medical sales. Drawing from his decades of experience in pharma and neuroscience-based training, Dan reveals the five key skills every rep must master—developing a communication process, asking powerful questions, listening actively, storytelling with emotion, and building emotional intelligence. This episode is a masterclass in how top performers connect deeply, earn trust fast, and influence through empathy, strategy, and purpose. Connect with Dan Docherty: LinkedIn Connect with Me: LinkedIn Love the show? Subscribe, rate, review, and share! Here's How »

Explore the worlds of weird little guys with us as we chat with game designer Will Jobst of Good Luck Press, creator of Torq, This Discord has Ghosts in It (with Adam Vass), Black Mass, and—recently—Plasmodics! We talk about designing mutant freaks in the weird future, 'demaking' vintage TTRPGs, imagining a better future through gaming, and more! Good Luck Press: https://goodluckpress.co/ Will's Itch.io: https://willjobst.itch.io/ Listen to Will and Adam Vass on The Brain Trust: https://linktr.ee/thebraintrust Plasmodics Kickstarter (late pledges open!): https://www.kickstarter.com/projects/goodluckpress/plasmodics?ref=9bidtk For strange mutants in the weird past, check out Danse Macabre: Medieval Horror Roleplaying on Kickstarter! Late pledges open: stillfleet.com/danse Learn more about your ad choices. Visit megaphone.fm/adchoices

In this episode of the Medical Sales Podcast, Samuel talks with Dan Docherty from BrainTrust about how neuroscience is transforming the way medical sales professionals build trust and communicate with impact. Drawing from his 25-year career in pharma, Dan explains how traditional training focuses too much on product and not enough on human connection. He introduces the concept of NeuroSelling®, showing how value-based storytelling and empathy drive real influence in conversations with healthcare providers. This episode reveals how the best reps in 2025 use emotional intelligence, authentic connection, and purposeful communication to create lasting trust and deliver meaningful results.   Connect with Dan Docherty: LinkedIn Connect with Me: LinkedIn Love the show? Subscribe, rate, review, and share! Here's How »

In this conversation with Malte Ubl, CTO of Vercel (http://x.com/cramforce), we explore how the company is pioneering the infrastructure for AI-powered development through their comprehensive suite of tools including workflows, AI SDK, and the newly announced agent ecosystem. Malte shares insights into Vercel's philosophy of “dogfooding” - never shipping abstractions they haven't battle-tested themselves - which led to extracting their AI SDK from v0 and building production agents that handle everything from anomaly detection to lead qualification.The discussion dives deep into Vercel's new Workflow Development Kit, which brings durable execution patterns to serverless functions, allowing developers to write code that can pause, resume, and wait indefinitely without cost. Malte explains how this enables complex agent orchestration with human-in-the-loop approvals through simple webhook patterns, making it dramatically easier to build reliable AI applications.We explore Vercel's strategic approach to AI agents, including their DevOps agent that automatically investigates production anomalies by querying observability data and analyzing logs - solving the recall-precision problem that plagues traditional alerting systems. Malte candidly discusses where agents excel today (meeting notes, UI changes, lead qualification) versus where they fall short, emphasizing the importance of finding the “sweet spot” by asking employees what they hate most about their jobs.The conversation also covers Vercel's significant investment in Python support, bringing zero-config deployment to Flask and FastAPI applications, and their vision for security in an AI-coded world where developers “cannot be trusted.” Malte shares his perspective on how CTOs must transform their companies for the AI era while staying true to their core competencies, and why maintaining strong IC (individual contributor) career paths is crucial as AI changes the nature of software development.What was launched at Ship AI 2025:AI SDK 6.0 & Agent Architecture* Agent Abstraction Philosophy: AI SDK 6 introduces an agent abstraction where you can “define once, deploy everywhere”. How does this differ from existing agent frameworks like LangChain or AutoGPT? What specific pain points did you observe in production that led to this design?* Human-in-the-Loop at Scale: The tool approval system with needsApproval: true gates actions until human confirmation. How do you envision this working at scale for companies with thousands of agent executions? What's the queue management and escalation strategy?* Type Safety Across Models: AI SDK 6 promises “end-to-end type safety across models and UI”. Given that different LLMs have varying capabilities and output formats, how do you maintain type guarantees when swapping between providers like OpenAI, Anthropic, or Mistral?Workflow Development Kit (WDK)* Durability as Code: The use workflow primitive makes any TypeScript function durable with automatic retries, progress persistence, and observability. What's happening under the hood? Are you using event sourcing, checkpoint/restart, or a different pattern?* Infrastructure Provisioning: Vercel automatically detects when a function is durable and dynamically provisions infrastructure in real-time. What signals are you detecting in the code, and how do you determine the optimal infrastructure configuration (queue sizes, retry policies, timeout values)?Vercel Agent (beta)* Code Review Validation: The Agent reviews code and proposes “validated patches”. What does “validated” mean in this context? Are you running automated tests, static analysis, or something more sophisticated?* AI Investigations: Vercel Agent automatically opens AI investigations when it detects performance or error spikes using real production data. What data sources does it have access to? How does it distinguish between normal variance and actual anomalies?Python Support (For the first time, Vercel now supports Python backends natively.)Marketplace & Agent Ecosystem* Agent Network Effects: The Marketplace now offers agents like CodeRabbit, Corridor, Sourcery, and integrations with Autonoma, Braintrust, Browser Use. How do you ensure these third-party agents can't access sensitive customer data? What's the security model?“An Agent on Every Desk” Program* Vercel launched a new program to help companies identify high-value use cases and build their first production AI agents. It provides consultations, reference templates, and hands-on support to go from idea to deployed agentFull Video EpisodeTimestamps00:00 Introduction and Malte's Background at Google01:16 Vercel's AI Engineering Philosophy and Ship AI Recap03:19 Deep Dive: Workflows vs Agents Architecture09:33 AI SDK Success Story: Staying Low-Level and Humble16:35 Framework Design Principles and Open Source Strategy19:20 Vercel Agent: AI-Powered DevOps and Anomaly Detection27:06 Internal Agent Use Cases: Lead Qualification and Abuse Analysis29:49 Agent on Every Desk Program and Enterprise Adoption32:13 Python Support and Multi-Language Infrastructure39:42 The Future of AI-Native Security and Development Get full access to Latent.Space at www.latent.space/subscribe

In this conversation with Malte Ubl, CTO of Vercel (http://x.com/cramforce), we explore how the company is pioneering the infrastructure for AI-powered development through their comprehensive suite of tools including workflows, AI SDK, and the newly announced agent ecosystem. Malte shares insights into Vercel's philosophy of "dogfooding" - never shipping abstractions they haven't battle-tested themselves - which led to extracting their AI SDK from v0 and building production agents that handle everything from anomaly detection to lead qualification. The discussion dives deep into Vercel's new Workflow Development Kit, which brings durable execution patterns to serverless functions, allowing developers to write code that can pause, resume, and wait indefinitely without cost. Malte explains how this enables complex agent orchestration with human-in-the-loop approvals through simple webhook patterns, making it dramatically easier to build reliable AI applications. We explore Vercel's strategic approach to AI agents, including their DevOps agent that automatically investigates production anomalies by querying observability data and analyzing logs - solving the recall-precision problem that plagues traditional alerting systems. Malte candidly discusses where agents excel today (meeting notes, UI changes, lead qualification) versus where they fall short, emphasizing the importance of finding the "sweet spot" by asking employees what they hate most about their jobs. The conversation also covers Vercel's significant investment in Python support, bringing zero-config deployment to Flask and FastAPI applications, and their vision for security in an AI-coded world where developers "cannot be trusted." Malte shares his perspective on how CTOs must transform their companies for the AI era while staying true to their core competencies, and why maintaining strong IC (individual contributor) career paths is crucial as AI changes the nature of software development. What was launched at Ship AI 2025: AI SDK 6.0 & Agent Architecture Agent Abstraction Philosophy: AI SDK 6 introduces an agent abstraction where you can "define once, deploy everywhere". How does this differ from existing agent frameworks like LangChain or AutoGPT? What specific pain points did you observe in production that led to this design? Human-in-the-Loop at Scale: The tool approval system with needsApproval: true gates actions until human confirmation. How do you envision this working at scale for companies with thousands of agent executions? What's the queue management and escalation strategy? Type Safety Across Models: AI SDK 6 promises "end-to-end type safety across models and UI". Given that different LLMs have varying capabilities and output formats, how do you maintain type guarantees when swapping between providers like OpenAI, Anthropic, or Mistral? Workflow Development Kit (WDK) Durability as Code: The use workflow primitive makes any TypeScript function durable with automatic retries, progress persistence, and observability. What's happening under the hood? Are you using event sourcing, checkpoint/restart, or a different pattern? Infrastructure Provisioning: Vercel automatically detects when a function is durable and dynamically provisions infrastructure in real-time. What signals are you detecting in the code, and how do you determine the optimal infrastructure configuration (queue sizes, retry policies, timeout values)? Vercel Agent (beta) Code Review Validation: The Agent reviews code and proposes "validated patches". What does "validated" mean in this context? Are you running automated tests, static analysis, or something more sophisticated? AI Investigations: Vercel Agent automatically opens AI investigations when it detects performance or error spikes using real production data. What data sources does it have access to? How does it distinguish between normal variance and actual anomalies? Python Support (For the first time, Vercel now supports Python backends natively.) Marketplace & Agent Ecosystem Agent Network Effects: The Marketplace now offers agents like CodeRabbit, Corridor, Sourcery, and integrations with Autonoma, Braintrust, Browser Use. How do you ensure these third-party agents can't access sensitive customer data? What's the security model? "An Agent on Every Desk" Program Vercel launched a new program to help companies identify high-value use cases and build their first production AI agents. It provides consultations, reference templates, and hands-on support to go from idea to deployed agent

Back in August Alan talked with guests Julianne O'Connor and Michael Keeter, the founders of Influential Dental. They discussed the company's efforts to elevate the dental space through its Influential Dental Podcast and the glossy lifestyle magazine, Influence Eleve. Julianne and Michael emphasize that their focus is on the authentic human element and the non-clinical stories of dentists—highlighting their journeys, mentors, and the challenges they've overcome—rather than the negative connotations of the "influencer" label. Alan discusses his history with audio and the evolution of the Dental Hacks podcast, contrasting his audio-first approach with the increasing trend of video content. They also touch on the challenges of print media in the digital age, the creative process behind their respective content, and the surprising utility of AI in podcast production. Some links from the show: Influential Dental Podcast Influential Dental Instagram Influence Eleve magazine Join the Very Dental Facebook group using the password "Timmerman," Hornbrook" or "McWethy," "Papa Randy," "Lipscomb" or "Gary!" The Very Dental Podcast network is and will remain free to download. If you'd like to support the shows you love at Very Dental then show a little love to the people that support us! -- Crazy Dental has everything you need from cotton rolls to equipment and everything in between and the best prices you'll find anywhere! If you head over to verydentalpodcast.com/crazy and use coupon code “VERYDENTAL10” you'll get another 10% off your order! Go save yourself some money and support the show all at the same time! -- The Wonderist Agency is basically a one stop shop for marketing your practice and your brand. From logo redesign to a full service marketing plan, the folks at Wonderist have you covered! Go check them out at verydentalpodcast.com/wonderist! -- Enova Illumination makes the very best in loupes and headlights, including their new ergonomic angled prism loupes! They also distribute loupe mounted cameras and even the amazing line of Zumax microscopes! If you want to help out the podcast while upping your magnification and headlight game, you need to head over to verydentalpodcast.com/enova to see their whole line of products! -- CAD-Ray offers the best service on a wide variety of digital scanners, printers, mills and even  their very own browser based design software, Clinux! CAD-Ray has been a huge supporter of the Very Dental Podcast Network and I can tell you that you'll get no better service on everything digital dentistry than the folks from CAD-Ray. Go check them out at verydentalpodcast.com/CADRay!  

Hamel Husain and Shreya Shankar teach the world's most popular course on AI evals and have trained over 2,000 PMs and engineers (including many teams at OpenAI and Anthropic). In this conversation, they demystify the process of developing effective evals, walk through real examples, and share practical techniques that'll help you improve your AI product.What you'll learn:1. WTF evals are2. Why they've become the most important new skill for AI product builders3. A step-by-step walkthrough of how to create an effective eval4. A deep dive into error analysis, open coding, and axial coding5. Code-based evals vs. LLM-as-judge6. The most common pitfalls and how to avoid them7. Practical tips for implementing evals with minimal time investment (30 minutes per week after initial setup)8. Insight into the debate between “vibes” and systematic evals—Brought to you by:Fin—The #1 AI agent for customer serviceDscout—The UX platform to capture insights at every stage: from ideation to productionMercury—The art of simplified finances—Where to find Shreya Shankar• X: https://x.com/sh_reya• LinkedIn: https://www.linkedin.com/in/shrshnk/• Website: https://www.sh-reya.com/• Maven course: https://bit.ly/4myp27m—Where to find Hamel Husain• X: https://x.com/HamelHusain• LinkedIn: https://www.linkedin.com/in/hamelhusain/• Website: https://hamel.dev/• Maven course: https://bit.ly/4myp27m—In this episode, we cover:(00:00) Introduction to Hamel and Shreya(04:57) What are evals?(09:56) Demo: Examining real traces from a property management AI assistant(16:51) Writing notes on errors(23:54) Why LLMs can't replace humans in the initial error analysis(25:16) The concept of a “benevolent dictator” in the eval process(28:07) Theoretical saturation: when to stop(31:39) Using axial codes to help categorize and synthesize error notes(44:39) The results(46:06) Building an LLM-as-judge to evaluate specific failure modes(48:31) The difference between code-based evals and LLM-as-judge(52:10) Example: LLM-as-judge(54:45) Testing your LLM judge against human judgment(01:00:51) Why evals are the new PRDs for AI products(01:05:09) How many evals you actually need(01:07:41) What comes after evals(01:09:57) The great evals debate(1:15:15) Why dogfooding isn't enough for most AI products(01:18:23) OpenAI's Statsig acquisition(1:23:02) The Claude Code controversy and the importance of context(01:24:13) Common misconceptions around evals(1:22:28) Tips and tricks for implementing evals effectively(1:30:37) The time investment(1:33:38) Overview of their comprehensive evals course(1:37:57) Lightning round and final thoughts—LLM Log Open Codes Analysis Prompt:Please analyze the following CSV file. There is a metadata field which has an nested field called z_note that contains open codes for analysis of LLM logs that we are conducting. Please extract all of the different open codes. From the _note field, propose 5-6 categories that we can create axial codes from.—Referenced:• Building eval systems that improve your AI product: https://www.lennysnewsletter.com/p/building-eval-systems-that-improve• Mercor: https://mercor.com/• Brendan Foody on LinkedIn: https://www.linkedin.com/in/brendan-foody-2995ab10b• Nurture Boss: https://nurtureboss.io/• Braintrust: https://www.braintrust.dev/• Andrew Ng on X: https://x.com/andrewyng• Carrying Out Error Analysis: https://www.youtube.com/watch?v=JoAxZsdw_3w• Julius AI: https://julius.ai/• Brendan Foody on X—“evals are the new PRDs”: https://x.com/BrendanFoody/status/1939764763485171948• Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences: https://dl.acm.org/doi/abs/10.1145/3654777.3676450• Lenny's post on X about evals: https://x.com/lennysan/status/1909636749103599729• Statsig: https://statsig.com/• Claude Code: https://www.anthropic.com/claude-code• Cursor: https://cursor.com/• Occam's razor: https://en.wikipedia.org/wiki/Occam%27s_razor• Frozen: https://www.imdb.com/title/tt2294629/• The Wire on HBO: https://en.wikipedia.org/wiki/The_Wire—Recommended books:• Pachinko: https://www.amazon.com/Pachinko-National-Book-Award-Finalist/dp/1455563935• Apple in China: The Capture of the World's Greatest Company: https://www.amazon.com/Apple-China-Capture-Greatest-Company/dp/1668053373/• Machine Learning: https://www.amazon.com/Machine-Learning-Tom-M-Mitchell/dp/1259096955• Artificial Intelligence: A Modern Approach: https://www.amazon.com/Artificial-Intelligence-Modern-Approach-Global/dp/1292401133/Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email podcast@lennyrachitsky.com.—Lenny may be an investor in the companies discussed.My biggest takeaways from this conversation: To hear more, visit www.lennysnewsletter.com